Skip to main content
Atlassian MCP logo
  • Category: model context protocol
  • Auth: DCR_OAUTH
  • Composio-managed OAuth available? No
  • Tools: 213
  • Triggers: 0
  • Slug: ATLASSIAN_MCP
  • Version: 20261026_00

Tools

Slug: ATLASSIAN_MCP_ADD_CONFLUENCE_CONTENT_PERMISSIONSAdds one or more content-level permission grants to a single Confluence content entity. Existing grants for other principals are preserved; to replace the full set, use replaceConfluenceContentPermissions instead.These are Specific access grants: operation read = Can view; update = Can edit and already includes view. A principal has exactly ONE level, so assigning read to a principal who currently has update is a downgrade to view-only. Never include the same principal under both operations. Adding a grant does NOT restrict others, make content private, or change General access; use setConfluenceContentRestrictionState for that baseline. Private creation already gives the creator update. Do not add read for that creator, because update already includes view. Existing-state and self-lockout rules are enforced by the Confluence monolith.Each grant pairs an operation with a list of principals. Pass the grants via the permissions input, an array of objects shaped exactly like: [ { “operation”: “read”, “principals”: [ { “principalType”: “user”, “principalId”: “<atlassian-account-id>” }, { “principalType”: “group”, “principalId”: “<group-id>” } ] } ] Enums: operation is one of read | update; principalType is one of user | group. For a user, principalId is the Atlassian account ID; for a group, principalId is the group ID.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric ID of the Confluence content entity (page, blog post, whiteboard, database, folder, etc.) to add permission grants to.
array
required
Permission grants to add. Array of objects, each with an operation (read | update) and a principals array. Each principal has a principalType (user | group) and a principalId (Atlassian account ID for a user, group ID for a group). A principal must appear under only one operation across the entire request. Example: [{ “operation”: “read”, “principals”: [{ “principalType”: “user”, “principalId”: “5b10a…” }] }].
Slug: ATLASSIAN_MCP_ADD_CONFLUENCE_REACTIONAdd emoji reaction to Confluence content

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Emoji ID as hex codepoint (e.g. 1f44d for 👍, 1f624 for 😤) or custom emoji UUID.
string
required
Numeric Confluence content ID (page, blog post, or comment).
Slug: ATLASSIAN_MCP_ADD_CONNECTIONS_TO_GOALSAdd one type of connection to one or more Atlassian Goals.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
array
required
Goal ARIs to connect. The number of Goals multiplied by the number of targets must not exceed 50.
object
required
Connection type and targets to add. Provide { “type”: “<type>”, “targets”: […] }. Supported types are TAG, FOLLOWER, TEAM, PROJECT, and JIRA_WORK_ITEM. TAG targets contain exactly one tag id or name. FOLLOWER targets contain an Atlassian account id. All other targets contain the target ARI in id.
Slug: ATLASSIAN_MCP_ADD_CONNECTIONS_TO_PROJECTSAdd one type of connection to one or more Atlassian Projects.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
object
required
Connection type and targets to add. Provide { “type”: “<type>”, “targets”: […] }. Supported types are TAG, FOLLOWER, USER_CONTRIBUTOR, TEAM_CONTRIBUTOR, GOAL, JIRA_WORK_ITEM, and EXTERNAL_LINK. TAG targets contain exactly one tag id or name. FOLLOWER and USER_CONTRIBUTOR targets contain an Atlassian account id. Other ID-based targets contain the target ARI in id. EXTERNAL_LINK targets contain a url and may include a name.
array
required
Project ARIs to connect. The number of Projects multiplied by the number of targets must not exceed 50.
Slug: ATLASSIAN_MCP_ADD_GRAPH_CONTEXTAdds a relationship between two entities in the Teamwork Graph (e.g. linking two Jira work items, marking one as blocking another, attaching a remote link, or connecting a Jira work item to an Atlas project or goal).

Input Parameters

string
Optional display label for the target. Used by relationships that surface a title (e.g. remote links); ignored otherwise.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Identifier of the source entity. Accepts an ARI, a full URL, or a stable key (e.g. ENG-123 for a Jira work item). Format depends on relationshipType.
string ("jira-work-item-links-jira-work-item" | "jira-work-item-blocks-jira-work-item" | "jira-work-item-links-jira-work-item-remote-link" | "jira-work-item-tracks-atlassian-project" | "jira-work-item-contributes-to-atlassian-goal")
required
Type of relationship to create. Determines which entity types ‘objectIdentifier’ and ‘targetObjectIdentifier’ must resolve to.
string
required
Identifier of the target entity. Accepts an ARI, a full URL, or a stable key (e.g. ATLAS-20426 for an Atlas project). Format depends on relationshipType.
Slug: ATLASSIAN_MCP_ADD_LABELS_TO_CONFLUENCE_CONTENTAdd labels to any Confluence content (page, blogpost, attachment, custom content)

Input Parameters

array
required
Labels to add. Provide 1-50 entries. Each array item is an object: { “name”: ”…”, “prefix”: “global” | “my” | “team” }. name is required, non-blank, at most 255 characters, and cannot contain whitespace. prefix is optional and defaults to “global” server-side.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric Confluence content id (page / blogpost / attachment / custom content)
Slug: ATLASSIAN_MCP_ADD_OR_EDIT_JIRA_ISSUE_COMMENTAdd a comment to a Jira issue, or edit an existing one: omit commentId to add, or pass one from listJiraIssueComments to edit. Returns the commentId, needed to edit or delete it later. When no file was appended through inlineFileId, it also returns the echoed body and its format (appliedContentFormat).

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
ID of an existing comment to edit. When omitted, a new comment is added.
string
Comment text. Markdown by default; set contentFormat: html to pass HTML instead. Required unless adding a new comment purely to embed a file via inlineFileId. Editing replaces the whole comment body: pass the full intended text (fetch the current comment first to preserve it), or "" for media only. Editing a body that already contains inline media must use contentFormat: html — markdown drops it. For HTML body shapes (inline media, panels, tables), first get the format guide via the generic operation runner (execute) as name=getContentFormatGuide, inputs={toolName: “addOrEditJiraIssueComment”}.
array
Media file ID(s) from uploadAttachmentToJiraIssue to append inline to the comment, e.g. [“id1”,“id2”]. Requires contentFormat: html and a matching inlineFileCollection (paired by index). Appends at the end; for exact placement, author the media node in the HTML commentBody instead. A file already embedded in the body is rejected (would duplicate).
string
required
Issue key (e.g. PROJ-123) or a Jira issue URL
string ("markdown" | "html")
Body format for commentBody. Defaults to markdown. html preserves inline media across a read-modify-write; a body fetched as HTML can be written straight back (Jira resolves media collection/filename server-side and omits them on read — not data loss). Requires the HTML content-format feature; when it is disabled the call is rejected rather than downgraded, because markdown would store the HTML tags as literal text and drop the media.
array
Optional file name(s) (from the upload step’s fileName), paired to inlineFileId by index. Only selects the render shape: images render as a block image, other files as an inline chip. Omit to default to the image shape.
string ("internalNote" | "publicComment")
JSM comment type. Use internalNote for an internal note or publicComment for a customer-visible comment. Applies when adding or editing a JSM comment. Omit for existing Jira behavior.
object
Restrict comment visibility to a Jira group or role. Shape: {"type":"group"&#124;"role","value":"<name>"}. Role and group names are site-specific, so do not reuse a name from another site. On JSM this does not make a comment internal — a restricted comment stays customer-visible (jsdPublic: true). Use jsmCommentType: "internalNote" for that.
array
Media collection(s) from the upload step, paired to inlineFileId by index (a single value applies to all). Required whenever inlineFileId is set.
string ("markdown" | "html")
Format of the echoed comment body. Defaults to the format written, so an html write reads back as html. Bodies markdown cannot represent (media, panels, statuses, @mentions) are always echoed as HTML so a follow-up edit does not destroy them. An explicit markdown request is overridden for those bodies, with a warning saying so; appliedContentFormat in the response reports the format you actually got.
Slug: ATLASSIAN_MCP_ADD_OR_EDIT_JIRA_ISSUE_WORKLOGLog time spent on a Jira issue, or edit an existing worklog: omit worklogId to add, or pass one from listJiraIssueWorklogs to edit, which changes only the fields you pass. A new worklog is always logged as the calling user; an edit keeps its original author. Jira reduces the issue’s remaining estimate by the time logged (by the difference on an edit). To change the estimate itself, use editJiraIssue. Returns the worklog’s id, needed to edit it later, with the stored timeSpent and started.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Work description (markdown by default, or HTML with contentFormat html; converted to ADF automatically)
string
Start time in ISO 8601 format (e.g. 2026-01-01T09:00:00.000+0000)
string
Time spent like 2h 30m. Required when adding; optional when editing.
string
ID of an existing worklog to edit. When omitted, a new worklog is added.
object
Restrict the worklog to a Jira group or role. Shape: {"type":"group"&#124;"role","value":"<name>"}. Examples: {"type":"role","value":"Administrators"}, {"type":"group","value":"jira-software-users"}. When omitted, the worklog is visible to everyone who can view the issue.
string
required
Issue key like PROJ-123
string ("markdown" | "html")
Body format for comment. Defaults to markdown. html preserves inline media across a read-modify-write: a note fetched from listJiraIssueWorklogs as html can be written straight back. For HTML body shapes, first get the format guide via the generic operation runner (execute) as name=getContentFormatGuide, inputs={toolName: “addOrEditJiraIssueWorklog”}. Requires the HTML content-format feature; when it is disabled the call is rejected rather than downgraded, because markdown would store the HTML tags as literal text.
Slug: ATLASSIAN_MCP_APPROVE_JSM_REQUEST_RESOLVER_PLANSApprove the current Request Resolver plans for explicitly selected JSM issue keys after the user has reviewed their plans with getJsmRequestResolverPlans and confirmed approval. Approval applies to each request’s current plan at execution time, which may have changed since retrieval. The caller must be the request’s human assignee or delegator. Returns one result per input in order; approved means approval was accepted, not that execution is complete. Output fields include requests[].issueKey, requests[].status, and approver.displayName; use these paths when selecting responseFields. Duplicate keys for the same request are submitted once per call. This is not idempotent across calls. For an unknown outcome, refresh the plan before any further approval; never automatically retry approval. Use getJsmRequestResolverPlans to check subsequent execution status. Does not decide customer-portal approvals.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
array
required
One to five issue keys selected for approval, for example HELP-123. Use the issueIdOrKey values from getJsmRequestResolverPlans when retrieving by key.
Slug: ATLASSIAN_MCP_ARCHIVE_CONFLUENCE_CONTENTArchive a single Confluence content entity

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric ID of the Confluence content to archive.
Slug: ATLASSIAN_MCP_ATLASSIAN_USER_INFOReturns the accountId of the current user
Slug: ATLASSIAN_MCP_COMPLETE_CONFLUENCE_TASKMark a Confluence inline task as complete

Input Parameters

string
required
The ID of the Confluence inline task to mark complete.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
Slug: ATLASSIAN_MCP_CONVERT_CONFLUENCE_CONTENT_MODEConvert a Confluence page or live doc between classic page mode and live-doc mode

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Numeric Confluence content ID. Provide either contentId or contentUrl.
string
Full Confluence content URL. Provide either contentUrl or contentId.
string ("page" | "live_doc")
required
Target mode to convert the content into.
Slug: ATLASSIAN_MCP_CONVERT_JIRA_ISSUE_HIERARCHYConvert an existing Jira issue across hierarchy levels: a standard issue (Task, Bug, Story) into a sub-task under a parent, or a sub-task back into a standard issue. Mirrors Jira’s Move / Convert-to-sub-task wizard: preview destination compatibility (mode=preview_step1), preview field retain/remap/drop (mode=preview_step2), then execute (mode=confirm). Do not use this for same-level type edits such as Bug → Story — use editJiraIssue for those. Task → Sub-task: always ask the user for parentIssueKey before calling. Do not search for, infer, or pick a parent. If they did not name a parent, ask them instead of calling this tool. The parent must be a standard issue. If this result has CHILD_ISSUES_WILL_REPARENT, those children will get the same new parent — ask the user to accept that, then confirm with acknowledgeChildReparent=true. If this result has SOURCE_HAS_SUBTASKS, the convert is blocked; tell the user that. If this result has MOVE_PERMISSION_REQUIRED, the user lacks Jira Bulk change or Move permission — tell them to convert in the Jira UI. Do not retry. Do not mention another project style. If preview execution.method is bulk-move, or confirm returns MOVE_CONFIRMATION_REQUIRED, this is Jira’s Move wizard: list the destination project, statusMapping, and fieldPlan.dropped to the user and ask them to accept that status change and that those fields will be dropped. Do not convert until they accept, then retry with mode=confirm and acknowledgeMove=true. If they decline, stop. Sub-task → Task: no parent needed; confirm clears the parent. After convert, reply with this issue’s key, new type, and parent. If appliedChanges.dropped is present, also name those dropped fields. If appliedChanges.status is present, also name that status change. Do not mention bulk-move permissions or project-style notes unless this result has MOVE_PERMISSION_REQUIRED.

Input Parameters

string ("preview_step1" | "preview_step2" | "confirm")
preview_step1 (default) returns destination compatibility without converting. preview_step2 adds the field retain/remap/drop plan. confirm executes the conversion. Omitting mode never mutates.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
boolean
When true, executes the conversion (same as mode=confirm). Prefer mode=confirm. Preview modes never convert, even if confirm is false.
object
Optional values for fields that are required on the destination type and empty or incompatible on the source. Keys may be field names or customfield_* IDs. Call mode=preview_step2 first to see fieldPlan.requiresInput.
string
required
Issue key or ID to convert (e.g. PROJ-123).
string
Parent issue key required when converting a standard issue into a sub-task. The user must provide this key — do not search for, infer, or pick a parent, including from other issues in the same project. The parent must be a standard issue in the destination project. Ignored when promoting a sub-task to a standard type.
boolean
Required as true on mode=confirm when this conversion uses Jira’s Move instead of a direct issue edit (preview execution.method is bulk-move, or confirm returned MOVE_CONFIRMATION_REQUIRED). After preview, show the destination project, statusMapping, and any fieldPlan.dropped names and only set this after the user accepts that status change and that those fields will be dropped. Not needed when a same-project convert succeeds via a direct issue edit.
string
required
Destination issue type name or ID. Use a sub-task type to demote a standard issue, or a standard type (Task, Bug, Story) to promote a sub-task. Same-level changes (Bug → Story) are rejected.
string
Optional destination project key. Omit to convert in the issue’s current project. A different project uses Jira’s bulk move API for this single issue (requires global Bulk change plus Move/Create issue permissions).
boolean
Required as true on mode=confirm when converting a team-managed issue that already has child sub-tasks. Those children become sub-tasks of the same new parentIssueKey (Jira does not nest sub-tasks). After preview, show CHILD_ISSUES_WILL_REPARENT and only set this after the user accepts that. Ignored on company-managed projects (those conversions are blocked) and when the source has no children.
Slug: ATLASSIAN_MCP_COPY_CONFLUENCE_CONTENTCopy a Confluence page, whiteboard, database, folder, or embed to a new parent

Input Parameters

string
required
Explicit title for the copied content (1–255 chars).
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
ID of the source Confluence content entity to copy. Numeric content ID (up to 19 digits).
string
ID of the parent content entity to copy under. Provide this OR destinationSpaceKey, not both. Numeric content ID (up to 19 digits).
string
Key of the destination space to copy to the root of. Provide this OR parentContentId, not both.
Slug: ATLASSIAN_MCP_CREATE_ARTIFACTS_UPLOADStep 1 of 2 for uploading a new artifact or a new version of an existing artifact. Creates an upload and returns a pre-signed URL and instructions for transferring the file’s bytes directly. After the upload completes, call publishArtifact (step 2) with the returned completionPayload.contentId and artifact metadata to finalize and get the share URL. This does not publish the artifact by itself. Requires code execution and HTTP upload capability.

Input Parameters

integer
required
Exact byte length of the final upload, not its character count. Calculate with wc -c < "$file"; never estimate. Equivalent Python, Node, or browser code is valid; encode text as UTF-8 before counting and hashing.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Base64-encoded SHA-256 digest of the exact bytes to upload, not hexadecimal. Calculate with openssl dgst -sha256 -binary "$file" &#124; openssl base64 -A or shasum -a 256 < "$file" &#124; awk '{print $1}' &#124; xxd -r -p &#124; base64. Equivalent Python, Node, or browser code is valid. Hash the same unchanged bytes used for length and the subsequent upload.
Slug: ATLASSIAN_MCP_CREATE_ARTIFACT_THUMBNAIL_UPLOADCreate a thumbnail for an artifact using an image generated locally or supplied by the user. Use only when the user explicitly requests a thumbnail. Requires artifact ownership and applies to the latest version. Creates a thumbnail only when none exists for that version. Overwriting, replacing, or regenerating an existing thumbnail is not supported. For HTML and PDF, use a static 672-by-400 PNG (1.68:1), capturing rendered HTML and a representative animation frame, or the first PDF page. Returns a pre-signed URL and instructions for uploading the image. No publishArtifact call is needed.

Input Parameters

string
required
Artifact ID returned by publishArtifact or listArtifacts, for which the user explicitly requested a new thumbnail. Use the artifact ID, not a content ID or thumbnail ID.
integer
required
Exact byte length of the final PNG; never estimate.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Base64-encoded SHA-256 digest of the exact PNG bytes, not hexadecimal.
Slug: ATLASSIAN_MCP_CREATE_CAPACITY_PLAN_NON_PROJECT_WORKCreate a non-project work item in Individual Capacity Planning. “Non-project work” is a bucket of time that is not a Jira issue or an Atlas project, such as Leave, Run the Business (RtB), on-call, or training. USE WHEN the user asks to create a new non-project work item, or a category of work that does not already exist as a Jira issue or Atlas project. Search first with listCapacityPlanNonProjectWork to avoid creating a duplicate - the match is on name and is case-insensitive. Non-project work is owned by Capacity Planning and exists nowhere else in Atlassian, so it can only be created through this tool. A contributor must be supplied: the new work item is created together with a work association for that person, so it is immediately allocatable to them. Allocate additional people or set the effort per period afterwards with updateCapacityPlanAllocations, using the ARI returned here as workId. On success, nonProjectWork contains the created item’s name and ari - use that ari as workId for updateCapacityPlanAllocations rather than fabricating one.

Input Parameters

string
required
Display name for the new non-project work item, e.g. “Leave” or “Run the Business”. Search first with listCapacityPlanNonProjectWork to avoid creating a duplicate of an existing item.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
ARI of the contributor to associate the new work item with, in the form ari:cloud:identity::user/{accountId} where {accountId} is an Atlassian account ID (e.g. ari:cloud:identity::user/5ea00a99d31fdf0c0d783dd5). The work item is created with a work association for this person so it is immediately allocatable to them.
Slug: ATLASSIAN_MCP_CREATE_CONFLUENCE_ATTACHMENTPrepare a Confluence attachment upload and return a local curl command

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Optional attachment version comment to include in the returned uploadCommand.
number
Optional local file size in bytes. Used by Confluence to fail fast if the file is too large.
string
required
Numeric ID of the Confluence content that will own the attachment. Confluence content IDs are int64 values (max 19 digits).
string
required
Absolute or relative local file path to upload. This is used only to build uploadCommand; it is not sent to Confluence during prepare.
Slug: ATLASSIAN_MCP_CREATE_CONFLUENCE_COMMENTCreate or reply to a comment on a Confluence page or blog post

Input Parameters

object
required
Comment body object. Use { “format”: “markdown” | “html”, “value”: ”…” }. format is required and must be “markdown” or “html”; value is required, non-empty, and at most 4096 characters.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Page or blog post ID. Required for top-level comments. Omit for replies.
string ("footer" | "inline")
Top-level comment type: “footer” for page-level comments or “inline” for anchored comments. Required for top-level comments; inferred for replies.
object
Required only for top-level inline comments. Omit for replies. Object shape: { “selectedText”: ”…”, “matchIndex”: 0, “matchCount”: 1 }. selectedText is required and non-empty; matchIndex is required and zero-based; matchCount is required and must be at least 1.
string
ID of a top-level comment to reply to. Required for replies. Must reference a top-level comment, not a reply. When set, omit contentId and commentType.
Slug: ATLASSIAN_MCP_CREATE_CONFLUENCE_CONTENTCreate a new Confluence page, blog post, live doc, whiteboard, database, embed, smart link, or folder.Before choosing body.format or authoring a body, call getContentFormatGuide through execute with name=getContentFormatGuide and inputs={toolName}. Use createConfluencePage for pages, blog posts, and live docs; createConfluenceWhiteboard for whiteboards; or createConfluenceDatabase for databases.Space instructions describe how to author content in a Confluence space. Apply relevant guidance to the content you create or update. Follow this decision rule:
  1. Before authoring, call getConfluenceSpace for the target space unless getConfluenceContent returned metadata.hasSpaceInstructions=false for content in that space. If getConfluenceSpace already returned for the same cloudId and space during the current task, reuse its spaceInstructions and do not call it again.
  2. When the value is true or unknown and instructions have not been loaded, you must call getConfluenceSpace once before authoring through execute with name=getConfluenceSpace, top-level cloudId, and inputs={spaceIdOrKey}.
  3. Apply any returned spaceInstructions. If a successful response omits them, no instructions are configured; author with defaults and do not block.
After a successful getConfluenceSpace call, do not make a separate getConfluenceSpaceInstructions call.

Input Parameters

object
Before composing this body, follow the space-instruction decision rule in the tool description. Reuse known instruction state and do not repeat the space lookup per write. Body content. For whiteboard and database it is technically optional, but only omit it when the user explicitly asked for an empty/blank board or database. Never omit body as a fallback because you could not load the authoring guidance — load it first via getContentFormatGuide through the generic operation runner (execute) as name=getContentFormatGuide, inputs={toolName} (createConfluencePage / createConfluenceWhiteboard / createConfluenceDatabase), then build a real body. A blank whiteboard (no shapes, stickies, connectors, or layout) is almost never the intended result. For doc types (page, live_doc, blogpost): format is html or markdown, value is the content string. Prefer HTML. Use markdown only when you are confident the content needs only basic text formatting and has no rich Confluence elements to create, such as panels, layouts, media, whiteboard embeds, or Remixes. If unsure, use HTML. For embed and smart_link: format must be url, value must be the URL to embed (e.g. https://example.com/design). For whiteboard: format must be svg and value must be the complete initial SVG document with root width, height, and viewBox. For database: format must be csv and value must be the complete initial CSV payload. For a synced (Smart) Folder (contentType=folder): format must be url and value must be the https URL of the external Google Drive, OneDrive, or SharePoint folder to sync from. Requires the confluence_smart_folders_milestone_1 experiment; otherwise the create returns FEATURE_NOT_ENABLED. Do not pass patches, edit envelopes, or context on create. Omit for a plain folder (no sync source) and for slide.
boolean
If true, create the content as a draft instead of publishing it. Only supported when contentType is page or blogpost.
string
required
Title for the new content. 1-255 characters.
object
required
Parent destination for the new content. Use { “spaceId”: “<numeric-space-id>” } to create at the homepage / sidebar root. Use { “spaceId”: “<numeric-space-id>”, “parentContentId”: “<numeric-content-id>” } to create under an existing content item. Use { “parentContentId”: “<numeric-content-id>” } when the parent content ID should be resolved to its space before creation. Use { “parentContentUrl”: “<confluence-content-url>” } when the parent content URL should be resolved before creation. Supported parentContentUrl paths include /pages/{id}, /blog/{id}, /whiteboard/{id}, /database/{id}, and /folder/{id}. If the destination is described only by space key or title, resolve it first to one of the supported parent shapes above.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
boolean
If true, the created content is private to the caller: only the creator has view and edit access. Supported for page, live_doc, blogpost, whiteboard, database, and folder, including creation at the homepage / sidebar root. Private creation is not supported for embed, smart_link, or slide. This sets General access to VIEW_RESTRICTED and gives the creator one Specific access grant, update (Can edit), which already includes read/view. Do not add a separate read grant for the creator. Omit or pass false for default visibility.
string
required
Type of content to create. One of: page, live_doc, blogpost, whiteboard, database, embed, smart_link, folder, slide.
string ("narrow" | "wide" | "max")
Optional page width for doc types only: page, live_doc, and blogpost. Omit unless the user explicitly requests a width; omission creates a narrow page. Do not infer wide or max from body content or layout. Accepted values are narrow, wide, and max. Non-doc content types do not support this field.
Slug: ATLASSIAN_MCP_CREATE_CONFLUENCE_INFOGRAPHIC_FOR_PAGECreate an infographic in a page workflow. Use only when a Confluence page creation or editing skill or guided workflow selects it; never as a standalone tool. Returns a media reference for embedding, which may sync later. Before prompting, reuse the shared Remix guide (headed ## Remix embeds) if its text is in your current context. Only if missing, call getContentFormatGuide with toolName=createConfluenceInfographicForPage and follow its Remix guidance. Generation and billing finish asynchronously; typical cost is 15–30 Rovo credits. Download detailed billing data for final usage; match any returned correlationId and usageUniqueId.

