> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Sentry MCP

> Investigate Sentry issues, events, projects, and application health.

![Sentry MCP logo](https://mintcdn.com/composio-preview/B09iGux45A5cYDuO/images/toolkits/sentry_mcp.svg?fit=max\&auto=format\&n=B09iGux45A5cYDuO\&q=85\&s=285ee11cb683833a43248efe2a723881)

* **Category:** server monitoring
* **Auth:** DCR\_OAUTH
* **Composio-managed OAuth available?** No
* **Tools:** 9
* **Triggers:** 0
* **Slug:** `SENTRY_MCP`
* **Version:** 20261018\_00

## Tools

> [accordion] Analyze issue with seer
>
> **Slug:** `SENTRY_MCP_ANALYZE_ISSUE_WITH_SEER`
>
> Use Seer to analyze production errors and get detailed root cause analysis with specific code fixes.
>
> Use this tool when:
>
> * The user explicitly asks for root cause analysis, Seer analysis, or help fixing/debugging an issue
> * You are unable to accurately determine the root cause from the issue details alone
>
> Do NOT call this tool as an automatic follow-up to get\_sentry\_resource.
>
> What this tool provides:
>
> * Root cause analysis with code-level explanations
> * Specific file locations and line numbers where errors occur
> * Concrete code fixes you can apply
> * Step-by-step implementation guidance
>
> This tool automatically:
>
> 1. Checks if analysis already exists (instant results)
> 2. Starts new AI analysis if needed (\~2-5 minutes)
> 3. Returns complete fix recommendations
>
> \<examples>
>
> ### User: "Run Seer on this issue"
>
> ```text theme={null}
> analyze_issue_with_seer(issueUrl='https://my-org.sentry.io/issues/PROJECT-1Z43')
> ```
>
> ### User: "Analyze this issue and suggest a fix"
>
> ```text theme={null}
> analyze_issue_with_seer(organizationSlug='my-organization', issueId='ERROR-456')
> ```
>
> \</examples>
>
> \<hints>
>
> * Only use when the user explicitly requests analysis or you cannot determine the root cause from issue details alone
> * Seer Autofix does not support metric alert issues (issueCategory: metric); use get\_issue\_details and search\_events instead
> * If the user provides an issueUrl, extract it and use that parameter alone
> * The analysis includes actual code snippets and fixes, not just error descriptions
> * Results are cached - subsequent calls return instantly \</hints>
>
> #### Input Parameters
>
> **issueId** `string`
>
> The Issue ID. e.g. `PROJECT-1Z43`
>
> **issueUrl** `string`
>
> The URL of the issue. e.g. [https://my-organization.sentry.io/issues/PROJECT-1Z43](https://my-organization.sentry.io/issues/PROJECT-1Z43)
>
> **regionUrl** `string`
>
> **instruction** `string`
>
> Optional custom instruction for the AI analysis
>
> **organizationSlug** `string`
>
> The organization's slug. You can find a existing list of organizations you have access to using the `find_organizations()` tool.

> [accordion] Execute sentry tool
>
> **Slug:** `SENTRY_MCP_EXECUTE_SENTRY_TOOL`
>
> Execute an available Sentry MCP tool discovered through search\_sentry\_tools.
>
> Use this tool when you need to:
>
> * Call a Sentry operation returned by search\_sentry\_tools
> * Execute a tool by name using arguments that match its returned schema
>
> \<examples> execute\_sentry\_tool(name='find\_projects', arguments=\{ organizationSlug: 'my-org' }) execute\_sentry\_tool(name='whoami', arguments=\{}) \</examples>
>
> \<hints>
>
> * Use search\_sentry\_tools first if you are not sure which name or arguments to pass.
> * Arguments are validated against the target tool's schema before execution.
> * Active organization, project, and region constraints are injected automatically. \</hints>
>
> #### Input Parameters
>
> **name** `string` *required*
>
> The name of the available tool to execute.
>
> **arguments** `object`
>
> Arguments for the target tool, matching the schema returned by search\_sentry\_tools.

> [accordion] Find organizations
>
> **Slug:** `SENTRY_MCP_FIND_ORGANIZATIONS`
>
> Find organizations that the user has access to in Sentry.
>
> Use this tool when you need to:
>
> * View organizations in Sentry
> * Find an organization's slug to aid other tool requests
> * Search for specific organizations by name or slug
>
> Returns up to 25 results. If you hit this limit, use the query parameter to narrow down results.
>
> #### Input Parameters
>
> **query** `string`
>
> #### Output
>
> **hasMore** `boolean` *required*
>
> **organizations** `array` *required*

> [accordion] Find projects
>
> **Slug:** `SENTRY_MCP_FIND_PROJECTS`
>
> Find projects in Sentry.
>
> Use this tool when you need to:
>
> * View projects in a Sentry organization
> * Find a project's slug to aid other tool requests
> * Search for specific projects by name or slug
>
> Returns up to 25 results. When hasMore is true, use the query parameter to narrow down results.
>
> #### Input Parameters
>
> **query** `string`
>
> **regionUrl** `string`
>
> **organizationSlug** `string` *required*
>
> The organization's slug. You can find a existing list of organizations you have access to using the `find_organizations()` tool.
>
> #### Output
>
> **hasMore** `boolean` *required*
>
> **projects** `array` *required*

> [accordion] Get sentry resource
>
> **Slug:** `SENTRY_MCP_GET_SENTRY_RESOURCE`
>
> Fetch a Sentry resource by URL, or by resourceType plus resourceId. Pass a Sentry URL directly when possible; the resource type is auto-detected.
>
> Supports issues, events, traces, spans, agent conversations, replays, monitors, preprod snapshots, and snapshot images. Trace lookups return a condensed overview by default.
>
> Agent Conversations: A conversation is a set of spans sharing the same gen\_ai.conversation.id. Use resourceType='ai\_conversation' with a conversation ID, or pass a Sentry conversation URL, to fetch the transcript/details. To discover or list conversations, use search\_agent\_conversations. Conversations are NOT issues — do not use search\_issues for conversation queries.
>
> For preprod snapshot URLs (matching 'sentry.io/preprod/snapshots/'):
>
> * Without ?selectedSnapshot=: returns the snapshot diff summary (changed, added, removed images)
> * With ?selectedSnapshot=\<image\_file\_name>: returns the image preview and metadata. Use the Sentry tool `get_snapshot_image` for full-resolution image bytes.
>
> Resource IDs:
>
> * monitor: \<monitorSlug>
> * snapshot: \<snapshotId>
>
> \<examples> get\_sentry\_resource(url='[https://sentry.io/issues/PROJECT-123/](https://sentry.io/issues/PROJECT-123/)') get\_sentry\_resource(resourceType='issue', organizationSlug='my-org', resourceId='PROJECT-123') get\_sentry\_resource(resourceType='ai\_conversation', organizationSlug='my-org', resourceId='conversation-123') get\_sentry\_resource(url='[https://sentry.sentry.io/preprod/snapshots/123/](https://sentry.sentry.io/preprod/snapshots/123/)') get\_sentry\_resource(url='[https://sentry.sentry.io/preprod/snapshots/123/?selectedSnapshot=login\_screen.png](https://sentry.sentry.io/preprod/snapshots/123/?selectedSnapshot=login_screen.png)') \</examples>
>
> #### Input Parameters
>
> **url** `string`
>
> Sentry URL. The resource type is auto-detected from the URL pattern.
>
> **resourceId** `string`
>
> Resource identifier: issue shortId (e.g., 'PROJECT-123'), event ID, trace ID, agent conversation ID, replay ID, monitor slug when inspect monitor tools are available, or snapshot artifact ID. Required when not using a URL.
>
> **resourceType** `string ("issue" | "event" | "trace" | "ai_conversation" | "replay" | "monitor" | "snapshot")`
>
> Resource type. With a URL, can override a span-focused trace URL with `trace`. Use `monitor` with a monitor slug only when inspect monitor tools are available or `snapshot` with a snapshot artifact ID.
>
> **organizationSlug** `string`
>
> The organization's slug. You can find a existing list of organizations you have access to using the `find_organizations()` tool.