Input Parameters

string
Optional visual theme for the infographic.
string
required
Self-contained description of the infographic to generate.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric ID of the existing Confluence page that will own and embed the infographic (content type: page or live_doc only).
string ("1:1" | "4:3" | "3:2" | "16:9" | "21:9" | "3:4" | "2:3" | "9:16")
Optional output aspect ratio.
Slug: ATLASSIAN_MCP_CREATE_CONFLUENCE_MAUI_APPCreate a Maui app in a page workflow. Use only when a Confluence page creation or editing skill or guided workflow selects it; never as a standalone tool. Returns a reserved app ID and embed URL for the owning page. Before prompting, reuse the shared Remix guide (headed ## Remix embeds) if its text is in your current context. Only if missing, call getContentFormatGuide with toolName=createConfluenceMauiApp and follow its Remix guidance. Generation and billing finish asynchronously; typical cost is 15–30 Rovo credits. Download detailed billing data for final usage; match any returned correlationId and usageUniqueId.

Input Parameters

string
required
This self-contained request must include the source content to remix, including the values and labels that the app must preserve, plus the visualization instructions. Read the source page first when necessary; contentId only identifies the page that will own and embed the app.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric ID of the existing Confluence page that will own and embed the Maui app (content type: page or live_doc only).
Slug: ATLASSIAN_MCP_CREATE_CONFLUENCE_SPACECreate a Confluence space. Successful responses include id, key, and homepageId (the homepage / sidebar root content ID).

Input Parameters

string
Optional short unique key for the new space. Provide either key or alias; alias is required when key is omitted.
string
required
Display name for the new Confluence space.
string
Optional alias used as the space identifier in Confluence page URLs. Provide either alias or key; key is required when alias is omitted.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Optional plain-text description for the new space.
string
Optional Confluence space template key.
array
Exact initial RBAC role assignments for the new space. When provided, default space roles are not applied and at least one Admin role assignment is required. Do not combine with createPrivateSpace or copySpaceAccessConfiguration.
boolean
Set to true only when the user explicitly asks for a private space. Do not combine with roleAssignments or copySpaceAccessConfiguration.
integer
Existing numeric space ID to copy access configuration from. Do not combine with roleAssignments or createPrivateSpace.
Slug: ATLASSIAN_MCP_CREATE_FOCUS_AREACreate a new Focus area in a workspace. Call getFocusAreaTypes first and use an enabled type UUID for focusAreaTypeId — do not fabricate it. Optionally set parentFocusAreaIdentifier (UUID, ARI, or Focus page URL); if set, the parent’s type must be a higher hierarchy level than the type being created. Optionally set startDate and targetDate as { date, confidence } where date is YYYY-MM-DDTHH:mm (e.g. 2026-08-10T00:00; bare dates are not accepted) and confidence is DAY, MONTH, or QUARTER. Omit owner to default to the creating user. Returns the created focus area (identifiers, type, owner, parent, dates, status, health, timestamps). Use getFocusArea for expansions such as aboutContent, statusUpdates, or subFocusAreas. When passing both cloudId and a parent ARI, they must refer to the same site.

Input Parameters

string
required
Name of the new focus area.
string
Optional Atlassian account ID (AAID) of the focus area owner. Defaults to the creating user when omitted.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
object
Projected start date. Object shape: { “date”: “YYYY-MM-DDTHH:mm”, “confidence”: “DAY” | “MONTH” | “QUARTER” }. Both fields required when startDate is set. Example date: 2026-08-10T00:00 — bare calendar dates like 2026-08-10 are not accepted; append T00:00 when only the day is known.
object
Projected target date. Object shape: { “date”: “YYYY-MM-DDTHH:mm”, “confidence”: “DAY” | “MONTH” | “QUARTER” }. Both fields required when targetDate is set. Example date: 2026-08-10T00:00 — bare calendar dates like 2026-08-10 are not accepted; append T00:00 when only the day is known.
string
required
UUID of an enabled Focus area type in the target workspace. Fetch a valid value first with getFocusAreaTypes rather than fabricating it — via execute as name=getFocusAreaTypes when it is not a top-level tool.
string
Optional parent focus area (UUID, ARI, or Focus page URL). If omitted, the new focus area has no parent. When set, the parent’s type must be a higher hierarchy level than focusAreaTypeId (see getFocusAreaTypes).
Slug: ATLASSIAN_MCP_CREATE_FOCUS_AREA_STATUS_UPDATECreate a status update on a focus area, or save it as a draft. A status update is a change to one or more of status, health, summary, target date. Changing status needs an id discovered first with getFocusArea and include.statusTransitions; health does not. Passing only focusAreaIdentifier still posts a visible, empty update when publishing, so never call this tool speculatively. Field-level behavior for status, health, summary, target date, and draft constraints is documented on the inputs.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
boolean
When true, save the status update as a draft instead of publishing it. Drafts do not change the focus area’s live status, health, or target date; transition and target-date values are stored on the draft until published. Requires focusAreaIdentifier to be a focus area ARI. Retrieve a saved draft later with getFocusArea and include.latestDraftUpdate; publish it by calling this tool again without isDraft. Defaults to false (publish).
string
Optional progress summary as plain text or Markdown; it is converted to rich content. Maximum 25,000 characters.
string ("2001" | "2002" | "2003")
The only input that sets health. Health has three fixed values, the same on every site: “2001” for Off track, “2002” for At risk, and “2003” for On track. Pass one of those ids directly — unlike statuses, health is not configurable, so it does not need to be looked up first and will not appear in statusTransitions on sites with configurable statuses. Health applies independently of status, so it can be set on its own, with no status input at all, or alongside a status change. Never pass a health name such as “at risk” here, or into statusTransitionId. Omitting it leaves the current health unchanged; to remove health when publishing, set clearHealth instead.
string
Status to record on a draft. Obtain it by calling getFocusArea with include.statusTransitions and passing status.id of the chosen entry, in whatever form it is returned. Use status.id, not status.key — key is a display slug such as “paused” on some statuses and is not a usable id. Draft only; use statusTransitionId when isDraft is false or omitted. Omit to leave the draft’s status unset.
boolean
The only way to remove a focus area’s health. Set this to true only when asked to clear, remove, or unset health. A status change never implies it: transitions on sites with configurable statuses carry no health object at all, and that absence says nothing about the focus area’s current health, so an ordinary status-only request leaves both this and healthId omitted. Omitting healthId does not clear health — it leaves the current health unchanged — so clearing must be requested explicitly with this field. Cannot be combined with healthId: to change health to a different value, pass healthId instead. Publish only — a draft records whatever healthId it is given, so omitting healthId already leaves a draft with no health.
object
Optional new target date for the focus area. Object shape: { “date”: “YYYY-MM-DDTHH:mm”, “confidence”: “DAY” | “MONTH” | “QUARTER” }. Both fields required when newTargetDate is set. Example date: 2025-07-05T00:00 — bare calendar dates like 2025-07-05 are not accepted; append T00:00 when only the day is known. Omit to leave the existing target date unchanged. See isDraft for draft behavior.
string ("OFF_TRACK" | "AT_RISK" | "ON_TRACK" | "PENDING" | "PAUSED" | "COMPLETED")
Last resort; do not reach for this first. Prefer statusTransitionId (or statusId for drafts): include.statusTransitions returns usable ids on every site, so that path works everywhere, while this legacy vocabulary fails on sites that have adopted configurable statuses. This field is also coarser — each value sets both status and health at once: ON_TRACK, AT_RISK, and OFF_TRACK set health to that value and set status to IN_PROGRESS; PENDING, PAUSED, and COMPLETED set that status and clear health. Cannot be combined with statusTransitionId, statusId, healthId, or clearHealth. Omit to leave the current status and health unchanged. See isDraft for draft behavior.
string
Status transition to apply when publishing. Obtain it by calling getFocusArea with include.statusTransitions and passing the id of the chosen entry. Sets status only: to change health, pass healthId instead, including when health is the only thing being changed. Statuses are configurable per workspace, so this id must come from that lookup for this focus area — never guess it, reuse one from another focus area or site, or pass a status or health name here. Publish only; use statusId when isDraft is true. Omit to leave the current status unchanged.
string
required
The focus area to post the update on. Accepts a focus area UUID, a focus area ARI, or a focus area page URL. Saving a draft (isDraft true) requires a focus area ARI; UUID and URL cannot be used. If only a UUID or URL is known, call getFocusArea first and pass the returned ari. When reusing an identifier from an earlier response, pass its uuid field — not its id field — unless you need the ARI for a draft.
Slug: ATLASSIAN_MCP_CREATE_GOALCreate an Atlassian Goal or Success Measure using an enabled Goal Type.

Input Parameters

string
required
Name of the Goal.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
ARI of an enabled Goal Type returned by getGoalTypes.
object
Projected target date with date and confidence (DAY, MONTH, or QUARTER).
string ("OPEN_EDIT" | "OPEN_VIEW" | "RESTRICTED")
Goal visibility and editing access. Defaults to the site’s Goal access setting.
string
Optional Goal description in plain text or Markdown.
string
ARI of the parent Goal. Required when the selected Goal Type requires a parent.
string
Atlassian account ID of the owner. Defaults to the current user.
Slug: ATLASSIAN_MCP_CREATE_GOAL_UPDATECreate a progress update for an existing Atlassian Goal.

Input Parameters

array
Notes to include. Each item has an optional title and required body in plain text or Markdown.
integer
Exact progress score. The score determines the resulting health status.
string
required
ARI of the Goal receiving the update.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Progress summary in plain text or Markdown. Rendered text is limited to 280 characters.
array
Learnings, risks, or decisions. Each item has type, summary, and Markdown-capable description.
object
Updated target date with date and confidence (DAY, MONTH, or QUARTER).
string ("pending" | "paused" | "off_track" | "at_risk" | "on_track" | "done" | "cancelled")
Lifecycle phase or in-progress health status of the Goal.
array
Metric measurements for this update. Provide one item with targetId, value, and optional measuredAt.
Slug: ATLASSIAN_MCP_CREATE_JIRA_BOARDCreate a new company-managed Jira Software board (scrum or kanban) from an existing filter. Requires a filter ID the user can view. When location is omitted, the board is filed in the single company-managed project from the filter’s JQL. Team-managed (TMP) locations are always rejected: TMP projects are 1:1 project to board (one built-in board at project creation, no way to add another). User locations are also rejected. The response includes a url that opens the board. The filter decides which issues the board shows; location only decides where the board is filed in navigation.

Input Parameters

string
required
Display name for the new board. Must be less than 255 characters.
string ("scrum" | "kanban")
required
Company-managed board type: scrum or kanban.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
integer
required
ID of a Jira filter the user can view. This filter’s JQL determines which issues appear on the board — pick or create one that targets the intended project, since location does not restrict the issue set. Board sharing follows the filter’s sharing; without Create shared objects permission a private board may be created instead.
object
Optional board container, controlling only where the board is filed in navigation — not which issues it shows. When omitted (or {}), defaults to the single project in the filter’s JQL. Object with type “project” and projectKeyOrId set to a company-managed project key or numeric ID. Team-managed (TMP) locations are always rejected (TMP is 1:1 project to board). User locations are also rejected. Example: {“type”:“project”,“projectKeyOrId”:“PROJ”}.
Slug: ATLASSIAN_MCP_CREATE_JIRA_ISSUECreate a new Jira issue. Custom fields go in additional_fields: keyed by field name, values are resolved automatically, so no field lookup is needed first (user fields take accountIds); keyed by customfield_* ID, pass the value in Jira’s format. A rejected create returns a repairHint and names the field at fault where there is one, with its allowedValues when known, so retry from that. If sprint assignment fails, the response still has the new issue’s key and sprintAssignment.assigned: false — do not create it again.

Input Parameters

array
List of label strings (e.g. [“bug”, “needs-triage”]).
string
Parent issue key for sub-tasks or child issues (e.g. PROJ-10).
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Issue summary / title.
string
Account ID of the assignee. Resolve a name with listJiraIssueAssignableUsers, which returns only users who can be assigned in this project; lookupJiraAccountId resolves any user and does not check that.
string
Priority name (e.g. High, Medium, Low, Highest, Lowest).
string
required
Issue type name (e.g. Bug, Task, Story, Epic). Use listJiraProjectIssueTypesMetadata to list valid types for this project if unsure.
string
required
Project key (e.g. PROJ).
string
Issue description in markdown, or HTML with contentFormat html. Converted to Jira ADF automatically.
string ("markdown" | "html")
Body format for description. Defaults to markdown; html adds panels, tables and status lozenges. For HTML body shapes, first get the format guide via the generic operation runner (execute) as name=getContentFormatGuide, inputs={toolName: “createJiraIssue”}. Inline media needs an existing issue: create first, then embed with editJiraIssue. When the HTML content-format feature is disabled the call is rejected rather than downgraded, because markdown would store the HTML tags as literal text.
string
Optional sprint assignment after the issue is created. Accepts a numeric sprint ID, an exact sprint name, or “active” to resolve an active sprint. Numeric sprint IDs assign directly and do not need board lookup. When omitted, createJiraIssue behaves exactly as before and does not make sprint calls.
object
Additional Jira fields. Keys can be human-readable field names or raw customfield_* IDs. Values can be human-readable (resolved automatically) or already-correct Jira shapes. Examples: {“Story Points”: 8} ← number field by name {“Team”: “Backend”} ← option/select by name {“Reviewers”: [“alice@acme.com”, “bob@acme.com”]} ← multi-user by accountId {“Component Area”: “Platform / Auth”} ← cascading select as “Parent / Child” {“customfield_10010”: 8} ← raw ID (no resolution needed, fastest) {“components”: [{“name”: “Backend”}]} ← system array field (raw shape) {“fixVersions”: [{“name”: “v2.0”}]} ← system array field (raw shape) On error, the response includes allowedValues and a repairHint for self-correction.
Slug: ATLASSIAN_MCP_CREATE_JSM_REQUESTCreate a Jira Service Management customer-request work item using an explicit JSM service desk ID, JSM request type ID, and request field values. Do not use Jira issue type IDs or generic Jira create-issue workflows. First use getJsmRequestCreationOptions to select a JSM request type, then getJsmRequestTypeFields to build requestFieldValues.

Input Parameters

object
Optional form values required by the selected JSM request type.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
ID of the JSM request type to use when creating the request.
string
required
ID of the JSM service desk where the request will be created.
object
required
Field values required by the selected JSM request type.
Slug: ATLASSIAN_MCP_CREATE_LOOM_FOLDERCreate a new folder in the current Loom workspace, optionally nested under a parent folder or placed in a space. Returns the new folder’s id, which you can pass to moveLoomVideoToFolder. To list existing folders instead of creating one, use listLoomFolders.

Input Parameters

string
required
Name for the new folder.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Optional ARI of a Loom space to create the folder in, ari:cloud:loom:{siteId}:space/activation/{activationId}/{spaceId}.
string
Optional, top-level folders only. One of owner or workspace. Ignored for space or nested folders.
string
Optional ARI of an existing folder to nest this one under, ari:cloud:loom:{siteId}:folder/activation/{activationId}/{folderId}.
Slug: ATLASSIAN_MCP_CREATE_LOOM_VIDEO_COMMENTPost a comment on a Loom video, anchored to a specific point in the video. The timestamp is in SECONDS (for example 90 for the 1:30 mark). Use this to leave feedback or a note at a moment in the recording. To read existing comments use getLoomVideo with expand: [“comments”]; to add an emoji reaction instead of a text comment use createLoomVideoReaction. Identify the video by ARI or share URL. NOTE: the returned timestamp is remapped onto the video’s current (post-trim) timeline, so for a video with trimmed/edited ranges the echoed value can come back up to 1 second lower than the value sent (never higher); for videos with no trims it always matches exactly.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Plain-text content of the comment. Maximum 5000 characters.
string
ARI of the Loom video, formatted as ari:cloud:loom:{siteId}:video/activation/{activationId}/{videoId}. Provide this or videoUrl.
string
Loom share URL for the video, for example https://www.loom.com/share/&#123;videoId&#125;. Used when videoAri is not supplied; a supporting action resolves the URL to an ARI.
integer
required
Position in the video in seconds at which to anchor the comment, for example 90 for 1:30. Must be greater than or equal to 0.
Slug: ATLASSIAN_MCP_CREATE_LOOM_VIDEO_REACTIONAdd an emoji reaction to a Loom video, anchored to a specific point in the video. The timestamp is in SECONDS (for example 90 for the 1:30 mark), the same unit as createLoomVideoComment. Use a Loom-native reaction name (joy, love, wow, nervous, yay, up, down) or an extended emoji slug. To leave a text comment instead, use createLoomVideoComment. Identify the video by ARI or share URL.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Optional reaction category. Use super to mark a super reaction. Defaults to no category if not provided.
string
ARI of the Loom video, formatted as ari:cloud:loom:{siteId}:video/activation/{activationId}/{videoId}. Provide this or videoUrl.
string
Loom share URL for the video, for example https://www.loom.com/share/&#123;videoId&#125;. Used when videoAri is not supplied; a supporting action resolves the URL to an ARI.
integer
required
Position in the video in seconds at which to place the reaction, for example 90 for 1:30. Must be greater than or equal to 0. Same unit as createLoomVideoComment’s timestamp.
string
required
The emoji reaction to add. For Loom-native reactions use one of joy, love, wow, nervous, yay, up, down. For extended emoji reactions use an emoji slug, for example heart_eyes, +1, raised_hands, optionally suffixed with a skin-tone modifier such as heart_eyes::skin-tone-2.
string
The type of reaction. Use LOOM for Loom-native reactions or EXTENDED for standard emoji slugs. Defaults to LOOM if not provided.
Slug: ATLASSIAN_MCP_CREATE_LOOM_VIDEO_UPLOADStep 1 of 2 for uploading a new video to Loom. Creates an upload and returns a ready-to-run local script (plus raw upload endpoints) that transfers the file’s bytes. After the script reports the upload is complete, call publishLoomVideo (step 2) with the returned completionPayload to finalize and get the share URL. This does not publish the video by itself.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Name of the file being uploaded, including its extension, for example Loom Live Sizzle.mp4. The extension is required; uploads without a recognizable file extension never finish transcoding.
string ("video/mp4" | "video/quicktime" | "video/webm" | "video/x-m4v" | "audio/x-ms-wma" | "video/x-ms-asf" | "application/vnd.ms-asf" | "video/x-ms-wmv" | "video/avi" | "video/vnd.avi" | "video/msvideo" | "video/x-msvideo" | "video/3gpp" | "video/x-matroska")
MIME type of the file, for example video/mp4. Defaults to video/mp4 if omitted.
integer
Optional advisory file size in bytes. When supplied, the returned upload script is annotated with a size hint so the agent knows whether the single-PUT or multipart path will be used. The script re-checks size at runtime.
Slug: ATLASSIAN_MCP_CREATE_PROJECTCreate an Atlassian Project.

Input Parameters

string
required
Name of the Project.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
boolean
Whether the Project is restricted to its contributors.
string
Planned start date in YYYY-MM-DD format.
object
Projected completion date with date and confidence (DAY, MONTH, or QUARTER).
object
Content for the Project About tab. Supported fields are what, why, and measurement; plain text and Markdown are accepted.
string
Atlassian account ID of the owner. Defaults to the current user.
Slug: ATLASSIAN_MCP_CREATE_PROJECT_UPDATEPost a progress update on an existing Atlassian Project, or save it as an unposted draft with isDraft. Posting is immediately visible on the Project and notifies its followers, so only post when the user asked to; use isDraft to leave it for them to review and post themselves. The response carries isDraft so you can tell which happened, and a draft returns fewer fields than a posted update.

Input Parameters

array
Additional context for the update. Provide one item with an optional title and required Markdown-capable body.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
boolean
When true, save the update as an unposted draft instead of publishing it. Nothing becomes visible on the Project and no followers are notified. Omit it to post the update immediately, which cannot be undone. A Project holds one draft per update period and saving never overwrites it: if a draft already exists the save is rejected. There is no way to amend a draft from here, so tell the user to post or discard the existing one in Atlas; read it first with getProject include=draftUpdate if they want to see what it says. The rejection can come back as an empty result rather than an error, so treat an empty response to a draft save as “a draft already exists” rather than success.
string
Progress summary in plain text or Markdown. Rendered text is limited to 280 characters.
string
required
ARI of the Project receiving the update.
array
Learnings, risks, or decisions. Each item has type, summary, and Markdown-capable description.
object
Updated target date with date and confidence (DAY, MONTH, or QUARTER).
string ("pending" | "paused" | "off_track" | "at_risk" | "on_track" | "done" | "cancelled")
Lifecycle phase or in-progress health status of the Project.
Slug: ATLASSIAN_MCP_CREATE_TEAMCreate an Atlassian team with a bounded name, optional description, MEMBER_INVITE or OPEN membership settings, and up to 50 initial account IDs. Tenant and organization are derived by the server.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
array
Up to 50 unique Atlassian account IDs to add initially.
string
Team description. Defaults to an empty string.
string
required
Non-blank team display name.
string ("MEMBER_INVITE" | "OPEN")
Membership policy.
Slug: ATLASSIAN_MCP_DECIDE_JSM_REQUEST_APPROVALApprove or decline a pending approval on an existing Jira Service Management request. Provide the request issue ID/key and an explicit decision of approve or decline. approvalId is optional; when omitted, the tool discovers pending request approvals and proceeds only when exactly one answerable approval is unambiguous. Use this for approval decisions, not workflow transitions, field edits, or comments.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string ("approve" | "decline")
required
Approval decision to apply. Must be approve or decline.
string
Optional approval ID. Prefer reading getJsmRequestActionMetadata with include=[approvals] and passing the chosen pending approval’s ID. If omitted, each call selects the current answerable pending approval; repeating the call can decide a newly created approval stage. After an uncertain result, refresh approvals before retrying and keep the original approvalId. Deciding a new stage requires fresh user intent.
string
required
JSM request issue ID or key, for example HD-123.
Slug: ATLASSIAN_MCP_DIFF_CONFLUENCE_CONTENT_VERSIONSCompute a unified diff between two versions of a Confluence page, live doc, or blog post

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric ID of the Confluence page, live doc, or blog post.
integer
required
Positive version number for the later side of the comparison.
integer
required
Positive version number for the earlier side of the comparison. List version numbers with listConfluenceContentVersions.
string ("markdown" | "html")
Body format used to compute the diff. Defaults to markdown.
Slug: ATLASSIAN_MCP_DOWNLOAD_CONFLUENCE_ATTACHMENTGet a Confluence attachment download URL and return a local curl command

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
number
Optional attachment version. Omit to download the latest version.
string
Optional absolute or relative local path where the downloaded file should be saved. If omitted, the tool derives a relative path from the download URL filename and falls back to ./attachment-<attachmentId>. This is used only to build downloadCommand.
string
required
Numeric or att-prefixed ID of the Confluence attachment to download. The numeric portion may contain up to 19 digits.
Slug: ATLASSIAN_MCP_DOWNLOAD_JIRA_ISSUE_ATTACHMENTGet a short-lived download URL for a Jira attachment and return a local downloadCommand. Run it from your shell to save the file.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Optional local path where the file should be saved (used only to build downloadCommand). Prefer a path relative to your current working directory (e.g. ”./report.pdf”); avoid temp directories. Defaults to the attachment’s filename in the current directory when omitted.
string
required
Numeric ID of the Jira attachment to download. Get it from getJiraIssue with fields: [“attachment”], which returns id, filename, size and mimeType per attachment. This is the numeric attachment ID, not a filename and not the media UUID that appears in comment or description bodies.
Slug: ATLASSIAN_MCP_EDIT_CONFLUENCE_INFOGRAPHIC_FOR_PAGEEdit an infographic in a page workflow. Use only when a Confluence page editing skill or guided workflow selects it; never as a standalone tool. Regenerates the existing infographic and returns a new placeholder media reference for embedding. Before prompting, reuse the shared Remix guide (headed ## Remix embeds) if its text is in your current context. Only if missing, call getContentFormatGuide with toolName=editConfluenceInfographicForPage and follow its Remix guidance. Generation and billing finish asynchronously; typical cost is 15–30 Rovo credits. Download detailed billing data for final usage; match any returned correlationId and usageUniqueId.

Input Parameters

string
Optional visual theme for the infographic.
string
required
Detailed description of the regenerated infographic.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric ID of the existing Confluence page containing the infographic (content type: page or live_doc only).
string ("1:1" | "4:3" | "3:2" | "16:9" | "21:9" | "3:4" | "2:3" | "9:16")
Optional output aspect ratio.
string
required
ID of the existing infographic being edited.
Slug: ATLASSIAN_MCP_EDIT_CONFLUENCE_MAUI_APPEdit a Maui app in a page workflow. Use only when a Confluence page editing skill or guided workflow selects it; never as a standalone tool. Regenerates the existing app and returns a new placeholder Maui ID and embed URL. Before prompting, reuse the shared Remix guide (headed ## Remix embeds) if its text is in your current context. Only if missing, call getContentFormatGuide with toolName=editConfluenceMauiApp and follow its Remix guidance. Generation and billing finish asynchronously; typical cost is 15–30 Rovo credits. Download detailed billing data for final usage; match any returned correlationId and usageUniqueId.

Input Parameters

string
required
ID of the existing Maui app being edited.
string
required
Detailed description of the regenerated Maui app.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric ID of the existing Confluence page containing the Maui app (content type: page or live_doc only).
Slug: ATLASSIAN_MCP_EDIT_JIRA_ENTITY_PROPERTYSets a single property (technical key/value store) on a specific Jira entity (issue, issueComment, issueWorklog, dashboardItem, user), creating or overwriting it. Returns {key, entityType, status}, status being “created” or “updated”; the value you wrote is not returned — read it back with getJiraEntityProperty.