> [accordion] Search events
>
> **Slug:** `SENTRY_MCP_SEARCH_EVENTS`
>
> Search Sentry events and replays. Use for event counts/statistics.
>
> `query` can be natural language or Sentry search syntax. With an agent configured, it fixes dataset, query, fields, and sort before running.
>
> Supports TWO query types:
>
> 1. AGGREGATIONS (counts, sums, averages): 'how many errors', 'total tokens'
> 2. Individual events with timestamps: 'error logs from last hour'
>
> Datasets:
>
> * errors: Exception/crash events with stack traces, usually grouped into issues
> * logs: Application log entries, including error-severity log messages
> * spans: Raw trace/span events for performance, AI/LLM calls, requests, and operations
> * metrics: Metric rows and aggregates: counters, gauges, distributions, values
> * profiles: Transaction/continuous profile results, profile IDs, profiled transactions
> * replays: Session replay results: rage clicks, dead clicks, visited pages, replay users If the user says logs, log messages, error logs, or warning logs, choose logs instead of errors.
>
> Replay searches return replay lists only; replay count()/avg()/sum() are not supported.
>
> NOT for grouped issue lists (use search\_issues) or app screenshots/images (use get\_latest\_base\_snapshot).
>
> \<examples> search\_events(organizationSlug='my-org', query='how many errors today') search\_events(organizationSlug='my-org', dataset='errors', query='level:error') search\_events(organizationSlug='my-org', dataset='errors', fields=\['issue', 'count()'], sort='-count()') search\_events(organizationSlug='my-org', dataset='spans', query='span.op:db', sort='-span.duration') search\_events(organizationSlug='my-org', dataset='replays', query='count\_errors:>0', sort='-count\_errors') \</examples>
>
> \<hints>
>
> * If the user passes a parameter in the form of name/otherName, it's likely in the format of \<organizationSlug>/\<projectSlug>.
> * Parse org/project notation directly without calling find\_organizations or find\_projects.
> * Use fields with aggregate functions like count(), avg(), sum() for statistics
> * Sort by -count() for most common, -timestamp for newest \</hints>
>
> #### Input Parameters
>
> **sort** `string`
>
> Sort field (prefix with - for descending). If omitted, event datasets default to -timestamp and replays default to -started\_at. Use -count() for event aggregations. For dataset='replays', use replay sorts like -started\_at or -count\_errors.
>
> **limit** `number`
>
> Maximum number of results to return (1-100)
>
> **query** `string`
>
> Natural language or Sentry event search query syntax.
>
> **fields** `string`
>
> Fields to return for event datasets. If not specified, uses sensible defaults. Include aggregate functions like count(), avg() for statistics. Leave null for dataset='replays'.
>
> **period** `string`
>
> Relative time window, such as `24h`, `7d`, `14d`, `30d`, or `90d`. Controls which records fall within the search window.
>
> **dataset** `string ("spans" | "errors" | "logs" | "metrics" | "profiles" | "replays")`
>
> Initial dataset hint: errors, logs, spans, metrics, profiles, or replays. The agent may correct this when configured.
>
> **regionUrl** `string`
>
> **environment** `string`
>
> Optional environment filter for dataset='replays'. Use a string for one environment or an array for multiple. Omit when unused. For other datasets, filter environment in the query string instead.
>
> **projectSlug** `string`
>
> **organizationSlug** `string` *required*
>
> The organization's slug. You can find a existing list of organizations you have access to using the `find_organizations()` tool.
>
> **includeExplanation** `boolean`
>
> Include explanation of how the query was translated or repaired