Input Parameters

string
required
Full property value to store; replaces any existing value for the key. Accepts any valid JSON — object, array, string, number, or boolean (e.g. {“enabled”: true, “level”: 3}, [1, 2, 3], “dark”, or 42). Must be non-empty: null and blank strings are rejected.
string
Dashboard gadget/item ID. Required when entityType is “dashboardItem”.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
User account ID. Required when entityType is “user” (including for the calling user’s own properties)
string
ID of an existing comment. Required when entityType is “issueComment”.
string
ID of a worklog for a specific issue. Required when entityType is “issueWorklog”.
string ("issue" | "issueComment" | "issueWorklog" | "dashboardItem" | "user")
required
Which Jira entity type to set the property on. Determines the required identifier(s). Irrelevant identifiers are ignored.
string
ID for a dashboard. Required when entityType is “dashboardItem”.
string
required
The full property key to set. Must be namespaced under “atlassian-mcp.” prefix (e.g. “atlassian-mcp.config”) or call is rejected. This keeps MCP-written properties isolated from app-written keys.
string
Issue key (PROJ-123) or a Jira issue URL. Required for entityTypes “issue” and “issueWorklog”.
Slug: ATLASSIAN_MCP_EDIT_JIRA_ISSUEEdit an existing Jira issue. Custom fields go in additional_fields: keyed by field name, values are resolved automatically (user fields take accountIds); keyed by customfield_* ID, pass the value in Jira’s format. Every field is set, not appended: send the full list for labels, components and other multi-value fields. Change status or move to a sprint with transitionJiraIssue, and convert Task↔Sub-task with convertJiraIssueHierarchy. Empty description or environment with "". When editing a body that holds inline media, use contentFormat: html, or the media is dropped. Reorder on a board with rankBeforeIssue or rankAfterIssue; fields are saved first, so a failed reorder leaves the edit applied and returns ranking.ranked: false. The response shows only getJiraIssue’s default fields, so other fields you set are not echoed back.

Input Parameters

object
Jira fields payload to set, keyed by field name or customfield_* ID. To clear a field, pass explicit null (e.g. {“resolution”: null}). Rich-text fields (description/environment) default to markdown; set contentFormat: html to author them in HTML. Editing a body that already contains inline media must use contentFormat: html — markdown drops it. For HTML body shapes (inline media, panels, tables), first get the format guide via the generic operation runner (execute) as name=getContentFormatGuide, inputs={toolName: “editJiraIssue”}.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string ("jira_mcp_card" | "model_tool_call")
Optional invocation attribution. Jira MCP cards set jira_mcp_card; omit for model/tool-loop calls.
array
Media file ID(s) from uploadAttachmentToJiraIssue to append inline to the description, e.g. [“id1”,“id2”]. Requires contentFormat: html and a matching inlineFileCollection (paired by index). Appends at the end, keeping existing content; for exact placement, author the media node in the HTML description instead. A file already embedded in the body is rejected (would duplicate).
string
required
Issue key (e.g. PROJ-123).
string ("markdown" | "html")
Body format for rich-text fields (description/environment). Defaults to markdown. html preserves inline media across a read-modify-write; a body fetched as HTML can be written straight back (Jira resolves media collection/filename server-side and omits them on read — not data loss). Requires the HTML content-format feature; when it is disabled the call is rejected rather than downgraded, because markdown would store the HTML tags as literal text and drop the media.
array
Optional file name(s) (from the upload step’s fileName), paired to inlineFileId by index. Only selects the render shape: images render as a block image, other files as an inline chip. Omit to default to the image shape.
string
Optional. Rank this issue immediately after the given issue key or ID (LexoRank relative anchor). Mutually exclusive with rankBeforeIssue. When omitted, editJiraIssue does not make ranking calls.
string
Optional. Rank this issue immediately before the given issue key or ID (LexoRank relative anchor). Mutually exclusive with rankAfterIssue. When omitted, editJiraIssue does not make ranking calls.
object
Additional Jira fields. Keys can be human-readable field names or raw customfield_* IDs. Values can be human-readable (resolved automatically) or already-correct Jira shapes. Examples: {“Story Points”: 8} ← number field by name {“Team”: “Backend”} ← option/select by name {“Reviewers”: [“alice@acme.com”, “bob@acme.com”]} ← multi-user by accountId {“Component Area”: “Platform / Auth”} ← cascading select as “Parent / Child” {“customfield_10010”: 8} ← raw ID (no resolution needed, fastest) {“components”: [{“name”: “Backend”}]} ← system array field (raw shape) {“fixVersions”: [{“name”: “v2.0”}]} ← system array field (raw shape) On error, the response includes allowedValues and a repairHint for self-correction.
integer
Optional. Numeric Rank field id for this rank call (e.g. 10020). Pass only when the user explicitly provides a Rank field id, or asks to reorder on a specific board’s Rank field. For a named board, call getJiraBoardConfig first and use ranking.rankCustomFieldId. Do not invent or guess this id. Omit for ordinary reorders so Jira uses its default Rank field. Ignored unless rankBeforeIssue or rankAfterIssue is also set.
array
Media collection(s) from the upload step, paired to inlineFileId by index (a single value applies to all). Required whenever inlineFileId is set.
string ("markdown" | "html")
Output format for rich-text fields in the returned issue. Defaults to markdown. Bodies markdown cannot represent (media, panels, expands, statuses, @mentions) are always returned as HTML, so a follow-up edit does not destroy them. An explicit markdown request is overridden for those bodies, with a warning saying so; appliedContentFormat in the response reports the format you actually got.
Slug: ATLASSIAN_MCP_EXPORT_CONFLUENCE_CONTENTExport Confluence content as PDF or Word and return a download link

Input Parameters

string ("pdf" | "word")
required
Export format. Use “pdf” for a PDF document or “word” for a legacy Microsoft Word .doc file.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric Confluence content ID to export. Must be a positive numeric string (e.g. “123456”). PDF supports pages, blog posts, and live docs; Word is intended for pages.
Slug: ATLASSIAN_MCP_GET_ACCESSIBLE_ATLASSIAN_RESOURCESReturns the cloudId(s) available to the current user
Slug: ATLASSIAN_MCP_GET_ARTIFACTGet metadata for an artifact by ID.

Input Parameters

string
required
Artifact ID.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
Slug: ATLASSIAN_MCP_GET_ASSETS_OBJECTGet an Assets object by ID from the selected site.

Input Parameters

string
Assets object ID, matching-workspace ARI, object key or supported site URL
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Assets object ID, matching-workspace ARI, object key or supported site URL
Slug: ATLASSIAN_MCP_GET_ASSETS_OBJECTS_BY_IDGet one or more Assets objects by ID from the selected site.

Input Parameters

array
One or more Assets IDs to query
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
Slug: ATLASSIAN_MCP_GET_ASSETS_OBJECT_SCHEMAGet one or more Assets object schemas by ID from the selected site.

Input Parameters

array
Schema ID, matching-workspace ARI or exact schema name
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
Slug: ATLASSIAN_MCP_GET_ASSETS_OBJECT_TYPEGet one or more Assets object types by ID from the selected site.

Input Parameters

array
Object type ID
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Schema ID, ARI or exact name for type-name resolution
Slug: ATLASSIAN_MCP_GET_ASSETS_SERVICE_OBJECTS_BY_IDGet one or more Assets service objects by ID from the selected site.

Input Parameters

array
One or more Assets IDs to query
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
Slug: ATLASSIAN_MCP_GET_CAPACITY_PLAN_ALLOCATIONSFind who is allocated to what work in Individual Capacity Planning, across ALL capacity plans - not scoped to a single plan. USE WHEN the user asks what someone is working on, who is working on an issue or project, whether a contributor is on a given work item, how loaded or available someone is, or how staffed a work item is. People are contributors, not assignees: allocation is independent of the Jira assignee field - use the Jira tools for assignees. Pass contributorDataIds for the work those people are allocated to, workDataIds for who is allocated to those items, or both to check one contributor against one item. At least one is required; resolve non-project work ARIs with listCapacityPlanNonProjectWork rather than fabricating them. Returns contributor-work associations with contributor and work names/keys. expand adds ‘contributions’ (allocated value per period), ‘contributorAggregations’ (a contributor’s total contribution AND availability across all plans - “how loaded is X”) and ‘workAggregations’ (total effort across all contributors on an item - “how staffed is PROJ-42”); both aggregations come back as separate top-level objects, and all three can be combined. IMPORTANT: contributionStartDate and contributionEndDate do NOT filter which associations are returned - they only set the window for the contribution and aggregation figures. To check whether a contributor is allocated during a period, request contributions for that window and see whether any come back. A baseline 40-hour working week means 5 days, 40 hours and 100 percent are the same amount - say so when reporting days or percentages. PAGINATION - YOU MUST CHECK THIS: results come back one page at a time. When the response has pageInfo.hasNextPage = true the allocations list is INCOMPLETE - more contributor-work associations exist that are not in this response. Do NOT draw conclusions (totals, counts, “that’s the whole team”, “nobody else is allocated”) from a single page when hasNextPage is true. To get the rest, call again with after set to pageInfo.endCursor and repeat until hasNextPage = false, then combine every page before answering. For a broad “everyone’s allocations for this range” request, keep paging until hasNextPage = false.

Input Parameters

integer
Page size for backward pagination. Mutually exclusive with first; pair with before for previous pages.
string
Cursor for forward pagination. Pass pageInfo.endCursor from the previous response.
integer
Page size for forward pagination. Mutually exclusive with last; pair with after for subsequent pages.
string
Cursor for backward pagination. Pass pageInfo.startCursor from the previous response.
array
Array of extras to include: ‘contributions’ (allocated value per period in the contribution window, per allocation), ‘contributorAggregations’ (per contributor, total contribution and availability across ALL capacity plans; requires contributorDataIds), and ‘workAggregations’ (per work item, total contribution effort across ALL contributors; requires workDataIds, and carries totalContribution only, since work items have no availability). Both aggregations are returned as separate top-level objects. Combine freely, but omit expand entirely when the association itself is the answer, e.g. “is Chris on PROJ-42?” - each value costs extra work upstream.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string ("WEEKLY" | "FORTNIGHTLY" | "MONTHLY" | "QUARTERLY")
Bucket granularity for the aggregation figures. Omitted means adaptive from the contribution window: weekly up to three months, monthly up to a year, quarterly beyond that. Only applies when expand includes contributorAggregations or workAggregations - per-allocation contributions always use the adaptive scale.
array
Work item ARIs, maximum 20. Supported forms: Jira issues (ari:cloud:jira:{cloudId}:issue/{issueId}), Atlas projects (ari:cloud:townsquare:{cloudId}:project/{projectId}), and non-project work / custom contribution targets (ari:cloud:capacity-planning::custom-contribution-target/activation/{activationId}/{targetId}). Finds who is allocated to these items. At least one of contributorDataIds or workDataIds is required, and expand’s workAggregations requires this one.
array
Contributor ARIs shaped ari:cloud:identity::user/{accountId}, where {accountId} is an Atlassian account ID (e.g. ari:cloud:identity::user/5ea00a99d31fdf0c0d783dd5). Maximum 20. Finds the work these people are allocated to. At least one of contributorDataIds or workDataIds is required, and expand’s contributorAggregations requires this one.
string
End of that same window, as YYYY-MM-DD. Does NOT filter which associations are returned. See contributionStartDate for the default windows and the two-year limit.
string
Start of the window for the returned contribution and aggregation figures, as YYYY-MM-DD. Does NOT filter which associations are returned. Default window: no dates = one year either side of today, start only = two years forward, end only = two years back; when both are given they must be in order and span at most two years. The window also sets the default reporting period: weekly up to three months, monthly up to a year, quarterly beyond that.
object
Unit for every effort value returned - per-allocation contributions, contributor totals and availability, and work totals. Shape: { “valueType”: “PERCENTAGE” | “HOURS” | “DAYS” }, default PERCENTAGE. Use HOURS or DAYS when the user asks about effort, PERCENTAGE for utilisation or how much of someone’s time is taken up. The response echoes the unit in its top-level valueType field. Applies whenever expand is set.
Slug: ATLASSIAN_MCP_GET_CODE_FILERead the full contents of a single file in a connected source-control repository at a specific commit. Use this to inspect a file surfaced by searchCode: pass matchedFiles[].workspace, repo, path, and version (as commitHash) from that result. Returns the file’s text and a link to it.

Input Parameters

string
required
Repository-relative path to the file.
string
required
Pass the matched file repo slug, e.g. example-repo, not example-org/example-repo; supply the owner separately in workspace.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Repository owner — a Bitbucket workspace or GitHub organization. Use workspace (not namespace). Pass the matched file workspace from searchCode; do not infer it from the search filter.
string
required
Commit to read the file at. A searchCode result’s matchedFiles[].version, or a listCodeDirectory entry’s commitHash, supplies one.
Slug: ATLASSIAN_MCP_GET_CONFLUENCE_APPROVALGet Confluence page approval availability, approval status, reviewers, and optional progress or history. Omit contentId to list the pages awaiting the current user’s approval decision. For a general page status request, also call getConfluenceContentStatus; for approval status, use this tool only.

Input Parameters

integer
Maximum number of expanded history entries to return (1-100, default 25). When listing pending approvals, 1-50 (default 25).
string
Opaque pagination cursor returned from a previous expanded history response, or from a previous pending approvals list.
array
Optional details to include for a contentId. Values are progress and history. Up to 2 values. Not supported when listing pending approvals.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Numeric Confluence page identifier, up to 19 digits. Approvals support pages only, not live docs or blog posts. Omit to list the pages awaiting your approval decision.
string ("CURRENT" | "DRAFT")
Content version whose approval state should be returned; omit when only checking availability or listing pending approvals.
Slug: ATLASSIAN_MCP_GET_CONFLUENCE_ATTACHMENTGet Confluence attachment metadata by attachment ID

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
number
Optional attachment version. Omit to fetch the latest version metadata.
string
required
Numeric or att-prefixed ID of the Confluence attachment to inspect. The numeric portion may contain up to 19 digits.
Slug: ATLASSIAN_MCP_GET_CONFLUENCE_COMMENTGet a single Confluence comment by ID

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
ID of the comment to fetch.
string ("markdown" | "html")
Response body format (default markdown).
string ("footer" | "inline")
Assert the comment surface (“footer” or “inline”). Omit to auto-detect.
boolean
Include replies as a flat descendant list (default true). Pass false to omit and read only the count.
Slug: ATLASSIAN_MCP_GET_CONFLUENCE_CONTENTREQUIRED: Supply at least one content locator: content_id or content_url. Read any Confluence content (page, blog, live doc, comment, whiteboard, embed, database, folder).

Input Parameters

boolean
If true, read the draft version instead of current. Only supported for pages and blog posts.
string ("summary" | "ai_summary" | "outline" | "full")
Response shape for document-style reads. summary = title + excerpt + counts (default, cheap). ai_summary = the generated AI summary when available, otherwise null; it does not fall back to the standard excerpt. outline = heading tree (cheap, for navigation). full = body in the requested format (use when intending to edit). Non-document content such as whiteboards, databases, folders, and embeds does not support detail; content_format is a separate representation selector for formats such as whiteboard svg/png, database csv, or embed url.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Required when content_url is omitted. Numeric Confluence content ID, or a Confluence tiny link key (the encoded part from /wiki/x/ URLs, e.g. 4_sXAQ). Recognized Confluence content URLs are also accepted and converted to the content ID, but prefer content_url for URLs. One of content_id or content_url is required.
string
Required when content_id is omitted. Full URL of the Confluence content. Supported: pages/live docs (/pages/{id}), blog URLs (/blog/{id}), whiteboards (/whiteboard/{id}), databases (/database/{id}), folders (/folder/{id}), embeds (/embed/{id}), and TinyUrl (/wiki/x/{key}). Prefer this for URLs copied from Confluence. One of content_id or content_url is required.
string ("html" | "markdown" | "url" | "svg" | "png" | "csv")
Body format. Doc types: html (default) or markdown. Document HTML can contain supported macro wrappers instead of content displayed in Confluence web. When visible macro content is required, use resolveConfluenceContentMacros with the returned numeric content ID and all=true; use discover if its full contract is needed. Whiteboards support only svg and png: use svg to inspect content or prepare edits, or png for a screenshot. Never use html or markdown for a whiteboard. PNG is read-only and returns a short-lived presigned URL in body.value, not the image content. Databases: csv. URL-backed content such as embeds: url. For an embed or Smart Link, including a Smart Folder child, explicitly request content_format=url and omit detail to read the destination URL in body.value. Then follow retrievalGuidance to read the target. Omitting content_format preserves the existing envelope-only embed read.
Slug: ATLASSIAN_MCP_GET_CONFLUENCE_CONTENT_ANALYTICSReturn per-user Confluence viewer rows for one supported content item (page, live doc, or blog post), including each viewer’s engagement category, the latest version viewed, and last viewed time. Always present results as a horizontal table, even for one viewer, with exactly these columns in this order: People and agents, Engagement, Latest version viewed, Last viewed, Views. When dates are omitted, Confluence uses the same default range as the Viewers table. Use the relative last-viewed value, such as “7 minutes ago”, instead of the exact timestamp. For an AGENT row with both names, present People and agents as “<displayName> with <relatedUserDisplayName>”. Keep the Engagement column; if engagement is missing, put ”-” rather than inventing another category.

Input Parameters

integer
Max viewer rows to return per page (1-100, default 25).
string
Opaque nextCursor for the same content. Omit when sending dates; it preserves the original range.
string
Inclusive end date, not in the future in the user’s timezone.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Inclusive start date, at most 12 months ago in the user’s timezone.
string
required
Numeric Confluence content ID for a page, live doc, or blog post.
Slug: ATLASSIAN_MCP_GET_CONFLUENCE_CONTENT_ANCESTORSList the ancestor chain (parent, grandparent, …) of a Confluence content entity

Input Parameters

integer
Maximum number of ancestors to return (1-250). Defaults to 25.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric ID of the Confluence content whose ancestors should be listed.
Slug: ATLASSIAN_MCP_GET_CONFLUENCE_CONTENT_DESCENDANTSList descendants of a Confluence content entity (page, folder, whiteboard, database, embed, or slide)

Input Parameters

integer
How many levels of descendants to return (1 = direct children only). Defaults to 2; maximum 10.
integer
Maximum number of descendant entries to return per page (1-250). Defaults to 25.
string
Opaque pagination cursor extracted from the previous response’s _links.next URL.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric ID of the Confluence content entity whose descendants to list. For a whole space’s page tree, pass the space’s homepageId from getConfluenceSpace.
Slug: ATLASSIAN_MCP_GET_CONFLUENCE_CONTENT_PERMISSIONSLists the explicit content-level permission grants on a single Confluence content entity. Each grant pairs an operation (read or update) with a principal (a user or a group). Optionally filter by operation, principal-type, or principal-id, and paginate with cursor and limit.Use this to audit who has been granted read or update access before adding, replacing, or removing grants. To read the higher-level restriction state (OPEN / EDIT_RESTRICTED / VIEW_RESTRICTED), use getConfluenceContentRestrictionState instead.Specific access rows: read = Can view and update = Can edit (which already includes view). Each principal has one level: read, update, or none. These grants add principal access; they do not restrict other people or change General access. General access is controlled by the restriction state, not direct grants.

Input Parameters

number
Max number of grants to return per page (1–250). Defaults to 100.
string
Opaque pagination cursor returned in _links.next by a previous call. Omit to start from the first page.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric ID of the Confluence content entity (page, blog post, whiteboard, database, folder, etc.) whose permission grants should be listed.
string
Filter by operation. One of: read, update.
string
Filter by principal ID. For users this is the Atlassian account ID; for groups it is the group ID.
string
Filter by principal type. One of: user, group.
Slug: ATLASSIAN_MCP_GET_CONFLUENCE_CONTENT_RESTRICTION_STATEReads General access for a single Confluence content entity. The restriction states are: OPEN — “Open, Anyone in this space can edit”. EDIT_RESTRICTED — “Open, Anyone in this space can view”; only Specific access update principals can edit. VIEW_RESTRICTED — “Restricted, Only specific people can view or edit”; Specific access read/update grants determine access.Use this for a quick read of the overall restriction posture; use getConfluenceContentPermissions to enumerate the individual user/group grants.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric ID of the Confluence content entity (page, blog post, whiteboard, database, folder, etc.) whose restriction state should be read.
Slug: ATLASSIAN_MCP_GET_CONFLUENCE_CONTENT_STATUSRead the content state (status) of a Confluence page or blog post

Input Parameters

string ("current" | "draft")
current (default, published badge) or draft. Lowercase only.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric ID of the Confluence content whose state should be read.
Slug: ATLASSIAN_MCP_GET_CONFLUENCE_CONTENT_VERSIONGet one historical version of a Confluence page, live doc, or blog post

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric ID of the Confluence page, live doc, or blog post.
integer
required
Positive version number to retrieve.
string ("markdown" | "html")
Optional historical body format. Omit to return version metadata without rendering the body.
Slug: ATLASSIAN_MCP_GET_CONFLUENCE_MAUI_APPRetrieve the source and metadata for a Maui app owned by a Confluence page.

Input Parameters

string
required
ID of the Maui app to retrieve.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric ID of the Confluence page that owns the Maui app (content type: page or live_doc only).
Slug: ATLASSIAN_MCP_GET_CONFLUENCE_PERSONAL_SPACEGet the current user’s Confluence personal space

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
Slug: ATLASSIAN_MCP_GET_CONFLUENCE_PUBLIC_LINK_STATUSGet the external public-link (anonymous share) status of a Confluence page

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric ID of the Confluence page to read the public-link status for.
Slug: ATLASSIAN_MCP_GET_CONFLUENCE_REACTIONSGet emoji reactions on Confluence content

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric Confluence content ID (page, blog post, or comment).
Slug: ATLASSIAN_MCP_GET_CONFLUENCE_SPACEGet one Confluence space by id or key, including enabled content types, optional labels, and instructions when configured. Reuse the result for the same cloudId and space during the current task instead of reading the space before every write. If spaceInstructions is omitted, no instructions are configured; normal authoring does not require a separate getConfluenceSpaceInstructions call.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric Confluence space id or space key, for example 123456, DEV, or ~accountId for a personal space.
boolean
If true, include the space labels in the response. Defaults to false.
Slug: ATLASSIAN_MCP_GET_CONFLUENCE_SPACE_INSTRUCTIONSGet the space instructions for a Confluence space

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Numeric ID of the Confluence space. Resolved to the space key before the request. Provide either spaceKey or spaceId.
string
Confluence space key, for example DEV or ~accountId for a personal space. Provide either spaceKey or spaceId.
string ("markdown" | "html")
Instruction body format to return. Defaults to markdown. Use html for Confluence HTML. Do not request ADF.
Slug: ATLASSIAN_MCP_GET_CONFLUENCE_TASKGet a single Confluence inline task by its ID

Input Parameters

string
required
The ID of the Confluence inline task to fetch.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
Slug: ATLASSIAN_MCP_GET_CONFLUENCE_TEMPLATEGet a Confluence template body

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
ID of the Confluence template or blueprint to fetch. Use templateId returned by listConfluenceTemplates.
Slug: ATLASSIAN_MCP_GET_CONTENT_FORMAT_GUIDEGet the content-format guide for authoring a rich content body or constructing a Confluence Remix prompt. Pass toolName to receive the canonical guidance for that operation. For generic Confluence content writes, pass the content-specific key (for example createConfluencePage, not createConfluenceContent). For Remix, pass the exact create/edit operation you are about to call. Use this before authoring or editing rich Confluence content, constructing a Remix generation/edit prompt, or writing a Jira issue/comment body in HTML. First call with only toolName; if the returned guidance references follow-up documents, call this operation again with the same toolName and reference set to a single referenced path to load that additional guidance. Fetch one document per call.

Input Parameters

string
required
The content-specific operation key to fetch guidance for, never a bare content type such as whiteboard. For generic Confluence content authoring/editing, this is NOT createConfluenceContent or updateConfluenceContent; use the create/update key for the target content type: createConfluencePage/updateConfluencePage (pages, blog posts, live docs), createConfluenceWhiteboard/updateConfluenceWhiteboard, or createConfluenceDatabase/updateConfluenceDatabase, or addConfluenceContentSuggestions for content suggestions. For Remix prompt construction, use the exact operation: createConfluenceInfographicForPage, editConfluenceInfographicForPage, createConfluenceMauiApp, or editConfluenceMauiApp. For authoring Jira issue/comment bodies in HTML (contentFormat: html) the value is editJiraIssue or addOrEditJiraIssueComment. The response lists the supported values if an unknown one is passed.
string
Optional provider-specific reference for alternate or follow-up guidance content. Use a value referenced by the initial description response when fetching additional guidance after the initial toolName lookup. Accepts a single path string; fetch one document per call.
Slug: ATLASSIAN_MCP_GET_FOCUS_AREAGet a focus area by identifier, with optional expansions. Use when the exact focus area UUID, ARI, or page URL is known. For text search or listing, use searchFocusAreas instead. Optional include expansions cover about content, the current user’s latest draft status update, status updates, sub-focus areas, linked goals, linked work, and custom field values.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
object
Optional focus area details to include. Shape: { “aboutContent”: true, “latestDraftUpdate”: true, “statusTransitions”: true, “customFields”: true, “statusUpdates”: {}, “subFocusAreas”: {}, “linkedGoals”: {}, “linkedWork”: {} }. aboutContent, latestDraftUpdate, statusTransitions and customFields are booleans (all default to false). latestDraftUpdate includes the current user’s latest saved draft status update for this focus area, if one exists. statusTransitions lists the status changes this focus area currently allows, and is the required first step before changing its status: createFocusAreaStatusUpdate takes ids from this list. customFields returns the focus area’s stored custom field values as customFields[] entries with definitionId (the definition ARI, usable in setFocusAreaCustomFieldValues), name, searchKey (usable in searchFocusAreas filters.customFields), type, and the typed value: textValue, numberValue, dateValue, booleanValue, option { id, label }, options, userId, or userIds (user values are flat Atlassian account IDs). Only fields with a stored value are returned — a field absent from customFields is unset. statusUpdates and subFocusAreas are objects, not booleans — pass an empty object ({}) to include one with its defaults. statusUpdates.first defaults to 3 (max 20); statusUpdates.after paginates via statusUpdates.pageInfo.endCursor; statusUpdates.includeTransitions defaults to true. subFocusAreas returns direct children — subFocusAreas.query is optional plain text; subFocusAreas.first defaults to 10 (max 50); subFocusAreas.after paginates via subFocusAreas.pageInfo.endCursor; subFocusAreas.sort is an array like [{ “field”: “targetDate”, “direction”: “asc” }], where field is one of name, status, health, targetDate, focusAreaType and direction is asc or desc. linkedGoals and linkedWork are objects, not booleans — pass {} to include defaults. linkedGoals.first defaults to 10 (max 50) and linkedGoals.after paginates via linkedGoals.pageInfo.endCursor. linkedWork supports optional query plus first/after pagination (first defaults to 10, max 50). linkedWork.sort is an array like [{ “field”: “targetDate”, “direction”: “asc” }], where field is one of name, key, status, type, source, sourceStatus, applicationName, targetDate and direction is asc or desc. linkedWork results are filtered to the resolved cloud ID input. include.linkedGoals requires focusAreaIdentifier to be a focus area ARI; if only a UUID or URL is known, call getFocusArea first and pass the returned ari. include.linkedWork also requires a focus area ARI; if only a UUID or URL is known, call getFocusArea first and pass the returned ari.
string
required
The focus area to retrieve. Accepts a focus area UUID, a focus area ARI, or a focus area page URL. When reusing an identifier from an earlier response, pass its uuid field — not its id field.
Slug: ATLASSIAN_MCP_GET_FOCUS_AREA_TYPESGet the configured Focus area type hierarchy for a workspace. USE WHEN the user needs the valid Focus area types for a site — for example before creating a Focus area, or to understand hierarchy levels and parent type relationships. Returns each type with identifiers, hierarchy level, parent hierarchy references, and associated Focus area counts.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
Slug: ATLASSIAN_MCP_GET_GOALRetrieve one Atlassian Goal by its exact Goal ARI or key, with optional related details.

Input Parameters

object
Optional per-connection page sizes for updates, tags, teams, projects, subGoals, metricTargets, and highlights. Each defaults to 5 and accepts 1-20.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
object
Optional pagination cursors keyed by updates, tags, teams, projects, subGoals, metricTargets, or highlights.
array
Optional details to include. Allowed values are description, updates, tags, teams, projects, parentGoal, subGoals, metricTargets, and highlights. Metric targets include the target IDs required for metric updates. Highlights are the learnings, risks, and decisions recorded on the Goal, including any attached to a Goal update.
string
required
Exact Goal ARI or key. A key may contain multiple hyphens and must end in a numeric segment.
string ("GOAL" | "SUCCESS_MEASURE")
Filter the subGoals expansion by kind. Applies only when subGoals is included.
string ("DECISION" | "LEARNING" | "RISK")
Filter the highlights expansion by type. Applies only when highlights is included; omit it to return every type.
boolean
Return only highlights that are not attached to any Goal update. Applies only when highlights is included; omit it to return every highlight.
Slug: ATLASSIAN_MCP_GET_GOAL_TYPESGet the Goal Types available in an Atlassian site for creating Goals and Success Measures.

Input Parameters

integer
Maximum number of Goal Types to return.
string
Pagination cursor returned by a previous call.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
boolean
Whether to include disabled Goal Types. Disabled types cannot be used to create Goals.
Slug: ATLASSIAN_MCP_GET_GOAL_UPDATERetrieve one Atlassian Goal update by its exact Goal Update ARI, with optional related details.

Input Parameters

object
Optional per-connection page sizes for comments, notes, highlights, and metricUpdates. Each defaults to 5 and accepts 1-20.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
object
Optional pagination cursors keyed by comments, notes, highlights, or metricUpdates.
array
Optional details to include. Allowed values are comments, notes, highlights, and metricUpdates.
string
required
Exact Goal Update ARI in the form ari:cloud:townsquare:{cloudId}:goal-update/{resourceId}.
Slug: ATLASSIAN_MCP_GET_GRAPH_CONTEXTRetrieves connected context from Teamwork Graph for any Atlassian entity. Returns all relationships and linked objects within one traversal – including cross-product and third-party connections. Use when the answer requires connections between entities, not just a single entity’s fields.Supported entry points:Jira: issues, projects, sprints, versions, commentsConfluence: pages, blogposts, whiteboards, databases, spacesGoals, Projects, Focus Areas, Tags and updatesPeople: users, teams, organisationsDevOps: PRs, repos, deployments, services, builds, designsLoom: videos, meetingsCompass: componentsAssets: objectsIncidents, conversations, calendar events, external documentsAfter calling this tool, call getGraphObject on returned ARIs to get full content.The utilisation of this tool may consume up to 10 Rovo Credits. If the user or organization does not have any Rovo Credits available, the tool call will fail.

Input Parameters

string
Pagination cursor for fetching the next page of results.
integer
Max number of related items to return.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
object
Optional time range to filter relationships by creation or update time.
string ("AtlassianGoal" | "AtlassianGoalUpdate" | "AtlassianHomeComment" | "AtlassianHomeTag" | "AtlassianProject" | "AtlassianProjectUpdate" | "AtlassianTeam" | "AtlassianUser" | "CompassComponent" | "ConfluenceBlogPost" | "ConfluenceComment" | "ConfluenceDatabase" | "ConfluencePage" | "ConfluenceSpace" | "ConfluenceWhiteboard" | "ExternalCalendarEvent" | "ExternalConversation" | "ExternalDeployment" | "ExternalDesign" | "ExternalDocument" | "ExternalOrganisation" | "ExternalPosition" | "ExternalPullRequest" | "ExternalRepository" | "ExternalService" | "FocusFocusArea" | "JiraSpace" | "JiraSprint" | "JiraVersion" | "JiraWorkItem" | "JiraWorkItemComment" | "AssetsObject" | "LoomMeeting" | "LoomMeetingRecurrence" | "LoomVideo")
required
Type of object to fetch context for.
string ("summary" | "full")
‘summary’ (counts/metadata) or ‘full’ (detailed content).
string
required
Identifier for the object. It could be a key (e.g. ENG-1234), ID, ARI, or full URL; format depends on objectType.
array
Filter full results to specific relationship types to save tokens (e.g. ‘jira-work-item-links-external-build’ for Jira work items).
array
Filter results to only include relationships targeting specific object types (e.g. AtlassianUser, ConfluenceComment).
Slug: ATLASSIAN_MCP_GET_GRAPH_OBJECTFetches the entire available data for one or more objects (Atlassian or third-party) using their ARIs or URLs. Use for the objects gathered from getGraphContext tool.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
array
required
A list of object identifiers to hydrate. Supports both ARIs (e.g. ‘ari:cloud:jira::issue/123’) and full browser URLs (e.g. ‘https://mysite.atlassian.net/browse/PROJ-1’). At most 25 per call.
Slug: ATLASSIAN_MCP_GET_JIRA_BOARD_CONFIGReturns the configuration for a Jira board; filter, column layout, and each column’s mapped statuses with their id, name and category. For the issues on the board, use getJiraBoardIssueData.

Input Parameters

integer
required
Numeric ID of the board. Get from listJiraBoards.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
Slug: ATLASSIAN_MCP_GET_JIRA_BOARD_ISSUE_DATAGet the issues on a Jira board, its backlog, or all of them, with optional count and JQL filtering. For an issue search that is not scoped to a board, use searchJiraIssuesUsingJql. For one sprint’s issues with progress metrics, use getJiraBoardSprintData — on a Scrum board dataset “board” spans current and future sprints, not just the active one.

Input Parameters

string
Optional JQL to further filter the issues, e.g. “status = ‘In Progress’ AND assignee = currentUser()”. To filter by epic, add (“Epic Link” = <epicId> OR parent = <epicId>); OR-join one such clause per epic for multiple epics. To filter for no epics, use (“Epic Link” is EMPTY AND parent is EMPTY). If the tool returns a repairHint, follow it and retry.
string ("compact" | "evidence" | "full")
Output view preset. Default: “compact”. Options: “compact”, “evidence”, “full”. compact = minimal fields for scanning; evidence = decision-relevant detail; full = complete response.
array
Fields per issue (e.g. [“summary”, “status”, “customfield_10010”]). customfield_* IDs are site-specific — discover the correct id for story points etc. on this Cloud site. Honoured exactly when supplied. Values map to issues[].fields.customFields (human labels), not raw customfield_* keys. The default “compact” view omits custom fields; use view: “evidence” (fetches and maps all custom fields) or pass explicit customfield_* IDs.
integer
required
Numeric ID of the board. Get from listJiraBoards.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string ("board" | "backlog" | "all")
Which issues to return. “board”: issues on the active board (for scrum boards, those in current/future sprints). “backlog”: backlog issues (for scrum boards, those with no sprint). “all”: every issue on the board and backlog. Kanban boards have no backlog.
number
Maximum number of issues to return (default 50, max 100).
string
Pagination token from a previous response to fetch the next page.
string ("issues" | "count" | "all")
Never count for a normal listing or if nextPageToken is used. If the total for the same board/dataset/JQL is already known, reuse it. Use “count” only when no trusted count exists and either the user asks or a downstream step needs it. Use “all” only if both count and issues are required.
string ("markdown" | "html")
Format for rich-text bodies (description, environment, comments) when the view returns them. Defaults to markdown; html is lossless for a later editJiraIssue. Issues holding anything markdown cannot represent (media, panels, expands, statuses, @mentions) are returned as HTML automatically, decided per issue. An explicit markdown request is overridden for those bodies, with a warning saying so; appliedContentFormat in the response reports the format you actually got.
Slug: ATLASSIAN_MCP_GET_JIRA_BOARD_SPRINT_DATAResolve a Jira board plus its sprint data in one call. Supports board lookup by name, sprint lookup by name, and defaults to the active sprint when sprintId and sprintName are omitted. Returns the board, the resolved sprint, all sprint metadata on that board, and — unless includeIssues is false — the sprint’s issues with computed focus and progress slices such as assigned-to-me and at-risk items. If the requested sprint name or ID is not found, the tool returns the resolved board plus the available sprint names to help the agent repair the request. To only list a board’s sprints or filter them by state, use listJiraBoardSprints. For board or backlog issues that are not scoped to a single sprint, use getJiraBoardIssueData.

Input Parameters

string
Jira board ID. Preferred when already known because it avoids board-name ambiguity.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Specific sprint ID to resolve on the selected board.
string
Jira board name to resolve when boardId is unknown. Uses an exact case-insensitive name match when possible; narrow with projectKeyOrId or boardType if multiple boards share a similar name.
string ("all" | "CMPScrum" | "CMPKanban" | "TMP")
Optional board type filter for board lookup. Use all to omit Jira’s type filter, CMPScrum for company-managed Scrum boards, CMPKanban for company-managed Kanban boards, and TMP for Jira’s “simple” boards. TMP can include both team-managed Scrum and team-managed Kanban boards; inspect board features/details when you need to distinguish them.
string
Specific sprint name to resolve on the selected board. When omitted, the tool resolves the board’s active sprint by default.
boolean
When true (default), also fetch every issue in the resolved sprint and compute assigned-to-me, at-risk, and progress metrics. Pass false for a lighter metadata-only response.
string
Optional Jira project key or numeric project ID used to narrow board lookup.
Slug: ATLASSIAN_MCP_GET_JIRA_CURRENT_USERGet the calling user’s own Jira profile. Use it to turn “me” or “my” into an accountId, and to read the user’s time zone before resolving relative dates. For a JQL search, skip this tool and write assignee = currentUser() in the query instead. For anyone else use lookupJiraAccountId or getJiraUser.

Input Parameters

string
Comma-separated list of extra data to include. Options: groups (all groups you belong to) and applicationRoles (application roles you are assigned). Example: “groups,applicationRoles”. Both are omitted from the response unless requested here.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
Slug: ATLASSIAN_MCP_GET_JIRA_ENTITY_PROPERTYReturns a single property (technical key/value store) from a specific Jira entity (issue, issueComment, issueWorklog, dashboardItem, user), or lists all its property keys when propertyKey is omitted. With propertyKey it returns {key, value} with the stored JSON, null-valued fields generally dropped except assignee; without one, {keys: […]} — key names only, no values.

Input Parameters

string
Dashboard gadget/item ID. Required when entityType is “dashboardItem”.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
User account ID. Required when entityType is “user” (including for the calling user’s own properties)
string
ID of an existing comment. Required when entityType is “issueComment”.
string
ID of a worklog for a specific issue. Required when entityType is “issueWorklog”.
string ("issue" | "issueComment" | "issueWorklog" | "dashboardItem" | "user")
required
Which Jira entity to read the property from. Determines the required identifier(s). Irrelevant identifiers are ignored.
string
ID for a dashboard. Required when entityType is “dashboardItem”.
string
The exact property key to fetch (a single known key; no wildcards). Omit to list all property keys on the entity instead.
string
Issue key (PROJ-123) or a Jira issue URL. Required for entityTypes “issue” and “issueWorklog”.
Slug: ATLASSIAN_MCP_GET_JIRA_ISSUEGet a Jira or JSM issue by key or ID. Use for one known issue; use searchJiraIssuesUsingJql to find or list many issues. Reports how many comments an issue has, not the comments themselves — for those use listJiraIssueComments. View “evidence” also returns the issue’s links to other issues.

Input Parameters

string ("compact" | "evidence" | "full")
Output view preset. Default: “compact”. Options: “compact”, “evidence”, “full”. compact = minimal fields for scanning; evidence = decision-relevant detail; full = complete response.
string
Additional Jira expand tokens (comma-separated), e.g. “renderedFields,changelog”. Merged with any expand the server adds for custom-field mapping (e.g. “names”); duplicate tokens removed. Note “changelog” here returns only the newest page, sorted newest-first, and it accepts startAt/maxResults then ignores them — so it cannot be paged and reports a longer history as complete. Use listJiraIssueChangelogs to read all of it (oldest-first); do not mix their orderings.
array
Custom Jira field IDs to fetch (e.g. [“customfield_10010”, “customfield_10020”]). Overrides the view’s fetch strategy. For custom fields in normal use, prefer view: “evidence”, which fetches and maps them automatically. Use [“*all”] to fetch every field (expensive — prefer view: “full” instead).
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
boolean
When true, forwards Jira’s failFast query flag for this GET. Omit for Jira default behavior.
array
Issue entity property keys to return (Jira properties query param, repeated per key). Omit unless you rely on app-specific issue properties.
string ("jira_mcp_card" | "model_tool_call")
Optional invocation attribution. Jira MCP cards set jira_mcp_card; omit for model/tool-loop calls.
boolean
When true, each entry in fields is interpreted as a Jira field key (e.g. “summary”, “description”) instead of a field id. Matches the Jira REST fieldsByKeys query parameter. Ignored when fields is omitted (default field list uses ids).
string
required
Issue key (PROJ-123), numeric ID, or a Jira issue URL
boolean
When true, also return compact metadata for fields the authenticated user can edit on this issue, including type, allowed values, and operations. Omit unless preparing an edit: this makes an extra Jira REST call.
string ("markdown" | "html")
Format for rich-text bodies — description and environment, plus any comment bodies the view returns. Defaults to markdown. Set html to receive HTML, which is lossless, so you can pass it straight back to editJiraIssue/addOrEditJiraIssueComment with contentFormat: html. Bodies holding anything markdown cannot represent — inline media, panels, expands, layouts, statuses, @mentions, dates, emoji — are returned as HTML automatically, because markdown would drop those nodes or turn them into literal text on write-back. An explicit markdown request is overridden for those bodies, with a warning saying so; appliedContentFormat in the response reports the format you actually got.
Slug: ATLASSIAN_MCP_GET_JIRA_ISSUE_TYPE_META_WITH_FIELDSReturns the schema and field metadata for a specific issue type in a project, useful for creating issues with correct fields. Get issueTypeId from listJiraProjectIssueTypesMetadata first. Each entry in fields gives the fieldId, its name, whether it is required, schema.type — with schema.items naming the element type on arrays — and allowedValues on fields whose value must come from a predefined list. Only required fields are returned unless you pass requiredFieldsOnly: false.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
number
Index of the first field to return (page offset). Defaults to 0.
number
Maximum fields to return per page (max 200, default 50).
string
required
Issue type ID
string
required
Project ID or key (e.g. PROJ or 10000)
boolean
When true (default), returns only the fields that are required to create an issue of this type, reducing response size. Set to false to return all available fields (both required and optional).
Slug: ATLASSIAN_MCP_GET_JIRA_PROJECT_VERSION_RELATED_WORKList the related work on a Jira project version (release): the designs, test plans, runbooks and change records teams attach to it. Use an item’s relatedWorkId to edit it with manageJiraProjectVersionRelatedWork; Jira’s own release-note item has no relatedWorkId and cannot be edited.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
ID of the version. Use getJiraProjectVersions to find the ID.
Slug: ATLASSIAN_MCP_GET_JIRA_PROJECT_VERSIONSList a Jira project’s releases/versions (pass projectIdOrKey), or fetch a single version (pass versionId) — provide exactly one. Results come back in a paginated envelope (values[]); in single-version mode the list-only inputs (startAt, maxResults, query, status, orderBy) are ignored. Optionally set include to add the “driver” and/or “approvers” to every version returned, but leave it unset unless the user explicitly asks for them. To create, update, or release a version, use manageJiraProjectVersion instead.

Input Parameters

string
Filter versions by name or description (case-insensitive substring match). List mode only.
array
Filter by version status. Array of any of: “released”, “unreleased”, “archived”. Example: [“released”, “unreleased”]. List mode only.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
array
Extra sections to add to every version returned. Allowed values: “driver” (the resolved driver display name) and “approvers” (approvers with displayName, status, description, declineReason). Only set this when the user explicitly asks for the driver or approvers; otherwise omit it. In list mode one call enriches all versions, so never call per version.
string
Order results by a field. Options: description, name, releaseDate, sequence, startDate. Prefix with ’-’ for descending. Example: ‘-releaseDate’. List mode only.
integer
Pagination offset (default 0). List mode only; ignored when versionId is provided.
string
The numeric ID of a single version (release) to fetch. Provide either versionId or projectIdOrKey (not both); required when projectIdOrKey is omitted. In this mode the pagination/filter inputs are ignored and a single-entry envelope is returned.
integer
Maximum results per page (default 50). List mode only; ignored when versionId is provided.
string
The project key (e.g. PROJ) or numeric project ID to list versions for. Use listJiraProjects to find the key if not known. Provide either projectIdOrKey or versionId (not both); required when versionId is omitted.
Slug: ATLASSIAN_MCP_GET_JIRA_USERGet a Jira user’s profile by account ID, including time zone, locale and active status, plus groups and application roles when asked for via expand. If you do not have the accountId, use lookupJiraAccountId or listJiraIssueAssignableUsers first. For the calling user’s own profile use getJiraCurrentUser instead.

Input Parameters

string
Comma-separated list of extra data to include. Options: groups (all groups the user belongs to) and applicationRoles (application roles the user is assigned). Example: “groups,applicationRoles”. Both are omitted from the response unless requested here.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
The account ID of the user to retrieve.
Slug: ATLASSIAN_MCP_GET_JSM_AGENT_AVAILABILITYRead Jira Service Management Workforce Management availability for agents in a service project. Workforce Management uses agent availability alongside capacity, skills, and shift coverage when routing work. Returns project-level availability counts by default. Set includeSelf to read the authenticated agent’s project-scoped status, or set includeAgents to true to list individual agents, statuses, teams, or paginated results. This is read-only; it does not assign work or change availability. Output fields include summary for project counts, agents[] for individual agents, and myAvailability for includeSelf; use those names when selecting responseFields.

Input Parameters

string
Pagination cursor, used only when includeAgents is true.
number
Number of agent rows to return when includeAgents is true (default 20, maximum 100).
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
array
Optional Workforce Management team IDs to filter by.
array
Optional agent IDs to filter by.
array
Optional repeatable status filters. Use AVAILABLE or ON_BREAK. TWG aliases such as available, active, online, away, on-break, or unavailable are normalized before forwarding.
string
required
JSM service project key, for example HELP.
boolean
Set true to include the authenticated user’s project-scoped availability. Cannot be combined with includeAgents.
boolean
Set true to include individual project agent rows and pageInfo.
Slug: ATLASSIAN_MCP_GET_JSM_OPS_ALERTSGet one Jira Service Management Operations alert by ID or alias, or list and search alerts with optional query, time window, and pagination. If multiple selectors are supplied, id takes precedence, then alias, otherwise list/search inputs are used.

Input Parameters

string
Alert ID. Takes precedence over alias and query when more than one is supplied.
string
Optional ISO 8601 upper time bound. Use with from.
string
Optional ISO 8601 lower time bound. Use with to.
integer
Maximum alerts to return. Defaults to 20; maximum 100.
string
Alert alias. Used when id is not supplied.
string
Optional alert search query, for example priority:P1 AND status:open.
integer
Starting alert index. Defaults to 0.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
Slug: ATLASSIAN_MCP_GET_JSM_OPS_SCHEDULE_INFOGet Jira Service Management Operations schedule information: list schedules, get a specific schedule by ID, or retrieve current or next on-call responders for a schedule. Use action=“schedule” to list schedules or get schedule details. Use action=“oncall” with scheduleId to get on-call responders.

Input Parameters

boolean
In oncall mode, return flattened user responders when true; otherwise return the responder tree.
boolean
In oncall mode, return next on-call responders when true; otherwise return current responders.
number
Maximum schedules to return. Defaults to 25; maximum 50.
string
Optional schedule-name query used when listing schedules.
string ("schedule" | "oncall")
Use schedule to list or get schedules. Use oncall to get current or next on-call responders.
number
Starting index for schedule pagination. Defaults to 0.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Schedule ID. In schedule mode, returns that schedule when supplied; in oncall mode, this is required.
Slug: ATLASSIAN_MCP_GET_JSM_OPS_TEAM_INFOGet Jira Service Management Operations team information: list all teams or get escalation policies for a specific team. Use action=“teams” to retrieve a list of all teams based on the user’s role. Use action=“escalations” to list escalation policies for a team and obtain escalationId values used by updateJsmOpsAlert.

Input Parameters

number
Maximum number of items to return per page. Default is 20. Only used when action=“escalations”.
string ("teams" | "escalations")
Action to perform. Use “teams” to list all teams. Use “escalations” to list escalation policies for a team. Default is “teams”.
number
Starting index (offset) for pagination. Default is 0. Only used when action=“escalations”.
string
Team ID (UUID). Required when action=“escalations”.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
Slug: ATLASSIAN_MCP_GET_JSM_REQUESTGet details and the current customer-facing state of an existing Jira Service Management (JSM) customer request by issue key or ID. Returns requestType (request type), serviceDesk (service desk), reporter (requester), requestParticipants (participants), requestFields (request fields), status, agentUrl (request link), and nextActions. Use these exact output names when selecting responseFields. Supports summary and detail views. For editable fields on the underlying Jira issue, call getJiraIssue with includeEditableFields=true. Use this read-only tool to understand a request; use request action-metadata tools for transitions, editable fields, and valid options. Approvals are returned only when explicitly requested.