> [accordion] Search issues
>
> **Slug:** `SENTRY_MCP_SEARCH_ISSUES`
>
> Search for grouped issues/problems in Sentry - returns a LIST of issues, NOT counts or aggregations.
>
> Provide `query` as natural language or Sentry issue search syntax. When an embedded agent is configured, it fixes query and sort before running while preserving explicit Sentry search syntax.
>
> Returns grouped issues with metadata like title, status, and user count.
>
> Common Query Syntax:
>
> * is:unresolved / is:resolved / is:ignored / is:for\_review / is:new / is:regressed / is:escalating
> * level:error / level:warning
> * firstSeen:-24h / lastSeen:-7d
> * assigned:me / assigned\_or\_suggested:me
> * release:latest
> * issue.category:feedback
> * issue.priority:high
> * environment:production
> * userCount:>100
>
> DO NOT USE FOR COUNTS/AGGREGATIONS → use search\_events DO NOT USE FOR individual events with timestamps → use search\_events DO NOT USE FOR details about a specific issue → use get\_sentry\_resource
>
> \<examples> search\_issues(organizationSlug='my-org', query='critical bugs from last week') search\_issues(organizationSlug='my-org', query='is:unresolved is:unassigned', sort='freq') search\_issues(organizationSlug='my-org', query='level:error firstSeen:-24h', projectSlugOrId='my-project') \</examples>
>
> \<hints>
>
> * If the user passes a parameter in the form of name/otherName, it's likely in the format of \<organizationSlug>/\<projectSlugOrId>.
> * Parse org/project notation directly without calling find\_organizations or find\_projects.
> * The projectSlugOrId parameter accepts both project slugs (e.g., 'my-project') and numeric IDs (e.g., '123456'). \</hints>
>
> #### Input Parameters
>
> **sort** `string ("date" | "freq" | "new" | "user" | "recommended")`
>
> Sort order: date (last seen), freq (frequency), new (first seen), user (user count), recommended (Sentry's prioritized ranking)
>
> **limit** `number`
>
> Maximum number of issues to return (1-100)
>
> **query** `string`
>
> Natural language or Sentry issue search query syntax.
>
> **period** `string ("24h" | "7d" | "14d" | "30d" | "90d")`
>
> Time window for issue search results. Controls which issues are returned based on when they had activity. Default 30d is a balance between coverage and query performance; use 24h for very recent issues or 90d for broader historical searches.
>
> **regionUrl** `string`
>
> **projectSlugOrId** `string`
>
> The project's slug or numeric ID (optional)
>
> **organizationSlug** `string` *required*
>
> The organization's slug. You can find a existing list of organizations you have access to using the `find_organizations()` tool.
>
> **includeExplanation** `boolean`
>
> Include explanation of how the query was translated or repaired

> [accordion] Search sentry tools
>
> **Slug:** `SENTRY_MCP_SEARCH_SENTRY_TOOLS`
>
> Search the available Sentry MCP tool catalog by name and description.
>
> Many Sentry operations are intentionally not exposed as top-level tools. Use this for any Sentry-related task when you do not see an obvious direct tool, including long-tail inspection, project management, documentation lookup, preprod snapshots, attachments, DSNs, releases, teams, and issue-specific pivots.
>
> Use this tool when you need to:
>
> * Find the right Sentry operation for a task
> * Discover catalog tools and their schemas for a task
> * Inspect the executable JSON input schema for an available tool
>
> \<examples> search\_sentry\_tools(query='list projects') search\_sentry\_tools(query='issue details') search\_sentry\_tools(query='find dsn', limit=5) search\_sentry\_tools(query='snapshot image') \</examples>
>
> \<hints>
>
> * Results only include tools available in the current session.
> * If a Sentry operation is not listed as a direct tool, search here before deciding it is unavailable.
> * Returned schemas already account for active organization, project, and region constraints.
> * Use the returned name and schema when executing a catalog result.
> * This tool returns structured JSON. Do not parse markdown from its text content. \</hints>
>
> #### Input Parameters
>
> **limit** `string`
>
> Maximum number of matching tools to return, up to 20.
>
> **query** `string` *required*
>
> Natural language keywords describing the Sentry operation, resource, or workflow to find.
>
> #### Output
>
> **query** `string` *required*
>
> **results** `array` *required*