Input Parameters

string ("detail" | "summary")
Output view preset. Default: “detail”. Options: “detail”, “summary”. compact = minimal fields for scanning; evidence = decision-relevant detail; full = complete response.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
array
Optional related data to retrieve. Supported value is approvals.
string
required
JSM request issue ID or key, for example HD-123.
Slug: ATLASSIAN_MCP_GET_JSM_REQUEST_ACTION_METADATADiscover customer-visible request-portal actions for an existing Jira Service Management request before a follow-up write. Returns compact customer transitions by default and can explicitly include request type fields metadata or approvals. Uses JSM customer transitions, not Jira workflow transitions, and never mutates the request. The output field is customerTransitions (an array of id, name, and description); select customerTransitions, not transitions.*, when using responseFields.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
array
Optional companion metadata. Supported values are requestTypeFields and approvals; neither is fetched by default.
string
required
JSM customer request issue ID or key, for example HD-123.
string
Optional request type ID already known from getJsmRequest, avoiding context repair for request type fields.
string
Optional service desk ID already known from getJsmRequest, avoiding context repair for request type fields.
Slug: ATLASSIAN_MCP_GET_JSM_REQUEST_CREATION_OPTIONSPrepare creation of a Jira Service Management customer-request work item for a project. Use this first to return its service desk and available request types. Select a request type, then use getJsmRequestTypeFields before createJsmRequest. Requires projectKey, the key of an accessible JSM service desk project (for example ITSM), not a numeric project ID. JSM request types are not Jira issue types.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
JSM project key, for example ITSM.
Slug: ATLASSIAN_MCP_GET_JSM_REQUEST_RESOLVER_PLANSRetrieve a concise snapshot of Request Resolver plans for selected Jira Service Management requests by issue key or ID. Returns one result per distinct input in first-selection order, containing loading state, plan status, readable steps, runbook links or an error. Ready plans remain available when other requests are loading or fail. Excludes internal IDs, sources and reasoning. isLoading can mean generating or executing; a missing plan alone does not imply loading. Requires Jira read access to resolve ticket and project IDs. Does not approve or execute plans.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
array
required
One to twenty non-blank issue keys or numeric issue IDs, for example IT-123.
Slug: ATLASSIAN_MCP_GET_JSM_REQUEST_TYPE_FIELDSGet field IDs, required flags, and allowed values for selected Jira Service Management work-item request type. Use getJsmRequestCreationOptions first, then build createJsmRequest.requestFieldValues from these fields.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Request type ID returned by getJsmRequestCreationOptions.
string
required
Service desk ID returned by getJsmRequestCreationOptions.
Slug: ATLASSIAN_MCP_GET_LOOM_VIDEOReads a Loom video’s core metadata and optionally its transcript, comments, AI agent briefs, AI-extracted meeting action items, or attached links in one call via the expand input. USE WHEN the user asks about a specific Loom video — its title, description, duration, owner, view/comment/reaction counts, what was said in it (pass expand: [“transcript”]), what feedback or comments people left on it (pass expand: [“comments”]), what the AI summarised as key points (pass expand: [“agentBriefs”]), or what follow-up tasks or action items the AI extracted from a meeting recording (pass expand: [“meetingActionItems”]), or which links are attached to it (pass expand: [“links”]). DO NOT USE to get the downloadable MP4 file — use getLoomVideoDownloadUrl for that. To find a video’s ARI first, use listLoomVideos or listLoomVideosSharedWithMe.

Input Parameters

array
Optional list of extra data to include in the response, in addition to core metadata. Any subset of “transcript”, “comments”, “agentBriefs”, “meetingActionItems”, “links”. Omit for core metadata only — nothing is included by default.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
ARI of the Loom video, formatted as ari:cloud:loom:{siteId}:video/activation/{activationId}/{videoId}. Provide this or videoUrl.
string
Loom share URL for the video, for example https://www.loom.com/share/&#123;videoId&#125;. Used when videoAri is not supplied; a supporting action resolves the URL to an ARI.
Pagination cursor to fetch the next page of links when links is included via expand.
Maximum number of links to return when links is included via expand (1-50).
string
Pagination cursor to fetch the next page of comments when comments is included via expand.
integer
Maximum number of comments to return when comments is included via expand (1-100).
string ("text" | "phrases" | "both")
Transcript response shape when expand includes “transcript”. Use “text” for summaries, extraction, implementation instructions, and general “what was said” questions. Use “phrases” only when timestamps, speaker/chunk structure, or quote-to-time answers are needed. Use “both” only when the caller explicitly needs both representations.
Slug: ATLASSIAN_MCP_GET_LOOM_VIDEO_DOWNLOAD_URLGet a time-limited signed URL to download the actual MP4 file of a Loom video. This is the tool to use when the user wants the video file itself (to download, re-upload, or process), not its transcript or metadata (use getLoomVideo for those). MP4 generation is asynchronous: the response includes a status and, when not yet ready, a retryAfterSeconds hint — poll this tool until status is READY, then use the returned url before expiresAt. Identify the video by ARI or share URL.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
ARI of the Loom video, formatted as ari:cloud:loom:{siteId}:video/activation/{activationId}/{videoId}. Provide this or videoUrl.
string
Loom share URL for the video, for example https://www.loom.com/share/&#123;videoId&#125;. Used when videoAri is not supplied; a supporting action resolves the URL to an ARI.
Slug: ATLASSIAN_MCP_GET_MY_WORKRead the signed-in user’s recent Jira, Confluence, Goals, Projects and Loom activity on one site. Returns things worked on or viewed, newest activity first, with titles, URLs and activity timestamps. Uses Activity Platform with no enriched graph-context or Cypher calls. Assigned work is not part of this feed. The lookback is configurable and defaults to 90 days.

Input Parameters

string ("worked_on" | "viewed")
Which activity type to fetch. One call returns one type.
string ("compact" | "evidence" | "full")
Output view preset. Default: “compact”. Options: “compact”, “evidence”, “full”. compact = minimal fields for scanning; evidence = decision-relevant detail; full = complete response.
integer
Maximum number of activity items to request (1-50).
string
Opaque nextCursor from the previous response for the same site, user, activity type, product and sinceDays. Preserves the first page’s absolute lookback boundary. Invalid or legacy cursors require restarting without a cursor.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string ("goals" | "projects")
Filter worked-on activity to Goals or Projects. Omit for the shared multi-product feed. Cannot be combined with viewed activity.
integer
Include activity from this many days before the first page’s request (1-3650). Keep this value unchanged when continuing with a cursor.
Slug: ATLASSIAN_MCP_GET_PROJECTRetrieve one Atlassian Project by its exact Project ARI or key, with optional related details.

Input Parameters

object
Optional per-connection page sizes for updates, tags, teams, goals, dependencies, links, contributors, followers, and highlights. Each defaults to 5 and accepts 1-20.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
object
Optional pagination cursors keyed by updates, tags, teams, goals, dependencies, links, contributors, followers, or highlights.
array
Optional details to include. Allowed values are description, updates, tags, teams, goals, dependencies, links, contributors, followers, highlights, and draftUpdate. Highlights are the learnings, risks, and decisions recorded on the Project, including any attached to a Project update. draftUpdate returns your most recent unposted draft update for this Project, using the same fields createProjectUpdate accepts so it can be posted as-is. It is omitted when no draft is saved, and only fields you filled in are present.
Filter the links expansion by type. Applies only when links is included.
string
required
Exact Project ARI or key. A key may contain multiple hyphens and must end in a numeric segment.
string ("DECISION" | "LEARNING" | "RISK")
Filter the highlights expansion by type. Applies only when highlights is included; omit it to return every type.
object
Optional updates expansion filters with createdAtOrAfter and createdAtOrBefore ISO timestamps.
boolean
Return only highlights that are not attached to any Project update. Applies only when highlights is included; omit it to return every highlight.
Slug: ATLASSIAN_MCP_GET_PROJECT_UPDATERetrieve one Atlassian Project update by its exact Project Update ARI, with optional related details.

Input Parameters

object
Optional per-connection page sizes for comments, notes, highlights, and milestones. Each defaults to 5 and accepts 1-20.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
object
Optional pagination cursors keyed by comments, notes, highlights, or milestones.
array
Optional details to include. Allowed values are comments, notes, highlights, and milestones.
string
required
Exact Project Update ARI in the form ari:cloud:townsquare:{cloudId}:project-update/{resourceId}.
Slug: ATLASSIAN_MCP_GET_TALENT_FIELDSDiscover the workspace’s queryable Talent fields, or resolve the valid filter values for a specific field. Call BEFORE authoring RQL: with no fieldId it lists the available field IDs (including custom fields), grouped by what they describe (position, worker, team, skill, focus area, focus area type, proposal, proposed movement and view fields), excluding hidden fields; with a fieldId it returns that field’s valid values, paginated. Field IDs and values are workspace-specific and must not be guessed.

Input Parameters

string
Values mode only — optional RQL filter restricting which positions contribute field values. Ignored when fieldId is omitted.
integer
Values mode only — maximum number of field values to return in this page. 1-100, defaults to 100. Ignored when fieldId is omitted.
string
Values mode only — forward pagination cursor from a previous response’s endCursor. Ignored when fieldId is omitted.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
ID of a single Talent field whose distinct values should be listed, as returned by this tool’s list mode. Omit to list the workspace’s configured field IDs instead.
Slug: ATLASSIAN_MCP_GET_TALENT_GROUP_METRICSAggregate Talent positions into COUNTS grouped by one to four position field IDs — headcount by country, by status, by level, by job family, by manager, or any nesting of those. Returns only the grouped counts and their field values, never the positions themselves: when the underlying list is wanted use searchTalentPositions, and when the breakdown is by reporting line or focus area use getTalentPositionsByEntity, which groups by entity rather than by field. Grouping field IDs are workspace-specific, must be groupable, and must not be guessed — call getTalentFields to resolve them. The common built-ins are positionCountry, positionStatus, positionLevel, positionRole, positionJobFamily, positionJobTitle, positionEmploymentType, positionManager and team.

Input Parameters

string
Radar Query Language filter that scopes which positions are aggregated over. Field IDs and values are workspace-specific — resolve them with getTalentFields rather than guessing. Omit to group across all positions the caller can see.
string
Forward pagination cursor from a previous response’s endCursor.
integer
Maximum number of grouped rows to return, 1-100. Defaults to 50.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
array
required
Ordered array of one to four unique groupable field ID strings to group the counts by, as returned by getTalentFields. Always pass an array, even for a single field, for example [“positionStatus”]. Supplying more than one produces nested groupings, for example [“positionCountry”, “positionLevel”]. Passing more than four returns an empty result rather than an error, so keep to four or fewer.
Slug: ATLASSIAN_MCP_GET_TALENT_POSITIONRead a single Talent position by its ARI, returning its selected position field values and, optionally, field values for the worker filling it. Use this only when you already have the position ARI: take it from a searchTalentPositions result’s id, or from a getTalentPositionsByEntity result’s entityId — NOT that tool’s id, which is a connection node identifier and is not accepted here. To FIND a position rather than read a known one, use searchTalentPositions. To identify the worker filling the position, request positionWorker in positionFieldIdIsIn — that yields the worker’s id, name and accountId. Do not rely on workerFieldIdIsIn for more than that: the backing action accepts it but does not currently return the requested worker field values, so attributes like skills or email will not come back here. Field IDs are workspace-specific and must not be guessed — call getTalentFields to resolve them. Common position built-ins are positionJobTitle, positionCountry, positionLevel, positionStatus, positionManager and positionWorker.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
ARI of the Talent position to fetch. Take it from a searchTalentPositions result’s id, or from a getTalentPositionsByEntity result’s entityId. Do NOT pass a getTalentPositionsByEntity result’s id — that identifies the row within its connection and returns an empty result here.
array
Array of worker field ID strings for the position’s worker, as returned by getTalentFields. Accepted by the backing action but currently ineffective — the requested values are not returned, so expect only the worker id, name and accountId that positionWorker already provides. Omit unless you are deliberately probing this.
array
Array of position field ID strings to return, as returned by getTalentFields. When omitted, a default set of position fields is returned.
Slug: ATLASSIAN_MCP_GET_TALENT_POSITIONS_BY_ENTITYList the Talent positions attached to an entity — the direct reports of a manager position (entity=position with that manager’s ARI as fieldValue), or the positions rolled up to a focus area (entity=focusArea). This is the tool for walking the org chart and for breaking staffing down across focus areas or reporting lines, because it is the only one that can scope to those entities; it returns the underlying positions, paginated forward with after + endCursor. The two entities are scoped by DIFFERENT inputs: entity=position scopes with fieldValue, entity=focusArea scopes with rql. fieldValue is ignored when entity=focusArea, so a focus area passed there returns every row unfiltered — use rql “focusArea = ‘<focus area ARI>’” for that one area, or rql “focusAreaParent = ‘<focus area ARI>’” for its direct children. Use getTalentGroupMetrics INSTEAD when you want counts grouped by a position FIELD and not the positions themselves, and searchTalentPositions INSTEAD for a flat attribute filter that is not entity-scoped. Each returned position carries both an entityId and an id: entityId is the position identifier to pass to getTalentPosition, while id identifies the row within this connection and is NOT accepted as a position ARI. Field IDs and RQL values are workspace-specific and must not be guessed — resolve them with getTalentFields; focusArea and focusAreaParent are standard field IDs and are safe to use exactly as written. Useful built-ins are positionWorker, team, positionJobTitle, positionRole, positionStatus, aiMonthlyUsageCostSelfTotal and aiMonthlyUsageTokenSelfTotal.

Input Parameters

string
Radar Query Language filter and ordering applied to the positions returned. Field IDs and values are workspace-specific — resolve them with getTalentFields rather than guessing. For entity=focusArea this is the ONLY way to scope to an area, because fieldValue is ignored there. Use focusArea = ‘<focus area ARI>’ to match that one area, or focusAreaParent = ‘<focus area ARI>’ to match its direct children. Both are standard field IDs, so use them exactly as written, and quote the ARI with single quotes.
string
Forward pagination cursor from a previous response’s endCursor.
integer
Maximum number of positions to return in this page, 1-100. Defaults to 25.
string
Backward pagination cursor from a previous response’s startCursor. Prefer forward paging with after — backward paging is accepted by the backend but has been observed to return an empty page.
string ("position" | "focusArea")
Entity to scope the positions by. Use position for a reporting-line search, focusArea for a focus-area search. Defaults to position. Each value is scoped by a different input — position scopes with fieldValue, focusArea scopes with rql.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
ID of the specific entity to scope to. Honored only when entity=position — pass a manager’s position ARI to return that manager’s direct reports, or omit to return top-level positions that have no manager. IGNORED when entity=focusArea, where passing it returns every row unfiltered; scope a focus area through rql instead.
array
Array of position field ID strings to return for each position, as returned by getTalentFields. When omitted, a small default set of human-readable fields is returned. Useful field IDs include positionWorker, team, positionJobTitle, aiMonthlyUsageCostSelfTotal and aiMonthlyUsageTokenSelfTotal.
string
Radar Query Language filter applied to aggregate fields requested through fieldIdIsIn, such as AI usage period, provider or model filters.
Slug: ATLASSIAN_MCP_GET_TALENT_USERResolve the calling user’s own place in the Talent workspace: their position entity ID, their manager’s position entity ID, and their role. Call this FIRST to anchor any self-referential request (“my team”, “my reports”, “who do I report to”) before using the other Talent tools. Note this returns entity IDs, not position ARIs — to get a position ARI for getTalentPosition or getTalentPositionsByEntity, look the position up with searchTalentPositions.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
Slug: ATLASSIAN_MCP_GET_TEAMGet core metadata for one Atlassian team. Optionally expand any unique subset of members and hierarchy; each expansion supports its own cursor.

Input Parameters

array
Unique optional values from “members” and “hierarchy”. Omit for core metadata only.
string
required
Team UUID or ari:cloud:identity::team/{teamId}.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Member cursor; valid only when expand includes “members”.
integer
Member page size when expand includes “members”. Defaults to 100.
string
Child-team cursor; valid only when expand includes “hierarchy”.
integer
Child-team page size when expand includes “hierarchy”. Defaults to 25.
Slug: ATLASSIAN_MCP_LINK_TO_FOCUS_AREALink one of either goals, work items, or sub-focus areas to a focus area. Add exactly one connection type per call. Prefer identifiers from a prior lookup, or call a lookup to get them; do not fabricate ARIs. Useful lookup helpers: getGoal for goal ARIs, getJiraIssue for Jira work ARIs, and getProject for Atlassian project ARIs. In this tool, WORK_ITEM means one of the supported work ARI families: Jira/JPD issues or Atlassian projects. focusAreaIdentifier accepts a focus area UUID, ARI, or page URL. Linking GOAL or WORK_ITEM requires focusAreaIdentifier to be a focus area ARI; if only a UUID or URL is known, call getFocusArea and pass the returned ari. connection must specify exactly one type: GOAL with goalAris, WORK_ITEM with workAris, or FOCUS_AREA with focusAreaIdentifiers.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
object
required
The connection to add. Provide exactly one type per call: GOAL, WORK_ITEM, or FOCUS_AREA. Include only the fields for that type. Exactly one of goalAris, workAris, or focusAreaIdentifiers must be present, matching connection.type; all other target fields must be omitted. For GOAL or WORK_ITEM, see focusAreaIdentifier requirements. Shape: { “type”: “GOAL”, “goalAris”: [“ari:cloud:townsquare:{siteId}:goal/{goalUuid}”] } OR { “type”: “WORK_ITEM”, “workAris”: [“ari:cloud:jira:{siteId}:issue/{issueId}” | “ari:cloud:townsquare:{siteId}:project/{projectUuid}”] } OR { “type”: “FOCUS_AREA”, “focusAreaIdentifiers”: [“<uuid|ari|url>”] }. Arrays must be non-empty and deduplicated. For GOAL use only goal ARIs (use getGoal to look them up when needed); for WORK_ITEM use only supported work ARIs: Jira/JPD issue ARIs (ari:cloud:jira:{siteId}:issue/{issueId}), or Atlassian project ARIs (ari:cloud:townsquare:{siteId}:project/{projectUuid}) — for example from getJiraIssue or getProject. For FOCUS_AREA, focusAreaIdentifiers must not include focusAreaIdentifier.
string
required
Exact focus area UUID, ARI, or page URL identifying the focus area that will receive the new connections. Linking GOAL or WORK_ITEM requires a focus area ARI; if only a UUID or URL is known, call getFocusArea and pass the returned ari. This requirement applies only for GOAL and WORK_ITEM connections; FOCUS_AREA connections accept UUID, ARI, or URL for focusAreaIdentifier.
Slug: ATLASSIAN_MCP_LIST_ARTIFACTSList artifacts created by the current user using cursor pagination.

Input Parameters

number
Maximum artifacts to return. Defaults to 20 and is capped at 100.
string
Opaque cursor from the previous response. Omit for the first page.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
Slug: ATLASSIAN_MCP_LIST_ASSETS_OBJECT_SCHEMASList all Assets object schemas in the selected site’s workspace.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
boolean
Include object and object-type counts
Slug: ATLASSIAN_MCP_LIST_ASSETS_OBJECT_TYPE_ATTRIBUTESList attributes for one or more Assets object types in the selected site.

Input Parameters

array
Object type ID
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
Slug: ATLASSIAN_MCP_LIST_CAPACITY_PLAN_NON_PROJECT_WORKSearch the non-project work items on a site. “Non-project work” is the user-facing name for a custom contribution target - the buckets of time that are not a Jira issue or an Atlas project, such as Leave, Run the Business (RtB), on-call, or training. Non-project work is an entity that belongs to Capacity Planning: it is defined and stored in Capacity Planning itself, and exists nowhere else in Atlassian. Capacity can be allocated to three kinds of work item - Jira issues, Atlas projects, and non-project work - and only the third is owned by Capacity Planning, so it can only be found through this tool. There is no Jira or Confluence equivalent to look up instead. USE WHEN you need the ARI of a non-project work item before allocating someone to it, or when the user asks what non-project work categories exist. The returned ari is what feeds workId on updateCapacityPlanAllocations and workDataIds on getCapacityPlanAllocations - resolve it here rather than fabricating one. The query is case-insensitive and matches on name; omit it to list everything. Paginate with first/after or last/before.

Input Parameters

integer
Page size for backward pagination. Mutually exclusive with first; pair with before for previous pages.
string
Cursor for forward pagination. Pass pageInfo.endCursor from the previous response.
integer
Page size for forward pagination. Mutually exclusive with last; pair with after for subsequent pages.
string
Case-insensitive name filter for non-project work items, e.g. “leave”. Omit to list every item on the site.
string
Cursor for backward pagination. Pass pageInfo.startCursor from the previous response.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
Slug: ATLASSIAN_MCP_LIST_CODE_DIRECTORYList the files and subdirectories under a path in a connected source-control repository at a specific commit. Paginated — pass the returned nextPage cursor to fetch the next page. Use it to browse a repository’s structure discovered via searchCode.

Input Parameters

string
Pagination cursor from a previous result’s nextPage.
string
Repository-relative directory to list. Omit it to list the repository root.
string
required
Pass the matched file repo slug, e.g. example-repo, not example-org/example-repo; supply the owner separately in workspace.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
integer
Maximum directory traversal depth. Defaults to 1 — the path’s immediate children only — when omitted.
string
required
Repository owner — a Bitbucket workspace or GitHub organization. Use workspace (not namespace). Pass the matched file workspace from searchCode; do not infer it from the search filter.
string
required
Commit to list at. A searchCode result’s matchedFiles[].version, or a previous listCodeDirectory entry’s commitHash, supplies one.
Slug: ATLASSIAN_MCP_LIST_CONFLUENCE_ATTACHMENTSList attachment metadata for a Confluence content item

Input Parameters

string
Optional attachment sort order, following the Confluence v2 attachment API semantics.
number
Optional maximum number of attachments to return. Must be between 1 and 250.
string
Optional pagination cursor from a previous listConfluenceAttachments result.
string
Optional attachment status filter, for example current, archived, or a comma-separated list such as current,archived.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Optional filename filter. For a persisted Remix infographic, use its mediaFileId to resolve the attachment ID.
string
required
Numeric ID of the Confluence content whose current attachments should be listed. Confluence content IDs are int64 values (max 19 digits).
string
Optional media type filter, for example image/png.
Slug: ATLASSIAN_MCP_LIST_CONFLUENCE_COMMENTSList comments on a Confluence page or blog post

Input Parameters

string ("created-date" | "+created-date" | "-created-date")
Sort by creation date. “+created-date” = oldest first (default), “-created-date” = newest first.
number
Max top-level comments per page (1–250, default 50).
string
Pagination cursor from a previous response’s nextCursor. Omit for the first page.
string ("current" | "draft")
Filter by content status.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
ID of the page or blog post to list comments for.
string ("markdown" | "html")
Response body format (default markdown).
string ("footer" | "inline")
Filter by surface: “footer” (page-level) or “inline” (anchored). Omit to return both.
string ("page" | "blogpost")
Hint to skip content-type probing when the container type is already known.
boolean
Include replies as a flat descendant list on each top-level comment (default false).
string ("open" | "resolved")
Filter top-level comments by resolution status (“open” or “resolved”). Applies to both footer and inline comments, so combine with comment-type to narrow to one surface. “open” also includes reopened comments and inline comments whose anchor text was lost.
Slug: ATLASSIAN_MCP_LIST_CONFLUENCE_CONTENTList Confluence content of one type within a single space (page, blog post, live doc, whiteboard, database, embed, smart link, folder, slide)

Input Parameters

string
required
Type of content to list. One of: page, live_doc, blogpost, whiteboard, database, embed, smart_link, folder, slide.
number
Max number of items to return per page (1-250). Defaults to 25.
string
Opaque pagination cursor returned by a previous call.
string
Content status filter. Defaults to current. Hierarchical types only support current or archived.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric space ID.
Slug: ATLASSIAN_MCP_LIST_CONFLUENCE_CONTENT_VERSIONSList version history for a Confluence page, live doc, or blog post, newest first

Input Parameters

integer
Maximum number of versions to return (1-250). The service returns newest versions first.
string
Cursor from a previous response for the next page of versions.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric ID of the Confluence page, live doc, or blog post.
Slug: ATLASSIAN_MCP_LIST_CONFLUENCE_SPACESList Confluence spaces accessible to the caller

Input Parameters

string
Space ids to fetch directly, as an array ([“123”,“456”]) or a comma-separated string (“123,456”). Up to 250 ids per call.
string
Space keys to fetch directly, as an array ([“DEV”,“OPS”]) or a comma-separated string (“DEV,OPS”). Up to 250 keys per call.
string ("global" | "personal" | "collaboration" | "knowledge_base")
Filter by space type.
number
Max number of spaces to return per page (1-250). Defaults to 25.
string
Opaque pagination cursor returned by a previous call. Omit to start from the first page.
string
Labels to filter spaces by, as an array ([“team”,“docs”]) or a comma-separated string (“team,docs”). Returns spaces that have any of the listed labels.
string ("current" | "archived")
Filter by space status. Defaults to current.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
Slug: ATLASSIAN_MCP_LIST_CONFLUENCE_TASKSList Confluence inline tasks, optionally scoped to a page or blog post and filtered by status

Input Parameters

number
Max number of tasks per page (1-250). Defaults to 25.
string
Opaque pagination cursor returned by a previous call.
string ("complete" | "incomplete")
Task status filter. One of complete, incomplete. Omit to include both.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Optional numeric page ID to scope the query to a single page.
string
Optional numeric space ID (or comma-separated list) to scope the query.
string
Account ID (or comma-separated list) of the user who created the task.
string
Account ID (or comma-separated list) of the user to whom the task is assigned.
string
Optional numeric blog post ID to scope the query to a single blog post.
string
Account ID (or comma-separated list) of the user who completed the task.
Slug: ATLASSIAN_MCP_LIST_CONFLUENCE_TEMPLATESList Confluence templates and blueprints

Input Parameters

number
Optional maximum number of templates to return per page. Must be between 1 and 250; defaults to 25.
string
Optional case-insensitive search across template id, name, and description. Use terms such as meeting notes to find matching templates.
string ("global" | "space" | "available")
Template scope to list. Use global for global templates, space for templates in the specified space, or available for templates available when creating in the specified space.
string
Opaque pagination cursor returned in _links.next by a previous call. Omit to start from the first page.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Numeric Confluence space ID. Required when scope is space or available.
string ("all" | "page" | "blueprint")
Template kind to list. Defaults to all.
Slug: ATLASSIAN_MCP_LIST_JIRA_BOARDSList Jira boards visible to the current user. Use it to get board IDs for getJiraBoardIssueData, getJiraBoardConfig and listJiraBoardSprints; getJiraBoardSprintData can resolve a board by name directly. Returns each board’s ID, name, type, edit/privacy/favourite flags and location. Page with startAt until isLast is true. projectKeyOrId matches boards whose JQL references that project, not boards located in it. includePrivate appends private boards, but Jira omits their name and type.

Input Parameters

string
Optional partial board name filter.
string ("all" | "CMPScrum" | "CMPKanban" | "TMP")
Optional board type filter. Use all to omit Jira’s type filter, CMPScrum for company-managed Scrum boards, CMPKanban for company-managed Kanban boards, and TMP for Jira’s “simple” boards. TMP can include both team-managed Scrum and team-managed Kanban boards; inspect board features/details when you need to distinguish them.
string
Optional comma-separated expand tokens such as admins or permissions.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Optional sort order. Supported values are name, -name, or +name.
number
Index of the first result to return (page offset). Defaults to 0.
number
Optional filter ID used to find boards relevant to a Jira filter.
number
Maximum results to return per page. Jira defaults to 50.
boolean
When true, append private boards to the end of the result list.
string
Optional project key or numeric ID used to find boards relevant to a project.
array
Optional list of project type locations such as software or service_desk.
boolean
When true, negates location-based filters such as project or project type.
Slug: ATLASSIAN_MCP_LIST_JIRA_BOARD_SPRINTSList a board’s sprints — past, active or upcoming — or resolve a sprint name to the numeric sprintId that transitionJiraIssue and manageJiraSprint take. Not needed before createJiraIssue, whose assignToSprint accepts a sprint name or “active” directly. For the active sprint plus its issues and progress in one call, use getJiraBoardSprintData.

Input Parameters

string ("active" | "future" | "closed" | "all")
Optional sprint state filter. Use all or omit to return all sprint states.
integer
required
Numeric ID of the Scrum board. Get from listJiraBoards.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
number
Index of the first result to return (page offset). Defaults to 0.
number
Maximum results to return per page. Jira defaults to 50.
Slug: ATLASSIAN_MCP_LIST_JIRA_DASHBOARDSReturns Jira dashboards visible to the current user for discovery and linking workflows. Use this to find dashboard IDs, names, and links that can be shared or opened. This tool is intentionally lightweight and does not fetch dashboard gadget data. Page with startAt until isLast is true.

Input Parameters

string
Optional status filter. Allowed values are active, archived, or deleted.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Optional group ID filter for dashboards shared to a specific group. Do not combine with groupname.
string
Optional sort order. Supported values include name, -name, owner, -owner, +owner, favorite_count, -favorite_count, +favorite_count, id, -id, +id, description, -description, +description, is_favorite, -is_favorite, and +is_favorite.
number
Index of the first result to return (page offset). Defaults to 0.
string
Optional owner account ID filter (preferred over deprecated owner username).
string
Optional group name filter for shared dashboards (prefer groupId when available).
number
Optional project ID filter for dashboards shared to a specific project.
number
Maximum results to return per page (default 50, max 100).
string
Optional dashboard name filter (maps to Jira dashboardName).
Slug: ATLASSIAN_MCP_LIST_JIRA_FILTERSSearch saved Jira filters visible to the current user, returning their IDs and JQL. To get the matching issues, run a filter’s jql through searchJiraIssuesUsingJql; to build a board, pass its id as createJiraBoard’s filterId. projectId finds filters shared with that project, not filters whose JQL mentions it.

Input Parameters

array
Optional list of specific filter IDs to return. Jira accepts at most 200 IDs per call (id=10000&id=10001).
string
Comma-separated expand tokens on GET /rest/api/3/filter/search. jql, owner, and description are expand-only. Defaults to description,jql,owner.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string ("name" | "-name" | "+name" | "id" | "-id" | "+id" | "owner" | "-owner" | "+owner")
Optional sort order. Defaults to Jira’s own ordering when omitted.
number
Index of the first result to return (page offset). Defaults to 0.
string
Optional owner account ID used to return filters owned by that user.
integer
Optional numeric project ID used to return filters scoped to a project. Use listJiraProjects to resolve a project key to its ID.
string
Optional filter name to match. Partial matches are returned unless isSubstringMatch is false. Must be 255 characters or fewer.
number
Maximum results to return per page. Jira defaults to 50.
Slug: ATLASSIAN_MCP_LIST_JIRA_ISSUE_ASSIGNABLE_USERSList the users who can actually be assigned work in a project or on an issue. Filters by assign permission, which a plain name search does not, so prefer it when choosing an assignee for editJiraIssue or createJiraIssue.

Input Parameters

string
Narrow the result to users whose display name or email matches this term. Omit it to list every assignable user. Only assignable users are searched — for a site-wide search by name or email, use lookupJiraAccountId.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Project key (e.g. PROJ) whose assignable users to list. Pass this or issueKey — with neither, Jira rejects the request.
string
Issue key (e.g. PROJ-123) whose assignable users to list. More accurate than project for an issue that already exists, because permission and security-level rules are evaluated against that issue.
string ("jira_mcp_card" | "model_tool_call")
Optional invocation attribution. Jira MCP cards set jira_mcp_card; omit for model/tool-loop calls.
Slug: ATLASSIAN_MCP_LIST_JIRA_ISSUE_CHANGELOGSGet a Jira issue’s field-change history — field edits only — paginated oldest-first with no ordering options. For the current value or most recent change, read total (which counts entries, not items) and request startAt = max(0, total - your page size); for counts or patterns across the history, page from startAt 0. A field’s original value is in the first item that changed it; fields never changed leave no trace, and the log starts at the first edit, not at creation. On an item, from/to are IDs or raw values and are absent on text and array fields; fromString/toString are display text, and on array fields like labels each side is the complete set (space-joined, sorted) — diff the two sides, never read one as a delta. Jira omits from and fromString together when the field had no previous value, and to and toString together when it was cleared (so an assignee item with no to/toString is an unassignment). Match items on field, not position: order within an entry varies. Do not infer automation from author.accountType — a script running under a person’s token reads “atlassian”.

Input Parameters

string ("compact" | "evidence")
Output view preset. Default: “compact”. Options: “compact”, “evidence”. compact = minimal fields for scanning; evidence = decision-relevant detail; full = complete response.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
integer
Zero-based index of the first changelog entry to return (for pagination). Defaults to 0.
integer
Maximum changelog entries per page (1-50). Defaults to 20; larger pages risk exceeding the client’s token limit and failing the call. Use maxResults=1 as a cheap probe to read total before jumping to the end of the history.
string
required
Issue key (PROJ-123), numeric ID, or a Jira issue URL
Slug: ATLASSIAN_MCP_LIST_JIRA_ISSUE_COMMENTSGet a paginated list of comments for a Jira issue. Use this instead of getJiraIssue when an issue has many comments — getJiraIssue embeds at most 20 and cannot page them. Page with startAt until isLast is true; total is the full comment count. Each comment reports any visibility restriction on it and, on JSM, whether it is internal (jsdPublic: false) — check both before quoting or summarising a comment. Comments are returned as a flat list: a non-null parentId means the comment is a reply, and parentId identifies its root/parent comment. Group comments by parentId to reconstruct threads. Set reactionDetail when emoji reaction data is needed. For the issue’s own fields, use getJiraIssue.

Input Parameters

string ("compact" | "evidence" | "full")
Output view preset. Default: “compact”. Options: “compact”, “evidence”, “full”. compact = minimal fields for scanning; evidence = decision-relevant detail; full = complete response.
string
Comma-separated list of extra data to include on each comment, e.g. “renderedBody” (HTML-rendered body) or “properties”.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string ("created" | "-created" | "+created")
Order comments by created date — “created”/“+created” (oldest first) or “-created” (newest first).
integer
Zero-based index of the first comment to return (for pagination). Defaults to 0.
integer
Maximum number of comments to return per page (1-100). Defaults to 100. Read total from the response for the full count. With view: “full” the page is capped at 20, because a larger full-view page can exceed the client’s token limit and fail the whole call; the response echoes the effective value.
string
required
Issue key (PROJ-123), numeric ID, or a Jira issue URL
string ("none" | "summary" | "users")
Reaction enrichment level. “none” (default) returns comments only, with no Reactions API call. “summary” adds emoji counts and whether the current user reacted. “users” also names who reacted — ask for it only when attribution is requested, since it costs an extra request per distinct emoji and reports when it could not expand every one.
string ("markdown" | "html")
Format for comment bodies. Defaults to markdown. Set html to receive HTML, which is lossless, so a body can be passed straight back to addOrEditJiraIssueComment with contentFormat: html. Fetch as html before editing any comment, since markdown drops images, panels and expands and returns statuses/@mentions as literal text. A page holding any such comment is returned as HTML automatically. An explicit markdown request is overridden for those bodies, with a warning saying so; appliedContentFormat in the response reports the format you actually got.
Slug: ATLASSIAN_MCP_LIST_JIRA_ISSUE_LINK_TYPESList the issue link types configured on this site, each with its name and its inward and outward wording (name “Blocks”, inward “is blocked by”, outward “blocks”). Call it before createJiraIssueLink, which takes the name, when the user has described a link by its inward/outward wording. Issue linking must be enabled site-wide; where it is turned off this operation and createJiraIssueLink both fail.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
Slug: ATLASSIAN_MCP_LIST_JIRA_ISSUE_TRANSITIONSList the workflow transitions this issue can take right now, for the calling user. Pass a transition’s id to transitionJiraIssue. A transition’s name and the status it leads to are separate fields: when the user names a target status, match the status a transition leads to, not the transition’s name. For every status a project defines, rather than this issue’s currently valid moves, use listJiraStatuses.

Input Parameters

string
Comma-separated expand tokens for extra detail. Use “transitions.fields” to include the fields shown on each transition’s screen (for use with transitionJiraIssue).
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string ("jira_mcp_card" | "model_tool_call")
Optional invocation attribution. Jira MCP cards set jira_mcp_card; omit for model/tool-loop calls.
string
required
Issue key (e.g. PROJ-123) or numeric ID
string
Return only the transition with this ID
boolean
When true, sort by ops-bar sequence then status category (Todo, In Progress, Done); otherwise by ops-bar sequence only (default false)
boolean
When true, include transitions hidden by the “Hide From User” condition (default false)
boolean
When true, include transitions that currently fail a condition (default false)
Slug: ATLASSIAN_MCP_LIST_JIRA_ISSUE_WORKLOGSGet a paginated list of worklogs (logged time) for a Jira issue. Ordered by worklog creation time, not by when the work started — so the last page is not the most recent work. To find recent work, filter with startedAfter/startedBefore, or read every page and sort by started.

Input Parameters

string ("compact" | "evidence" | "full")
Output view preset. Default: “compact”. Options: “compact”, “evidence”, “full”. compact = minimal fields for scanning; evidence = decision-relevant detail; full = complete response.
string ("properties")
Extra data to include on each worklog. The only supported value is “properties” (worklog properties).
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
integer
Zero-based index of the first worklog to return (for pagination). Defaults to 0.
integer
Maximum number of worklogs to return per page (1-100). Defaults to 100. Read total from the response for the full count. With view: “full” the page is capped at 20, because a larger full-view page can exceed the client’s token limit and fail the whole call; the response echoes the effective value.
string
required
Issue key (PROJ-123), numeric ID, or a Jira issue URL
integer
Only return worklogs whose work started at or after this time, as a UNIX timestamp in milliseconds. Inclusive: a worklog starting exactly on this timestamp is returned.
integer
Only return worklogs whose work started strictly before this time, as a UNIX timestamp in milliseconds. Exclusive: a worklog starting exactly on this timestamp is not returned. Pairs with startedAfter as a half-open range, so [dayStart, dayStart+86400000) is exactly one day with no double-counting or gaps between adjacent windows.
string ("markdown" | "html")
Format for worklog notes. Defaults to markdown. Set html to receive HTML, which is lossless, so a note can be passed straight back to addOrEditJiraIssueWorklog with contentFormat: html. A page holding any note markdown cannot represent (media, panels, statuses, @mentions) is returned as HTML automatically. An explicit markdown request is overridden for those bodies, with a warning saying so; appliedContentFormat in the response reports the format you actually got.
Slug: ATLASSIAN_MCP_LIST_JIRA_PROJECT_COMPONENTSList a Jira project’s components with their ids, names, lead and assignee settings, and issueCount — 0 means no issues use a Jira component; Compass results list only components already linked to issues. realAssignee is who actually receives issues when the configured assignee cannot be used. Use it to find a valid component name before setting components on createJiraIssue or editJiraIssue.

Input Parameters

string
Optional case-insensitive literal filter that matches component name or description.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string ("description" | "-description" | "+description" | "issueCount" | "-issueCount" | "+issueCount" | "lead" | "-lead" | "+lead" | "name" | "-name" | "+name")
Optional sort order. Sort by description, issueCount, lead, or name. Prefix with - for descending or + for ascending.
integer
Pagination offset. Use 0 for the first page and previous startAt + maxResults for the next page.
integer
Maximum components to return per page. Use a smaller value when the user asks for a limited sample.
string
required
Jira project key or numeric project ID whose components should be listed.
string ("jira" | "compass" | "auto")
Optional component source filter: jira (default Jira components), compass (connected Compass components), or auto (Compass components when the project is opted into Compass, otherwise Jira components).
Slug: ATLASSIAN_MCP_LIST_JIRA_PROJECT_ISSUE_TYPES_METADATAReturns all issue types available in a Jira project, useful for knowing which issue types can be created. Each entry gives the issue type’s id, name, description and subtask flag; pass that id as issueTypeId to getJiraIssueTypeMetaWithFields to get the type’s create fields. Page with startAt until it covers total.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
number
Index of the first issue type to return (page offset). Defaults to 0.
number
Maximum issue types to return per page (max 200, default 50).
string
required
Project ID or key (e.g. PROJ or 10000)
Slug: ATLASSIAN_MCP_LIST_JIRA_PROJECTSFind the Jira projects the calling user can see — use it to resolve the projectKey that createJiraIssue requires, or the project a JQL search filters on. For a project’s releases use getJiraProjectVersions; for its statuses, use listJiraStatuses.

Input Parameters

string
Filter results by a literal string matching project key or name (case insensitive).
string
Filter by the action the user can perform on the project: view, browse, edit, or create. Defaults to view when omitted.
string
Comma-separated list of extra data to include per project. Options: description, url, projectKeys, lead (project lead account), issueTypes (issue types available in the project), insight (total issue count and last update time). Example: “issueTypes,lead”.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
number
Index of the first result to return (page offset). Defaults to 0.
number
Maximum results to return per page (max 100, default 50).
Slug: ATLASSIAN_MCP_LIST_JIRA_STATUSESList the statuses a Jira issue can be in — for a project (per work type), for one status looked up by ID or name, or across the whole site by name or category. Takes a PROJECT key (or project ID), not an issue key. For what a specific issue can do right now, use listJiraIssueTransitions instead; a status existing in a project does not mean a given issue can move to it.

Input Parameters

string ("project" | "status" | "site")
required
Which question to answer. “project” lists a project’s statuses per work type (e.g. what statuses a Bug can be in for PROJ) — pass issueType to narrow to one work type. “status” resolves a single status you saw elsewhere (changelog, JQL, user phrasing) to its ID, name, and category. “site” searches statuses across the site by nameContains and/or statusCategory, returning ID and name only — use mode “status” for the full detail on any one of them.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Only with mode “project”. Narrows the result to one work type, matched by name or ID (e.g. “Bug”), so the statuses returned are exactly that work type’s. Omit to get every work type in the project.
string
Project key (e.g. PROJ) or numeric project ID — not an issue key. Required when mode is “project”.
string
Only with mode “site”. Case-insensitive substring match on the status name. Combine with statusCategory to narrow further. Omitting both filters returns a capped sample of the site’s statuses rather than all of them.
string ("new" | "indeterminate" | "done")
Only with mode “site”. Restricts results to one status category: “new” (not started), “indeterminate” (in progress), or “done”.
string
Only with mode “status”. Numeric status ID (preferred) or status name. Names are not unique in Jira, so a name returns one match with a warning — use mode “site” with nameContains to see every status sharing a name.
Slug: ATLASSIAN_MCP_LIST_LOOM_FOLDERSList the folders in the current Loom workspace that a video can be moved into, returning each folder’s id, name, and parent space. Use this to discover a destination folder id before calling moveLoomVideoToFolder, or to pick a folderId for createLoomVideoUpload / publishLoomVideo. Pass query to filter folders by name; omit it to list all folders.

Input Parameters

string
Optional text to filter folders by name. Omit to list all available folders in the workspace.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
Slug: ATLASSIAN_MCP_LIST_LOOM_VIDEOSList the Loom videos you own (that you created), most recent first. This is a primary entry point for finding a video: it returns each video’s ARI, name, and description, which you can pass to getLoomVideo, getLoomVideoDownloadUrl, or any video action. Always scoped to the current user — there is no user parameter. Optionally filter by the video’s creation date with the ISO-8601 createdAtFrom / createdAtTo bounds, and paginate with limit / offset. To find videos other people shared with you, use listLoomVideosSharedWithMe.

Input Parameters

integer
Maximum number of videos to return per page (1-100). Each result has ari, name, and description. For responseFields, select these names without videos, items, or data prefixes; omit responseFields to keep the defaults.
integer
Pagination offset. Advance by limit to fetch the next page.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string ("ASC" | "DESC")
Sort by creation date. Defaults to DESC (most recent first).
string
Only return videos created on or before this ISO-8601 timestamp (inclusive), for example 2024-02-01T00:00:00.000Z. Optional; omit for no upper bound.
string
Only return videos created on or after this ISO-8601 timestamp (inclusive), for example 2024-01-01T00:00:00.000Z. Optional; omit for no lower bound.
Slug: ATLASSIAN_MCP_LIST_LOOM_VIDEOS_SHARED_WITH_MEList the Loom videos that other people have shared with you, most recent first. Returns each video’s ARI, name, and description so you can pass the ARI to getLoomVideo, getLoomVideoDownloadUrl, or any video action. Always scoped to the current user — there is no user parameter. Optionally filter by the video’s creation date with the ISO-8601 createdAtFrom / createdAtTo bounds (this filters on when the video was created, not when it was shared with you) and paginate with limit / offset. To list videos you own, use listLoomVideos.

Input Parameters

integer
Maximum number of videos to return per page (1-100).
integer
Pagination offset. Advance by limit to fetch the next page.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string ("ASC" | "DESC")
Sort by creation date. Defaults to DESC (most recent first).
string
Only return videos created on or before this ISO-8601 timestamp (inclusive), for example 2024-02-01T00:00:00.000Z. Filters by the video’s creation date, not the date it was shared with you. Optional; omit for no upper bound.
string
Only return videos created on or after this ISO-8601 timestamp (inclusive), for example 2024-01-01T00:00:00.000Z. Filters by the video’s creation date, not the date it was shared with you. Optional; omit for no lower bound.
Slug: ATLASSIAN_MCP_LOOKUP_JIRA_ACCOUNT_IDLook up a Jira user account ID by display name or email — skip it if you already have the accountId. Returns only accountId, displayName and active, plus emailAddress when profile visibility allows it; for time zone, locale, groups, or application roles, pass the accountId on to getJiraUser. To choose an assignee use listJiraIssueAssignableUsers instead, which returns only users who can be assigned.

Input Parameters

string
required
User name or email to search for
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
number
Max results (default 10)
string ("jira_mcp_card" | "model_tool_call")
Optional invocation attribution. Jira MCP cards set jira_mcp_card; omit for model/tool-loop calls.
Slug: ATLASSIAN_MCP_MANAGE_CONFLUENCE_APPROVALRequest, decide, cancel, clear, or update a Confluence page approval. Approvals support pages only, not live docs or blog posts.

Input Parameters

string ("request" | "approve" | "requestChanges" | "cancel" | "clear" | "update")
required
Approval operation to perform. The tool maps approve to the backend decision value APPROVED and requestChanges to DENIED.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Optional comment attached to an approve or requestChanges decision. Prompt for this before approving or requesting changes when the user has not already provided or declined a comment.
string
Optional date-only due date, formatted as YYYY-MM-DD. Use with action=update to set or replace the due date.
string
Optional request message or replacement message for reviewers.
string
Active approval review identifier; required except when action is request.
string
required
Numeric Confluence page identifier, up to 19 digits. Approvals support pages only, not live docs or blog posts.
array
Reviewer list for request. Do not infer or reuse reviewers from earlier conversation context; if the user has not explicitly provided a reviewer for this approval request, ask for one before calling this tool. Each reviewer is a user and includes an account ID. Include displayName when known so responses can use names instead of only IDs. Use 1-10 unique reviewers; reviewer ids must be non-blank strings of at most 128 characters.
array
Users to add when action=update. Include displayName when known so responses can say who was added.
boolean
Set true with action=update to clear the existing due date. Do not send dueDate when clearDueDate is true.
string ("CURRENT" | "DRAFT")
required
Content version whose approval should be managed.
array
Users to remove when action=update. Include displayName when known so responses can say who was removed.
Slug: ATLASSIAN_MCP_MANAGE_JIRA_PROJECT_VERSIONCreate, update, release, or archive a Jira project version (release or fix version). create returns the version id the other actions need. If release uses moveUnfixedIssuesTo, setting released: false later does not move those issues back. Otherwise release and archive change only the version, not its issues, and update can reverse either. To view or list versions, or read their release driver and approvers, use getJiraProjectVersions.

Input Parameters

string
Version name (e.g. “v2.1.0”). Required for “create”, optional for “update”.
string ("create" | "update" | "release" | "archive")
required
The version operation to perform.
string
Atlassian account ID (AAID) of the version driver, not a name. Used by “create” and “update”. Use lookupJiraAccountId (query = a name or email) to find the AAID to pass here. When set, the response echoes back the driver’s resolved display name so you can confirm it.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
boolean
Whether the version is archived. Used by “create” and “update”.
boolean
Whether the version is released. Used by “create” and “update”.
string
Start date in yyyy-mm-dd format (ISO 8601). Used by “create” and “update”.
string
ID of the version. Required for “update”, “release”, “archive”.
string
Description of what this version includes. Used by “create” and “update”.
string
Release date in yyyy-mm-dd format (ISO 8601). Used by “create”, “update”, and “release”.
string
Project key (e.g. “PROJ”) or numeric ID. Required for “create”.
string
Version ID to move any unresolved issues to when releasing. Used by “release” only; reassigns the fixVersion of open issues from this version to the given one.
Slug: ATLASSIAN_MCP_MANAGE_JIRA_PROJECT_VERSION_RELATED_WORKCreate or update related work links on a Jira project version (release). To read a version’s existing related work, use getJiraProjectVersionRelatedWork. Both actions return the relatedWorkId a later update requires, with the stored category, title and url.

Input Parameters

string
URL of the related work link. Any valid http(s) URL is accepted — a runbook, dashboard, change record, or a link to any other system. Required for “create”; on “update” it is optional and, when omitted, the existing URL is left unchanged.
string
Display title for the related work link. Used by “create” and “update”. Optional on “create” — when omitted or blank, the URL is used as the title. On “update”, omitting it leaves the title unchanged; passing an empty/blank string clears the title and resets the display back to the URL.
string ("create" | "update")
required
The related work operation to perform.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Category of the related work. Required for “create”; on “update” it is optional and, when omitted, the existing category is left unchanged. It cannot be cleared — passing an empty/blank value is rejected. Examples: “Designs”, “Testing”.
string
required
ID of the version. Use manageJiraProjectVersion or getJiraProjectVersions to find the ID.
ID of an existing related work item. Required for “update”; it must match an item that already exists on the version (validated before the update is applied). Use getJiraProjectVersionRelatedWork to list existing items and obtain their relatedWorkId values.
Slug: ATLASSIAN_MCP_MANAGE_JIRA_SPRINTCreate, add issues to, start, update, or close a Jira sprint; get a sprintId from listJiraBoardSprints. create returns the new sprint’s id, which every later action needs. update rewrites the whole sprint, so any of name, goal, startDate or endDate you omit is cleared — resend the ones to keep; start and close keep them. Closing is one-way. addIssues returns movedIssues, as does start when given issueIdsOrKeys; both add estimatedIssues, with the field each estimate was written to, when storyPoints are passed.