> [accordion] Update issue
>
> **Slug:** `SENTRY_MCP_UPDATE_ISSUE`
>
> Update a Sentry issue's status or assignment.
>
> Use this to resolve, reopen, assign, or ignore an issue.
>
> \<examples>
>
> ```text theme={null}
> update_issue(organizationSlug='my-org', issueId='PROJECT-123', status='resolved')
> update_issue(organizationSlug='my-org', issueId='PROJECT-123', assignedTo='user:123456')
> update_issue(organizationSlug='my-org', issueId='PROJECT-123', status='ignored')
> update_issue(organizationSlug='my-org', issueId='PROJECT-123', status='ignored', ignoreMode='forever')
> update_issue(organizationSlug='my-org', issueId='PROJECT-123', status='ignored', ignoreMode='untilOccurrenceCount', ignoreCount=100, ignoreWindowMinutes=60)
> update_issue(organizationSlug='my-org', issueId='PROJECT-123', status='ignored', reason='Ignoring because this is expected noise from the staging deploy')
> ```
>
> \</examples>
>
> \<hints>
>
> * Provide `issueUrl` or `organizationSlug` + `issueId`.
> * At least one of `status` or `assignedTo` is required.
> * `assignedTo` format: `user:ID` or `team:ID_OR_SLUG`.
> * Use `execute_sentry_tool(name='whoami', arguments={})` to find your user ID for self-assignment.
> * Status values: `resolved`, `resolvedInNextRelease`, `unresolved`, `ignored`.
> * `status='ignored'` defaults to `ignoreMode='untilEscalating'`.
> * Ignore modes: `untilEscalating`, `forever`, `forDuration`, `untilOccurrenceCount`, `untilUserCount`.
> * Matching ignore inputs are `ignoreDurationMinutes`, `ignoreCount` + optional `ignoreWindowMinutes`, or `ignoreUserCount` + optional `ignoreUserWindowMinutes`.
> * To switch an already ignored issue between `untilEscalating`, `forever`, and condition-based ignore modes, first set `status='unresolved'`, then ignore it again with the new rule.
> * `reason` is optional. When provided, it will be posted as a comment on the issue's activity feed explaining why the action was taken. \</hints>
>
> #### Input Parameters
>
> **reason** `string`
>
> Optional reason for taking this action. When provided, it will be posted as a comment on the issue's activity feed.
>
> **status** `string ("resolved" | "resolvedInNextRelease" | "unresolved" | "ignored")`
>
> The new status for the issue. Valid values are 'resolved', 'resolvedInNextRelease', 'unresolved', and 'ignored'.
>
> **issueId** `string`
>
> The Issue ID. e.g. `PROJECT-1Z43`
>
> **issueUrl** `string`
>
> The URL of the issue. e.g. [https://my-organization.sentry.io/issues/PROJECT-1Z43](https://my-organization.sentry.io/issues/PROJECT-1Z43)
>
> **regionUrl** `string`
>
> **assignedTo** `string`
>
> The assignee in format 'user:ID' or 'team:ID\_OR\_SLUG' where ID is numeric. Example: 'user:123456', 'team:789', or 'team:my-team-slug'. Use `execute_sentry_tool(name='whoami', arguments={})` to find your user ID.
>
> **ignoreMode** `string ("untilEscalating" | "forever" | "forDuration" | "untilOccurrenceCount" | "untilUserCount")`
>
> How ignored issues should behave. Use 'untilEscalating' to match the Sentry UI default, 'forever' for a permanent ignore, 'forDuration' with ignoreDurationMinutes, 'untilOccurrenceCount' with ignoreCount and optional ignoreWindowMinutes, or 'untilUserCount' with ignoreUserCount and optional ignoreUserWindowMinutes.
>
> **ignoreCount** `integer`
>
> How many times the issue must occur before it stops being ignored when ignoreMode is 'untilOccurrenceCount'.
>
> **ignoreUserCount** `integer`
>
> How many users must be affected before the issue stops being ignored when ignoreMode is 'untilUserCount'.
>
> **organizationSlug** `string`
>
> The organization's slug. You can find a existing list of organizations you have access to using the `find_organizations()` tool.
>
> **ignoreWindowMinutes** `integer`
>
> Optional time window in minutes for ignoreCount. If omitted, Sentry counts all future occurrences.
>
> **ignoreDurationMinutes** `integer`
>
> How many minutes to ignore the issue when ignoreMode is 'forDuration'.
>
> **ignoreUserWindowMinutes** `integer`
>
> Optional time window in minutes for ignoreUserCount. If omitted, Sentry counts all future affected users.