Input Parameters

string
Sprint goal. Used by “create”, “start”, and “update”.
string
Sprint name. Required for “create”; optional for “start” and “update”.
string ("create" | "addIssues" | "start" | "update" | "close")
required
Which sprint lifecycle action to perform.
integer
Numeric Jira board ID. Required for “create”.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Sprint end date/time in ISO 8601 format (e.g. 2026-08-14T18:00:00.000+0000).
integer
Numeric Jira sprint ID. Required for “start”, “update”, and “close”.
string
Sprint start date/time in ISO 8601 format (e.g. 2026-08-03T09:00:00.000+0000).
object
Optional issue-key → estimate map to apply before adding issues to the sprint or starting it. Example: {“PROJ-123”: 8, “PROJ-456”: 3}. The handler resolves the correct Story Points custom field automatically for each issue.
array
Issue keys or IDs to move into the sprint when action = “addIssues” or “start”. Example: [“PROJ-123”, “PROJ-456”].
Slug: ATLASSIAN_MCP_MOVE_CONFLUENCE_CONTENTMove a Confluence page, whiteboard, database, folder, or embed to a new parent or sibling position

Input Parameters

string
required
Numeric ID of the Confluence content to move (page, whiteboard, database, embed, or folder).
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Where to place the content relative to targetId. One of: append (under targetId as a child), before (immediately before targetId as a sibling), after (immediately after targetId as a sibling).
string
required
Numeric ID of the target content. For append this is the new parent; for before/after it is the sibling.
Slug: ATLASSIAN_MCP_MOVE_LOOM_VIDEO_TO_FOLDERMove a Loom video into a folder in the current workspace. Get a destination folder id from listLoomFolders (or createLoomFolder). Identify the video by ARI or share URL.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
ARI of the destination folder, formatted as ari:cloud:loom:{siteId}:folder/activation/{activationId}/{folderId}. Obtain it from the listLoomFolders tool.
string
ARI of the Loom video to move, formatted as ari:cloud:loom:{siteId}:video/activation/{activationId}/{videoId}. Provide this or videoUrl.
string
Loom share URL for the video, for example https://www.loom.com/share/&#123;videoId&#125;. Used when videoAri is not supplied; a supporting action resolves the URL to an ARI.
Slug: ATLASSIAN_MCP_PUBLISH_ARTIFACTStep 2 of 2 for uploading an artifact. Finalizes content whose bytes were already transferred via createArtifactsUpload (step 1), using the contentId from that step’s completionPayload. Only call after the upload has completed. Creates a new artifact, or publishes a new version by supplying an existing artifact ID. Save, preserve, or store AI-generated analysis, reports, dashboards, charts, visualizations, and HTML slide decks durably behind a persistent link. Returns that link, which does not by itself grant anyone access: use shareArtifact to let named users, groups, or teams open it.

Input Parameters

string
Existing artifact ID to update by publishing this content as its next immutable version. Omit to create a new artifact.
string
required
Artifact display name.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Content ID from createArtifactsUpload completionPayload.contentId. Provide only after the upload succeeds.
string
required
Exact MIME type used for both the upload and artifact metadata, such as text/html, text/markdown, or text/csv.
string
required
Free text describing what the artifact contains, up to 1000 characters. It is indexed to improve how well the artifact is found in search, so summarise the content and its purpose rather than restating the name.
Slug: ATLASSIAN_MCP_PUBLISH_LOOM_VIDEOStep 2 of 2 for uploading a new video to Loom. Finalizes a video whose bytes were already transferred via createLoomVideoUpload (step 1), using the keyPath and fileName from that step’s completionPayload. Only call this after the upload has completed. Returns the user-facing Loom share URL. Optionally place the video in a folder or space.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
The keyPath returned in completionPayload.keyPath from createVideoUpload. Must end in a file extension or the video will never finish transcoding.
string
Optional ARI of a Loom space to post the video into.
string
required
Display name for the video as it should appear in the Loom UI, for example Loom Live Sizzle.mp4. Use the value returned in completionPayload.fileName from createVideoUpload.
string
Optional ARI of a Loom folder to place the video in.
Slug: ATLASSIAN_MCP_QUERY_ASSETS_OBJECTSQuery Assets objects with generated AQL for one object type in the selected site.

Input Parameters

array
Exact Assets attribute filter in name=value form
string
Maximum number of results to return
array
Compatibility alias for accountId; accepts multiple people
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
array
Atlassian account ID or IdentityUser ARI; accepts multiple people
array
Assets LIKE attribute filter in name=pattern form
string
required
Assets object type, for example Service or Hardware
array
Assets user attribute to query
Slug: ATLASSIAN_MCP_QUERY_ASSETS_OBJECT_SCHEMA_ATTRIBUTESQuery attributes for one or more Assets object schemas in the selected site.

Input Parameters

array
Object schema ID
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
Slug: ATLASSIAN_MCP_QUERY_ASSETS_OBJECTS_USING_AQLQuery Assets objects with raw or generated AQL in the selected site.

Input Parameters

string
Raw AQL query string
array
Exact Assets attribute filter in name=value form
string
Maximum number of results to return
array
Compatibility alias for accountId; accepts multiple people
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
array
Atlassian account ID or IdentityUser ARI; accepts multiple people
array
Assets LIKE attribute filter in name=pattern form
array
Compatibility alias for the AQL query
string
Assets object type, for example Service or Hardware
array
Assets user attribute to query
Slug: ATLASSIAN_MCP_QUERY_ASSETS_OBJECT_TYPESQuery Assets object types by schema in the selected site.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Schema ID, matching-workspace ARI or exact schema name
boolean
Exclude abstract object types
Slug: ATLASSIAN_MCP_QUERY_ASSETS_REFERENCE_TYPESQuery global or schema-scoped Assets reference types in the selected site.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Object schema ID
boolean
Include all reference types
Slug: ATLASSIAN_MCP_RECOVER_LOOM_VIDEORecover a Loom video that failed to process, by initiating a recovery job to re-process it. Use this when a video is stuck or errored (for example isComplete is false in getLoomVideo). Identify the video by ARI or share URL.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
ARI of the Loom video, formatted as ari:cloud:loom:{siteId}:video/activation/{activationId}/{videoId}. Provide this or videoUrl.
string
Loom share URL for the video, for example https://www.loom.com/share/&#123;videoId&#125;. Used when videoAri is not supplied; a supporting action resolves the URL to an ARI.
Slug: ATLASSIAN_MCP_REMOVE_CONFLUENCE_CONTENT_PERMISSIONSRemoves content-level permission grants from a single Confluence content entity. Optionally narrow what is removed by operation, principal-type, and/or principal-id. Omitting all three filters clears ALL Specific access grants on the content. This does not change General access.This can revoke access. The server protects against the current user locking themselves out of their own content.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric ID of the Confluence content entity (page, blog post, whiteboard, database, folder, etc.) to remove permission grants from.
string
Only remove grants for this operation. One of: read, update. Omit to match any operation.
string
Only remove grants for this principal ID (Atlassian account ID for a user, group ID for a group). Omit to match any principal.
string
Only remove grants for this principal type. One of: user, group. Omit to match any principal type.
Slug: ATLASSIAN_MCP_REOPEN_CONFLUENCE_TASKReopen a completed Confluence inline task (mark it incomplete)

Input Parameters

string
required
The ID of the completed Confluence inline task to reopen.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
Slug: ATLASSIAN_MCP_REPLACE_CONFLUENCE_CONTENT_PERMISSIONSReplaces ALL content-level permission grants on a single Confluence content entity with the supplied set. Grants not present in the request are removed, so this can revoke access — prefer addConfluenceContentPermissions when you only intend to add grants.Pass the full desired grant set via the permissions input, an array of objects shaped exactly like: [ { “operation”: “update”, “principals”: [ { “principalType”: “user”, “principalId”: “<atlassian-account-id>” }, { “principalType”: “group”, “principalId”: “<group-id>” } ] } ] Enums: operation is one of read | update; principalType is one of user | group. For a user, principalId is the Atlassian account ID; for a group, principalId is the group ID.operation read = can view, update = can edit (edit includes view). A principal has only ONE effective level, so listing a principal under read when they should keep editing leaves them view-only — list them under update to preserve edit. Never list the same principal under both operations. Replacing Specific access does not change General access. Because this REPLACES the whole set, always include yourself with update if the content is (or is becoming) EDIT_RESTRICTED / VIEW_RESTRICTED. The server protects against locking the current user out of their own content.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric ID of the Confluence content entity (page, blog post, whiteboard, database, folder, etc.) whose permission grants should be fully replaced.
array
required
The complete desired set of permission grants. Array of objects, each with an operation (read | update) and a principals array. Each principal has a principalType (user | group) and a principalId (Atlassian account ID for a user, group ID for a group). Grants not listed here are removed. A principal must appear under only one operation across the entire request. Example: [{ “operation”: “update”, “principals”: [{ “principalType”: “group”, “principalId”: “<group-id>” }] }].
Slug: ATLASSIAN_MCP_RESOLVE_CONFLUENCE_CONTENT_MACROSResolve supported Confluence macro wrappers into per-macro HTML displayed in Confluence web. Use after getConfluenceContent when a full document read returns wrappers instead of visible content, especially for Include Page, Excerpt Include, and Jira macros. Use the returned HTML bodies to supplement the base document; this operation does not reconstruct the full page.

Input Parameters

boolean
Set true to resolve all supported macros, up to 10, in document order. Use this all-mode selector only when macroIds is omitted.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
array
One or more unique, non-blank macro IDs to resolve. Use this for explicit macro selection and omit all. The Confluence server owns the current explicit-ID limit, so MCP does not declare a maxItems cap.
string
required
Positive numeric Confluence content ID that contains the macros to resolve.
Slug: ATLASSIAN_MCP_RESTORE_CONFLUENCE_CONTENT_VERSIONRestore an earlier version of a Confluence page, live doc, or blog post as a new latest version

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Optional message recorded on the newly created latest version.
string
required
Numeric ID of the Confluence page, live doc, or blog post.
boolean
Also restore the title from the selected historical version. Defaults to false.
integer
required
Positive historical version number to restore.
Slug: ATLASSIAN_MCP_REVOKE_ARTIFACT_SHAREStop sharing an artifact with named users, groups, or teams, or with every audience at once. Supply either audienceAris or revokeAll, never both and never neither. Revoking a share that was never granted still succeeds. This does not change the artifact’s access level. An artifact readable by anyone with the link, or by the whole organisation, stays readable after every share is revoked, and the response says so when that is the case.

Input Parameters

string
required
Artifact ID to revoke shares on.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
boolean
Set to true to revoke every individual share instead of named audiences. Only true is accepted, so omit this input to revoke named audiences. Cannot be combined with audienceAris. Does not make the artifact private.
array
Users, groups, and teams to stop sharing with, as identity ARIs, the same form shareArtifact takes. Resolve a name or email to an account ID first with lookupJiraAccountId or getPeopleInfo rather than fabricating an ARI, and confirm which person is meant when a name matches more than one. At least one entry is required when supplied; an empty list is rejected rather than treated as everyone. Omit only when setting revokeAll.
Slug: ATLASSIAN_MCP_SCAN_CODE_REPOList the file paths in a connected source-control repository at a specific commit, optionally filtered by a glob or restricted to a subtree. Returns paths only, no file contents. Paginated — pass the returned nextCursor to fetch the next page.

Input Parameters

string
required
Pass the matched file repo slug, e.g. example-repo, not example-org/example-repo; supply the owner separately in workspace.
string
Repository-relative directory prefix, e.g. src/server. Use root for this operation, not path. Omit it to scan the repository root. Narrow with this before raising limit.
integer
Maximum number of paths per page. Defaults to the service’s own value when omitted.
string
Pagination cursor from a previous result’s nextCursor.
string
Glob matched against each path. Omit to list every indexed file.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Repository owner — a Bitbucket workspace or GitHub organization. Use workspace (not namespace). Pass the matched file workspace from searchCode; do not infer it from the search filter.
string
required
Commit to list at; a branch name is also accepted here. A searchCode result’s matchedFiles[].version, or a listCodeDirectory entry’s commitHash, supplies one.
Slug: ATLASSIAN_MCP_SEARCHSemantically search Jira, Confluence, and connected third-party content using Rovo Search. ALWAYS use this tool to search for Jira and Confluence content unless CQL or JQL is specified. The utilisation of this tool may consume up to 10 Rovo Credits. If the user or organization does not have any Rovo Credits available, the tool call will fail.

Input Parameters

string ("STANDARD" | "AGENTIC" | "ENHANCED")
Search mode. STANDARD returns matching records; AGENTIC asks the search agent to synthesize an answer with full agentic effort; ENHANCED uses a faster agentic loop to return ranked citations.
integer
string
required
The search query.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string ("ALL" | "JIRA" | "CONFLUENCE" | "THIRD_PARTY")
Filters results by product and is only applicable for standard mode. ALL searches everything. JIRA returns only Jira issues/boards/projects. CONFLUENCE returns only Confluence pages/blogs/spaces. THIRD_PARTY returns content from ready connected external sources.
Slug: ATLASSIAN_MCP_SEARCH_ASSETS_OBJECTSSearch Assets objects by name or query-builder filters in the selected site.

Input Parameters

string
Raw AQL query string
array
Exact Assets attribute filter in name=value form
string
Maximum number of results to return
string
Natural text to match against Assets object names
array
Compatibility alias for accountId; accepts multiple people
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
array
Atlassian account ID or IdentityUser ARI; accepts multiple people
array
Assets LIKE attribute filter in name=pattern form
array
Natural text to match against Assets object names
string
Assets object type, for example Laptop or Hardware
array
Assets user attribute to query
Slug: ATLASSIAN_MCP_SEARCH_CODESearch source code across connected source-control providers using semantic, lexical, or hybrid matching. Returns matching files along with the specific code spans that matched.

Input Parameters

string ("hybrid" | "semantic" | "lexical")
hybrid (default) blends meaning and literal matching. semantic finds conceptually similar code. lexical matches exact text — use it for known identifiers.
string
Restrict results to files under this repository-relative path prefix.
string
Repository slug only, e.g. example-repo, not example-org/example-repo. Supply the owner separately in namespace. Accepts ”|“-separated alternates.
string
required
What to search for. Use natural language for semantic and hybrid modes (e.g. “retry logic for rate limited requests”); use literal text for lexical mode (e.g. “createSpinner”).
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Programming language filter (e.g. typescript, python).
string
File extension filter without the dot (e.g. ts, py).
string
Search filter for a GitHub organization or Bitbucket workspace. Accepts multiple alternates separated by ”|”. For file reads and navigation, use the matched file’s workspace coordinate instead of this filter.
integer
Maximum number of matching files to return. Each result carries raw source, so raise this only when the extra breadth is genuinely needed.
Slug: ATLASSIAN_MCP_SEARCH_CONFLUENCESearch Confluence content with CQL

Input Parameters

string
required
CQL query string (max 4096 chars). Examples: type = page AND space = "DEV", title ~ "onboarding" AND lastmodified > "2025-01-01", creator = currentUser() AND type IN (page, blogpost) ORDER BY lastmodified DESC.
integer
Max number of results to return per page (1-100). Defaults to 25.
string
Opaque pagination cursor returned by a previous call. Omit to start from the first page.
string
Comma-separated list of content properties to expand on each result. Common values: space, version, body.view, metadata.labels, ancestors. Use sparingly to avoid large responses.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
JSON-encoded execution context, e.g. {“spaceKey”:“DEV”}. Restricts the search to the supplied scope.
Slug: ATLASSIAN_MCP_SEARCH_FOCUS_AREASSearch focus areas using text and structured filters with optional pagination and sorting. Omitting query and filters lists/browses focus areas. Exact lookup by ARI, UUID, or URL should use getFocusArea instead. getFocusArea also returns more detail per focus area than search results do — startDate, archived/draft/starred/watching flags, created and updated timestamps, and direct child focus areas — so follow up with it once a specific focus area is identified. Set include.aboutContent to true to fetch about content, and/or pass include.statusUpdates for latest status updates per result. Paginate with first/after using pageInfo.endCursor. Custom field filtering is supported through filters.customFields (resolve field searchKeys and select option UUIDs with getFocusAreaCustomFields first); filtering for focus areas where a custom field has no value is not supported — do not retry with other operators to express it.

Input Parameters

array
Sort order for focus areas. Shape: [{ “field”: “targetDate”, “direction”: “asc” }]. Each item must have field (one of name, status, health, targetDate, focusAreaType) and direction (asc or desc). When omitted, results default to name descending upstream.
string
Cursor for the next page. Pass pageInfo.endCursor from the previous response.
integer
The number of focus areas to return in a paginated result.
string
Plain-text focus area search.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
object
Structured filters for focus area search. Shape: { “status”: “IN_PROGRESS”, “health”: “AT_RISK”, “starred”: true, “owner”: “<accountId>”, “archived”: false, “customFields”: [{ “field”: “<searchKey>”, “operator”: “EQUALS”, “value”: ”…” }] } — all fields optional, combined with AND. status is one of PENDING, IN_PROGRESS, PAUSED, COMPLETED; health is one of OFF_TRACK, AT_RISK, ON_TRACK; starred accepts only true (focus areas you follow or watch); owner is an Atlassian account ID; archived is a boolean. Each customFields item has field (the definition’s searchKey from getFocusAreaCustomFields — definition ARIs are not accepted, and searchKeys are case-sensitive and may be mixed-case; do not fabricate them), operator, and value (single value) or values (array, for IN/NOT_IN only). operator is one of EQUALS, CONTAINS, GT, GTE, LT, LTE, IN, NOT_IN, validated against the field’s type: EQUALS applies to all types; CONTAINS to TEXT only; GT, GTE, LT, LTE to NUMBER and DATE; IN and NOT_IN to select and user fields. Select field values are option UUIDs (not labels) and user field values are Atlassian account IDs, both from getFocusAreaCustomFields. Filtering for focus areas where a custom field has no value is not supported.
object
Optional focus area details to include. Shape: { “aboutContent”: true, “statusUpdates”: {} }. aboutContent is a boolean (defaults to false). statusUpdates is an object, not a boolean — pass an empty object ({}) to include it with its defaults. statusUpdates.first defaults to 1 (max 20); statusUpdates.includeTransitions defaults to true (previous/new status and health).
Slug: ATLASSIAN_MCP_SEARCH_GOALSFind Atlassian Goals by text and structured filters.

Input Parameters

array
Up to three sort criteria in priority order. Each item has field and direction (asc or desc).
integer
Maximum number of Goals to return.
string
Plain-text Goal search, not raw TQL.
string
Use pageInfo.endCursor from the previous response to fetch the next page.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
object
Optional filters. Supported fields are archived, teamId, ownerAccountId, followerAccountId, statusPhases, and tag.
Slug: ATLASSIAN_MCP_SEARCH_JIRA_ISSUES_USING_JQLSearch for Jira issues using JQL, with an optional approximate count. Use view: “evidence” to fetch and map custom fields. Page with nextPageToken until isLast is true. For one known issue, use getJiraIssue. JQL only returns issues; inferring anything else from issue rows is silently incomplete. Use the purpose-built operation for sprints, boards, board config, field history, worklogs, releases, accountIds, issue types, projects and statuses.

Input Parameters

string
required
JQL query string e.g. “project = PROJ AND status = ‘In Progress’”. If the tool returns a repairHint, follow it and retry.
string ("compact" | "evidence" | "full")
Output view preset. Default: “compact”. Options: “compact”, “evidence”, “full”. compact = minimal fields for scanning; evidence = decision-relevant detail; full = complete response.
array
Fields per issue (e.g. [“summary”, “status”, “customfield_10010”]). customfield_* IDs are site-specific — discover the correct id for story points etc. on this Cloud site. Honoured exactly when supplied. Values map to issues[].fields.customFields (human labels), not raw customfield_* keys. The default “compact” view omits custom fields; use view: “evidence” for velocity/sprint JQL (fetches and maps all custom fields) or pass explicit customfield_* IDs.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
number
Maximum results to return (default 50, max 100)
string ("jira_mcp_card" | "model_tool_call")
Optional invocation attribution. Jira MCP cards set jira_mcp_card; omit for model/tool-loop calls.
string
Pagination token from a previous response to fetch the next page
string ("issues" | "count" | "all")
Default “issues”. Never count for normal search or if nextPageToken used. If total for same query is known, reuse it. Use “count” only when no trusted count exists and either the user asks or a downstream step needs it. Use “all” only if both count and issues required.
string ("markdown" | "html")
Format for rich-text bodies (description, environment, comments) when the view returns them. Defaults to markdown; html is lossless for a later editJiraIssue. Issues holding anything markdown cannot represent (media, panels, expands, statuses, @mentions) are returned as HTML automatically, decided per issue. An explicit markdown request is overridden for those bodies, with a warning saying so; appliedContentFormat in the response reports the format you actually got.
Slug: ATLASSIAN_MCP_SEARCH_JSM_REQUESTSSearch one bounded page of caller-visible Jira Service Management requests. Use JQL for project, request type, assignee, status, approval, text, due-date, and ordering filters. Use this tool when JSM requests, issues, or work items need your attention, when you need urgency signals from SLA state or sentiment, or when you need to identify auto-resolvable work items after approval. Returns summary, status, assignee, request type, sentiment, SLA state, card display data (issue-type icon, status category, assignee and requester avatars), URLs, and compact resolver-plan availability. This tool does not return full request details or plan steps. When the upstream request search ranks rows, it preserves the total score, each score component, and evidence so clients can render and explain urgency consistently.

Input Parameters

string
Optional Jira JQL expression for filtering and ordering requests, including project selection. Example: project = ITSM AND assignee = currentUser() AND statusCategory != Done ORDER BY updated DESC. Omit to use the default open-request search.
integer
Maximum request rows in one page. Defaults to 10; maximum 10. Continue with nextPageToken for more.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Token from a previous response for the same filters.
Slug: ATLASSIAN_MCP_SEARCH_PROJECTSFind Atlassian Projects by text and structured filters.

Input Parameters

array
Sort criteria in priority order. Each item has field and direction (asc or desc).
integer
Maximum number of Projects to return.
string
Plain-text Project search, not raw TQL.
string
Use pageInfo.endCursor from the previous response to fetch the next page.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
object
Optional filters. Supported fields are archived, teamId, ownerAccountId, contributorAccountId, followerAccountId, reportingLineAccountId, statusPhases, linkedGoalKey, and tag.
Slug: ATLASSIAN_MCP_SEARCH_TALENT_POSITIONSSearch Talent positions by their own attributes using an RQL filter, returning a paginated list of positions with their requested field values (each position’s ARI is the id, so this is how you obtain ARIs for getTalentPosition). Use this for flat attribute filters — job title, country, level, status, job family, tenure. Use getTalentPositionsByEntity INSTEAD when scoping to a reporting line or a focus area, and getTalentGroupMetrics INSTEAD when you only need counts rather than the positions themselves. RQL field IDs and their valid values are workspace-specific and must not be guessed — call getTalentFields to resolve them. The common built-ins are positionJobTitle, positionCountry, positionLevel, positionStatus, positionRole, positionManager, positionTenure, positionJobFamily, positionEmploymentType, positionWorker and team; for anything else, or for a field’s valid values, go through getTalentFields. If a filter returns nothing, suspect the field ID or its value and check it with getTalentFields rather than adding more filters.

Input Parameters

string
Radar Query Language filter and ordering that scopes which positions are returned. Field IDs and values are workspace-specific — resolve them with getTalentFields rather than guessing. Omit to search across all positions the caller can see.
string
Forward pagination cursor from a previous response’s endCursor.
integer
Maximum number of positions to return in this page, 1-100. Defaults to 25.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
array
Array of position field ID strings to return for each position, as returned by getTalentFields. When omitted, a default set of position fields is returned.
Slug: ATLASSIAN_MCP_SEARCH_TEAMSSearch Atlassian teams by name with cursor pagination. Core team fields are returned by default; pass expand [“members”] to include a separately paginated member summary for each team.

Input Parameters

string
Team page cursor from a previous result.
integer
Number of teams to return, from 1 to 100.
string
Case-insensitive team-name search. Omit to list teams.
array
Optional unique expansion list. The only supported value is “members”.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Nested member cursor; valid only when expand includes “members”.
integer
Members per team when expand includes “members”. Defaults to 100.
Slug: ATLASSIAN_MCP_SET_CONFLUENCE_CONTENT_RESTRICTION_STATESets the high-level restriction state for a single Confluence content entity. Provide state as one of: OPEN — “Open, Anyone in this space can edit”: everyone with space access can VIEW and EDIT. EDIT_RESTRICTED — “Open, Anyone in this space can view”: everyone with space access can VIEW; only Specific access update principals can edit. VIEW_RESTRICTED — “Restricted, Only specific people can view or edit”: only Specific access read/update principals can VIEW; only update principals can edit.HOW GENERAL AND SPECIFIC ACCESS WORK TOGETHER: the state is the General access baseline. Moving away from OPEN removes broad access. Permission grants are Specific access exceptions that add access for individual users or groups; they do not remove General access or make content private by themselves. A principal has exactly ONE Specific access level — update, read, or none — and update includes read/view. Changing the state does not create or modify Specific access grants.SELF-LOCKOUT: when leaving OPEN, the caller must retain update; read is not sufficient for editing. Private creation already performs the safe VIEW_RESTRICTED + creator update setup. Existing-state and self-lockout validation belongs to the Confluence monolith, and this tool never disables it.

Input Parameters

string ("OPEN" | "EDIT_RESTRICTED" | "VIEW_RESTRICTED")
required
New General access state. OPEN = anyone in the space can edit; EDIT_RESTRICTED = anyone in the space can view; VIEW_RESTRICTED = only Specific access principals can view or edit.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric ID of the Confluence content whose restriction state should be set.
Slug: ATLASSIAN_MCP_SET_CONFLUENCE_CONTENT_STATUSSet the content state (status) of a Confluence page or blog post

Input Parameters

number
ID of an existing content state to apply. Wins over name+color.
string
Name of a custom content state (1-20 chars). Sent together with color. Ignored when id is provided.
string
Hex color of the custom content state (e.g. #FF8B00). Sent together with name. Ignored when id is provided.
string
Which version of the content to update: current (default) or draft. Lowercase only.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric ID of the Confluence content whose state should be set.
Slug: ATLASSIAN_MCP_SET_CONFLUENCE_SPACE_INSTRUCTIONSSet the space instructions for a Confluence space

Input Parameters

string
required
Non-empty space instructions body to store.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Numeric ID of the Confluence space. Resolved to the space key before the request. Provide either spaceKey or spaceId.
string
Confluence space key, for example DEV or ~accountId for a personal space. Provide either spaceKey or spaceId.
string ("markdown" | "html")
Instruction body format to store. Use markdown or html. Do not send storage or ADF.
Slug: ATLASSIAN_MCP_SET_JSM_AGENT_AVAILABILITYSet one Jira Service Management Workforce Management agent’s availability for a service project. Use this for “set me available”, “set me on break”, or an explicitly supplied agentAccountId when you are authorized to update that agent. Status accepts AVAILABLE or ON_BREAK and TWG-compatible aliases available, active, online, away, on-break, or unavailable. This is not for reading availability, bulk team updates, project defaults, assignment, or Live Chat status.

Input Parameters

string ("AVAILABLE" | "ON_BREAK" | "available" | "active" | "online" | "away" | "on-break" | "unavailable")
required
Availability status to set. Use AVAILABLE or ON_BREAK; aliases available, active, online, away, on-break, and unavailable are accepted.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Jira Service Management project key or numeric project ID. Do not guess the project.
string
Optional Atlassian account ID of the agent to update. Omit only to update the authenticated agent; do not infer an agent from a name or email.
Slug: ATLASSIAN_MCP_SHARE_ARTIFACTGrant named users, groups, or teams permission to view an existing artifact. Use this when someone cannot open an artifact yet, because publishArtifact returns a link but grants nobody access, and this is what makes that link work for them. This adds individual grants; it does not make the artifact readable by anyone with the link or by the whole organisation, which are the artifact’s access level and are not set here. The call is atomic, so if any audience is invalid nothing is granted. Returns the artifact’s resulting access level and the audiences it is now shared with.

Input Parameters

string
required
Artifact ID to grant access to.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
array
required
Users, groups, and teams to share with. All three are identity ARIs of the form ari:cloud:identity::user/<accountId>, ari:cloud:identity::group/<groupId>, or ari:cloud:identity::team/<teamId>. At least one is required. Resolve a name or email to an account ID first with lookupJiraAccountId or getPeopleInfo — via execute as name=lookupJiraAccountId when it is not a top-level tool — rather than fabricating an ARI, and confirm which person is meant when a name matches more than one, because a wrong ARI grants the wrong person access. Team ARIs are returned ready to use by searchTeams. Use this only for named audiences. Granting access to everyone with the link or to the whole organisation is the artifact’s access level and cannot be set here.
Slug: ATLASSIAN_MCP_SHARE_LOOM_VIDEOShare a Loom video with one or more specific Atlassian users by sending them a notification (with an optional message). This notifies people; it does not change the video’s visibility — to make a video WORKSPACE- or PUBLIC-visible use updateLoomVideoPermissions instead. Identify the video by ARI or share URL, and recipients by their Atlassian user ARIs or exact name/email address.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Optional message to include in the share notification sent to recipients.
array
List of Atlassian user ARIs to share the video with, formatted as ari:cloud:identity::user/{aaid}. Provide this or recipientQueries, up to 50.
string
ARI of the Loom video, formatted as ari:cloud:loom:{siteId}:video/activation/{activationId}/{videoId}. Provide this or videoUrl.
string
Loom share URL for the video, for example https://www.loom.com/share/&#123;videoId&#125;. Used when videoAri is not supplied; a supporting action resolves the URL to an ARI.
array
Exact names or email addresses of active workspace members. Every value must resolve to exactly one member. Provide this or userAris.
Slug: ATLASSIAN_MCP_STAR_CONFLUENCE_CONTENTStar a Confluence content item for the current user

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric Confluence content ID.
Slug: ATLASSIAN_MCP_STAR_CONFLUENCE_SPACEStar a Confluence space for the current user

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Numeric ID of the Confluence space. Resolved to the space key before the request. Provide either spaceId or spaceKey.
string
Confluence space key. Provide either spaceKey or spaceId.
Slug: ATLASSIAN_MCP_TRANSITION_JIRA_ISSUEMove a Jira issue through its workflow and/or into a sprint or the backlog — at least one is required. Take transitionId from listJiraIssueTransitions; transitionName is the transition’s own name, not the target status. Returns the status the issue actually landed in, so no read-back is needed. If the sprint/backlog move fails after the status change succeeds, the status change stays — retry the move alone, not the whole call.

Input Parameters

object
Optional Jira field values to apply during the workflow transition.
object
Optional Jira field update operations to apply during the workflow transition. A comment passed here may be dropped without error — the transition reports success and no comment is created. Use addOrEditJiraIssueComment instead.
integer
Only used when assignToBacklog is true: targets this specific board’s backlog (board IDs from listJiraBoards). Ignored otherwise.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
integer
Assign the issue into this sprint. Mutually exclusive with assignToBacklog.
string ("jira_mcp_card" | "model_tool_call")
Optional invocation attribution. Jira MCP cards set jira_mcp_card; omit for model/tool-loop calls.
string
required
Issue key like PROJ-123
string
Transition ID (get from listJiraIssueTransitions). Provide either transitionId or transitionName.
string
Name of the transition itself, not the target status — the two often differ, so “Done” does not match a transition named “Review->Done”. Provide either transitionId or transitionName.
boolean
Set true to assign the issue to the backlog, mutually exclusive with sprintId. Optionally use boardId to target a specific board’s backlog.
object
Optional issue history metadata to attach to the workflow transition.
Slug: ATLASSIAN_MCP_TRANSITION_JSM_REQUESTPerform one customer/request-portal-visible Jira Service Management request transition selected from getJsmRequestActionMetadata. This is for help-seeker/customer portal transitions, not agent-side queue or generic Jira workflow transitions. It returns compact execution metadata only; use getJsmRequest afterwards when refreshed request state is needed.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
JSM customer request issue ID or key, for example HD-123.
string
required
Customer/request-portal transition ID returned by getJsmRequestActionMetadata. Do not provide a transition name.
string
Optional public, customer-facing comment to include with the transition. Maximum 5000 characters. Do not use for an internal note.
Slug: ATLASSIAN_MCP_UNARCHIVE_CONFLUENCE_CONTENTUnarchive (restore) a single Confluence content entity

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric ID of the Confluence content to unarchive.
Slug: ATLASSIAN_MCP_UNSTAR_CONFLUENCE_CONTENTRemove a star from a Confluence content item for the current user

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric Confluence content ID.
Slug: ATLASSIAN_MCP_UNSTAR_CONFLUENCE_SPACERemove a star from a Confluence space for the current user

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Numeric ID of the Confluence space. Resolved to the space key before the request. Provide either spaceId or spaceKey.
string
Confluence space key. Provide either spaceKey or spaceId.
Slug: ATLASSIAN_MCP_UNWATCH_CONFLUENCE_CONTENTStop watching a Confluence content item for the current user

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric Confluence content ID.
Slug: ATLASSIAN_MCP_UNWATCH_CONFLUENCE_LABELStop watching a Confluence label for the current user

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Confluence label name.
Slug: ATLASSIAN_MCP_UNWATCH_CONFLUENCE_SPACEStop watching a Confluence space for the current user

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Numeric ID of the Confluence space. Resolved to the space key before the request. Provide either spaceId or spaceKey.
string
Confluence space key or alias. Provide either spaceKey or spaceId.
Slug: ATLASSIAN_MCP_UPDATE_CAPACITY_PLAN_ALLOCATIONSAllocate people to a single work item over one or more time periods in Individual Capacity Planning. USE WHEN the user asks to put someone on a work item for a period, to change how much of their time it takes, to book leave, or to clear an allocation. Every person in contributorDataIds is assigned to the work item automatically, so it does not need to be assigned to them first, and every allocation is applied to every person - the number of writes is contributorDataIds x allocations, which must not exceed 100. Only one work item per call. Resolve a non-project work ARI with listCapacityPlanNonProjectWork rather than fabricating one. Each allocation covers a period and carries the TOTAL effort for that period, of any length. To express a RATE, send one allocation per interval: “2 days a week for three weeks” is three allocations of 2, NOT one allocation of 2 spanning three weeks. A single allocation spanning all of September means “this much effort across September”, which the plan spreads over the weeks in it. Re-running the same periods REPLACES those allocations rather than adding to them, so the call is safe to repeat; set value to 0 to clear a period. Because value is the TOTAL for the period and re-running replaces it, any RELATIVE change - “add a day”, “bump Chris to 3 days”, “halve it” - needs the current figure first. Call getCapacityPlanAllocations with the same contributorDataIds and workDataIds, the same date window, and expand: [“contributions”], then send the new total. Writing the relative amount directly overwrites the existing allocation instead of adding to it. An absolute request (“put Chris on PROJ-42 at 50% in September”) needs no prior read. This does NOT add anyone to a capacity plan and cannot create work items - contributors and work items are global, so an allocation written here shows up on every plan they belong to, matching the UI. Add ‘contributions’ to expand to return the value written per period and confirm what landed, ‘contributorAggregations’ for each person’s total contribution and availability across ALL their work in the allocated window (use this to report whether the change has pushed someone over capacity), and ‘workAggregations’ for the work item’s total effort across ALL contributors. Both aggregations come back as separate top-level objects. Omit expand when a simple confirmation is enough - each value costs extra work upstream. Capacity plans assume a baseline 40-hour working week, so 5 DAYS, 40 HOURS, and 100 PERCENTAGE are all the same amount - say so when reporting days or percentages.

Input Parameters

array
Optional extra data to return after the write, as an array of strings. Supported values: ‘contributions’ (the value written per period, per allocation, so the result can be confirmed back to the user), ‘contributorAggregations’ (per person allocated, total contribution and availability across ALL of their work for the allocated window - returned as a separate top-level object; use it to report whether the change left someone over-allocated), and ‘workAggregations’ (the work item’s total contribution effort across ALL contributors on it - a separate top-level object with totalContribution only). Combine freely, or omit when a simple confirmation is enough.
string
required
ARI of the single work item to allocate to. Supported forms: Jira issues (ari:cloud:jira:{cloudId}:issue/{issueId}), Atlas projects (ari:cloud:townsquare:{cloudId}:project/{projectId}), and non-project work / custom contribution targets (ari:cloud:capacity-planning::custom-contribution-target/activation/{activationId}/{targetId}). One work item per call - allocating the same people to a second work item needs a second call.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string ("PERCENTAGE" | "HOURS" | "DAYS")
Unit for every value in allocations and for all returned effort figures. Defaults to PERCENTAGE. Use PERCENTAGE when the request is about utilisation or how much of someone’s time is taken up, HOURS or DAYS when it is about effort. A baseline working week is 40 hours, so 5 DAYS, 40 HOURS, and 100 PERCENTAGE are all the same amount.
array
required
The periods to allocate, each applied to every person in contributorDataIds. Array of objects shaped { “startDate”: “YYYY-MM-DD”, “endDate”: “YYYY-MM-DD”, “value”: 2 } - all three fields required, startDate not after endDate, value a number >= 0 where 0 clears that period. value is the TOTAL effort for the period in the unit given by valueType, so send one object per interval to express a rate. Periods must be distinct; two objects covering the same period is an error. Maximum 100, and contributorDataIds x allocations must not exceed 100.
array
required
Array of contributor ARIs identifying the people to allocate, in the form ari:cloud:identity::user/{accountId} where {accountId} is an Atlassian account ID (e.g. ari:cloud:identity::user/5ea00a99d31fdf0c0d783dd5). Each person is assigned to the work item if not already, and every allocation is applied to every person. Maximum 100, and contributorDataIds x allocations must not exceed 100.
Slug: ATLASSIAN_MCP_UPDATE_CAPACITY_PLAN_NON_PROJECT_WORKRename an existing non-project work item in Individual Capacity Planning. “Non-project work” is a bucket of time that is not a Jira issue or an Atlas project, such as Leave, Run the Business (RtB), on-call, or training. USE WHEN the user asks to rename an existing non-project work item. This only changes the item’s name; it does not move allocations, add contributors, or delete anything. To change who is allocated or how much effort a period carries, use updateCapacityPlanAllocations instead. Resolve the item’s id first with listCapacityPlanNonProjectWork rather than fabricating one. Returns whether the update succeeded and any errors.

Input Parameters

string
required
Identifier of the non-project work item to rename. Resolve it with listCapacityPlanNonProjectWork rather than fabricating one.
string
required
New display name for the non-project work item, e.g. “Annual Leave”.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
Slug: ATLASSIAN_MCP_UPDATE_CONFLUENCE_COMMENTUpdate an existing Confluence footer or inline comment on a page or blog post

Input Parameters

object
required
Replacement comment body object. Use { “format”: “markdown” | “html”, “value”: ”…” }. format is required and must be “markdown” or “html”; value is required, non-empty, and at most 4096 characters.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric ID of the footer or inline comment to update. Confluence comment IDs are int64 values (max 19 digits).
string ("footer" | "inline")
Optional type guard. When set, the target comment must match: “footer” for page-level comments or “inline” for anchored comments.
number
Optional current version observed by the caller. Used for optimistic concurrency; stale values return version_conflict guidance.
Slug: ATLASSIAN_MCP_UPDATE_CONFLUENCE_COMMENT_RESOLUTIONResolve or reopen a Confluence footer or inline comment

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
boolean
required
Set to true to resolve the comment, or false to reopen it.
string
required
Numeric ID of the top-level footer or inline comment to resolve or reopen. Confluence comment IDs are int64 values (max 19 digits).
string ("footer" | "inline")
Optional type guard. Set to “footer” for page-level comments or “inline” for anchored comments.
Slug: ATLASSIAN_MCP_UPDATE_CONFLUENCE_CONTENTUpdate Confluence docs, whiteboards, or databases.Before choosing body.format or authoring an edit, call getContentFormatGuide through execute with name=getContentFormatGuide and inputs={toolName}. Use updateConfluencePage for pages, blog posts, and live docs; updateConfluenceWhiteboard for whiteboards; or updateConfluenceDatabase for databases.Space instructions describe how to author content in a Confluence space. Apply relevant guidance to the content you create or update. Follow this decision rule:
  1. Before authoring, call getConfluenceSpace for the target space unless getConfluenceContent returned metadata.hasSpaceInstructions=false for content in that space. If getConfluenceSpace already returned for the same cloudId and space during the current task, reuse its spaceInstructions and do not call it again.
  2. When the value is true or unknown and instructions have not been loaded, you must call getConfluenceSpace once before authoring through execute with name=getConfluenceSpace, top-level cloudId, and inputs={spaceIdOrKey}.
  3. Apply any returned spaceInstructions. If a successful response omits them, no instructions are configured; author with defaults and do not block.
After a successful getConfluenceSpace call, do not make a separate getConfluenceSpaceInstructions call.

Input Parameters

object
Before composing this body, follow the space-instruction decision rule in the tool description. Reuse known instruction state and do not repeat the space lookup per write. Body update object with format and value. Doc types accept format html or markdown. Prefer HTML. Use markdown only when you are confident the content needs only basic text formatting and has no rich Confluence elements to preserve or create, such as panels, layouts, media, whiteboard embeds, or Remixes. If unsure, use HTML. Re-read existing rich content as HTML before editing and preserve its content and embeds. Whiteboards accept format svg and should include context.content with the current SVG when applying a patch. Databases accept format csv and should include context.content with the current CSV when applying an edit envelope. Put the raw patch/envelope directly in value; do not wrap it in an extra JSON object or {“content”: ”…”} wrapper. For whiteboards, value is a patch, not a full SVG replacement. For databases, value is an edit envelope, not a create payload. Mutually exclusive with edits.
boolean
If true, update the draft version instead of current. Only supported for page and blogpost doc edits.
array
Granular edit operations. Array of tool-call objects, each with name (replaceNode, insertNodeAfter, insertNodeBefore, deleteNode, removeNodes, moveNode, appendNodeToEnd, setAttrs), localId, value, and arguments. Mutually exclusive with body.
string
New title for the content. 1-255 characters. Omit to keep existing title.
boolean
If true, validate and preview the result without persisting. For edits, returns the resulting HTML. For body replacement, echoes the input.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Atlassian account ID of the new owner to transfer page ownership to. Optional. This is an account ID (e.g. 5b10ac8d82e05b22cc7d4ef5), never an email/username or a content ID. The new owner must already have edit permission.
string
Numeric Confluence content ID. One of contentId or contentUrl is required.
boolean
Whether to mark the new content version as a minor edit.
string
Full URL of the Confluence content. One of contentId or contentUrl is required. Clear Confluence URLs for pages/live docs (/pages/{id}), blogs (/blog/{id}), whiteboards (/whiteboard/{id}), databases (/database/{id}), and folders (/folder/{id}) are normalized to their numeric content ID before the update is sent, so URLs copied from the product should work directly.
string ("narrow" | "wide" | "max")
Optional page width for doc types only: page, live_doc, and blogpost. Accepted values are narrow, wide, and max. The default width is narrow. Omit to keep the existing content width unchanged. A width-only update is valid and requires snapshotToken, but does not require title, body, or edits. Non-doc content types do not support this field.
string
Opaque token from the most recent getConfluenceContent or updateConfluenceContent response for this content. Each successful update returns the current snapshot.token; pass it to the next update, because changes to the content make earlier tokens stale. On snapshot_stale, re-read the content with getConfluenceContent and reapply the change to the latest body before retrying; do not resend the same payload with currentSnapshot.token. Required for doc-type updates that mutate page/blog/live_doc content or contentWidth. Not used for whiteboard svg or database csv object updates.
string
Optional version comment/message for the content update.
Slug: ATLASSIAN_MCP_UPDATE_FOCUS_AREAUpdate one or more fields on an existing Focus area. Provide at least one of name, owner, startDate, or description — identifier-only calls fail upstream. Omitted fields are unchanged. Use createFocusAreaStatusUpdate for status, health, target date, or status summary changes. Multiple fields become separate mutations — a later failure can leave earlier fields already applied.

Input Parameters

string
Optional new name for the focus area.
string
Optional Atlassian account ID (AAID) of the new focus area owner.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
object
Optional new projected start date. Object shape: { “date”: “YYYY-MM-DDTHH:mm”, “confidence”: “DAY” | “MONTH” | “QUARTER” }. Both fields required when startDate is set. Example date: 2026-08-10T00:00 — bare calendar dates like 2026-08-10 are not accepted; append T00:00 when only the day is known. Requires focusAreaIdentifier to be a Mercury focus area ARI; UUID or URL identifiers fail this field — call getFocusArea and pass the returned ari.
string
Optional new about/description content in plain text or Markdown. An empty string clears the existing content. Value will overwrite existing content. Maximum 25,000 characters.
string
required
The focus area to update. Accepts a focus area UUID, a Mercury focus area ARI, or a Focus focus area page URL. Prefer values from a prior lookup over fabricating them. When reusing an identifier from an earlier response, pass its uuid field — not its id field.
Slug: ATLASSIAN_MCP_UPDATE_JSM_OPS_ALERTUpdate one Jira Service Management Operations alert by acknowledging, unacknowledging, closing, or escalating it. Escalation requires an escalation responder ID assigned to that alert. Optionally poll the asynchronous request status once.

Input Parameters

string ("acknowledge" | "unacknowledge" | "close" | "escalate")
required
State-changing action to perform.
string
required
Alert ID to update.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
boolean
When true, poll asynchronous request status once after mutation. Defaults to false.
string
Required only when action is escalate. Must identify an escalation responder assigned to this alert.
Slug: ATLASSIAN_MCP_UPDATE_LOOM_VIDEO_PERMISSIONSChange who can access a Loom video by setting its visibility to OWNER (only you), WORKSPACE (anyone in your workspace), or PUBLIC (anyone with the link). The change is immediate and permanent. To notify specific people about a video instead of changing its visibility, use shareLoomVideo. Identify the video by ARI or share URL. Returns id, name, visibility, url, and updatedAt. Omit responseFields to keep these defaults; videoUrl and videoAri are inputs, not response field names.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
ARI of the Loom video, formatted as ari:cloud:loom:{siteId}:video/activation/{activationId}/{videoId}. Provide this or videoUrl.
string
Loom share URL for the video, for example https://www.loom.com/share/&#123;videoId&#125;. Used when videoAri is not supplied; a supporting action resolves the URL to an ARI.
string ("OWNER" | "WORKSPACE" | "PUBLIC")
required
Requested visibility for the video. One of OWNER (only the owner), WORKSPACE (anyone in the workspace), or PUBLIC (anyone with the link).
Slug: ATLASSIAN_MCP_UPDATE_LOOM_VIDEO_TITLERename a Loom video. The change is immediate and visible to all viewers. Identify the video by ARI or share URL. To change who can access the video instead of its title, use updateLoomVideoPermissions.

Input Parameters

string
required
New title for the video. Must be non-empty.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
ARI of the Loom video, formatted as ari:cloud:loom:{siteId}:video/activation/{activationId}/{videoId}. Provide this or videoUrl.
string
Loom share URL for the video, for example https://www.loom.com/share/&#123;videoId&#125;. Used when videoAri is not supplied; a supporting action resolves the URL to an ARI.
Slug: ATLASSIAN_MCP_UPDATE_TALENT_POSITION_FOCUS_AREA_MAPPINGSAllocate Talent positions to focus areas, or clear the focus area a position is allocated to. Each mapping sets the focus area of ONE position and REPLACES the focus area that position is allocated to now — a position is allocated to one focus area at a time, so this is not additive and it cannot add a second focus area to a position. Omit focusAreaId in a mapping to clear the allocation and leave that position unallocated. Every mapping is applied as a single all-or-nothing change, so one rejected ARI fails the whole call — keep batches small. Do not guess either ARI: take a position ARI from a searchTalentPositions result’s id or a getTalentPositionsByEntity result’s entityId, and take a focus area ARI from getTalentFields for the focus area field, or from searchFocusAreas. To see which positions a focus area is staffed by before or after the change, call getTalentPositionsByEntity with entity=focusArea.

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
array
required
The allocations to apply, one object per position. Array of objects shaped { “positionId”: “ari:cloud:radar:<cloudId>:position/<workspaceId>/<positionId>”, “focusAreaId”: “<focus area ARI>” }, where positionId is required and focusAreaId is optional. A mapping that omits focusAreaId clears the focus area of that position. Name each position once — two mappings for the same position leave the outcome undefined.
Slug: ATLASSIAN_MCP_UPDATE_TEAMUpdate one Atlassian team through exactly one operation. Use update_details with displayName, description, or membershipSettings; add_members with accountIds and/or add-only emails; or remove_members with accountIds. Metadata and membership changes cannot be mixed. Removing members can remove access.

Input Parameters

array
Email addresses for add_members only. Combined account IDs and emails are limited to 50.
string
required
Team UUID or ari:cloud:identity::team/{teamId}. Find a team by name with searchTeams.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string ("update_details" | "add_members" | "remove_members")
required
Selects exactly one downstream write and its mutually exclusive input shape.
array
Up to 50 account IDs for add_members or remove_members.
string
New description for update_details.
string
New name for update_details.
string ("MEMBER_INVITE" | "OPEN")
New membership policy for update_details.
Slug: ATLASSIAN_MCP_UPLOAD_ATTACHMENT_TO_JIRA_ISSUEAttach a single local file to a Jira issue. Two phases: (1) call with filePath only to get a local uploadCommand; run it from your shell to upload the bytes and obtain a fileId; (2) call again with that fileId to attach the file to the issue. To instead embed the uploaded file inline in a body, stop after phase 1 and pass the fileId (with its collection) to editJiraIssue/addOrEditJiraIssueComment via inlineFileId (appends at the end) or an HTML body media node (for positional placement) — do not also run phase 2 for the same file.

Input Parameters

string
Media file ID returned by running the phase-1 uploadCommand. Provide for phase 2 to attach the uploaded file to the issue.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Local path of the file to attach (absolute, or relative to where uploadCommand is run). Provide for phase 1 to get an uploadCommand. Ignored when fileId is supplied.
string
required
Issue key (e.g. PROJ-123) or a Jira issue URL
Slug: ATLASSIAN_MCP_WATCH_CONFLUENCE_CONTENTStart watching a Confluence content item for the current user

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Numeric Confluence content ID.
Slug: ATLASSIAN_MCP_WATCH_CONFLUENCE_LABELStart watching a Confluence label for the current user

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Confluence label name.
Slug: ATLASSIAN_MCP_WATCH_CONFLUENCE_SPACEStart watching a Confluence space for the current user

Input Parameters

string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
Numeric ID of the Confluence space. Resolved to the space key before the request. Provide either spaceId or spaceKey.
string
Confluence space key or alias. Provide either spaceKey or spaceId.
Slug: ATLASSIAN_MCP_WATCH_JIRA_ISSUEAdd or remove the calling user as a watcher on a Jira issue. Always acts on you — it cannot add or remove another person, and it does not list who is watching. Watching only subscribes you to notifications about the issue; it does not assign it to you. To do that, set the issue’s assignee field with editJiraIssue.

Input Parameters

string ("watch" | "unwatch")
Whether to watch or unwatch the issue as the calling user. Defaults to “watch”.
string
required
Site UUID or Jira/Confluence URL for this operation’s Atlassian site. cloudId is never silently auto-resolved or reused for you — call getAccessibleAtlassianResources ONCE per session, cache the returned cloudId, and pass it explicitly on this and every subsequent call, since most operations need it. execute and its read/write/destructive variants strictly require it for cloudId-scoped operations and fail without it. Not needed for cloudId-less operations (e.g. Bitbucket), which ignore this field.
string
required
Issue key (e.g. PROJ-123) or a Jira issue URL