Skip to main content
Amplitude MCP logo
  • Category: model context protocol
  • Auth: DCR_OAUTH
  • Composio-managed OAuth available? No
  • Tools: 48
  • Triggers: 0
  • Slug: AMPLITUDE_MCP
  • Version: 20261030_00

Tools

Slug: AMPLITUDE_MCP_CREATE_GROUP_TYPESCreate one or more group types in a project, OR add already-ingested group types with status “unexpected” to the tracking plan.A group type is a category of group that users can belong to (for example “Company”, “Account”, “Team”, “Workspace”, “Organization”). The Amplitude Accounts add-on lets you analyse product usage at the group level rather than per individual user. NOTE: group TYPES are the categories themselves — use create_properties with propertyType “group” to add attributes (e.g. company name, plan tier) to an existing group type.When a user says “create a group type” without further qualification, or “add to plan” for an unexpected group type, use this tool. Specify whether each item is unexpected with isUnexpected. If isUnexpected is true, the group type must already exist in the project as observed-but-unexpected and will be added to the tracking plan. If false (default), a brand-new entry is created.INSTRUCTIONS:
  • Use get_context to get available project IDs first.
  • Use get_group_types to check which group types already exist before creating new ones.
  • If the user has not specified a project, prompt the user to decide. Don’t decide for them.
EXAMPLES:
  • Minimal: {“projectId”: “123456”, “groupTypes”: [{“name”: “Company”}]}
  • With description: {“projectId”: “123456”, “groupTypes”: [{“name”: “Team”, “description”: “Engineering teams within a company”}]}
  • Mixed batch (one fresh, one add-to-plan, on a feature branch): {“projectId”: “123456”, “branchName”: “marketing-edits”, “groupTypes”: [{“name”: “Account”}, {“name”: “Workspace”, “isUnexpected”: true}]}
Response
Each input item is reported individually in groupTypes[] with a result of "created", "addedToPlan", or "failed" (with a reason). Partial successes are preserved: a failure on one item never discards the results of others in the same batch.PERMISSIONS:
  • This tool requires the “Update Tracking Plan” permission and may fail with a 403. Don’t pre-warn the user; if it fails, surface the error and note that an admin may need to grant access.
Workspace warnings
Be sure you have information on the workspace settings and environments from get_workspace_context before using this tool. If the workspace has more than one environment, warn the user that the change will apply across multiple environments. If the main branch is protected (workspace setting approvalWF is “Required”), let the user know that changes cannot be made on the default branch and they will have to first create a new branch and make changes on that.NOTES:
  • A group type with the same name cannot already exist on the targeted branch — that item will be marked as failed.
  • Branch targeting: unless specified, the default branch is used. Pass either branchId or branchName, not both.
  • description is only allowed on brand-new group types (isUnexpected: false). Unexpected items added to the plan cannot include metadata at the same time — add them first, then use a follow-up tool call to set the description.
USER-INTERFACING LANGUAGE: When relaying results to the user, do not surface internal mechanics.
  • Refer to the default branch as “main”, not “default branch”.
  • Say “unexpected group types” not “isUnexpected group types”.
  • Say “added to the tracking plan” rather than using field names like “addedToPlan”.
  • Say “branch approval setting” not “approvalWF”.
  • Do not mention “mutations”, “versionId”, “stagingVersionId”, “propertyPath”, branch IDs, or GraphQL details to the user.

Input Parameters

string
Optional branch ID to target a non-default branch. If omitted, the project’s default branch is used. Mutually exclusive with branchName.
string
required
Project ID to create the group types in. If the user has not specified a project, prompt the user to decide. Dont decide for them.
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
string
Optional branch name to target a non-default branch (e.g. “my-edits-branch”). If omitted, the project’s default branch is used. Mutually exclusive with branchId.
array
required
Array of group types to create or add to plan

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_CREATE_PROPERTIESCreate one or more properties in a project’s tracking plan. Use propertyType to select which kind of properties to create.PROPERTY TYPES:INSTRUCTIONS:
  • If a user says “create a property” without specifying a type, ask them to clarify which type they mean: event, user, or group.
  • If a user says “create a property on an event,” assume they mean an event property — propertyType “event” is the default for that phrasing.
  • Derived properties, profile properties, lookup properties, computed properties, and persisted properties are NOT supported via MCP tools. If the user asks to create one of these, let them know that this property type is not currently supported through MCP tools.
  • If the user has not specified a project, prompt them to decide. Don’t decide for them.
PERMISSIONS:
  • This tool requires the “Update Tracking Plan” permission and may fail with a 403. Don’t pre-warn the user; if it fails, surface the error and note that an admin may need to grant access.
Workspace warnings
Be sure you have information on the workspace settings and environments from get_workspace_context before using this tool. If the workspace has more than one environment, warn the user that the change will apply across multiple environments. If the main branch is protected (workspace setting approvalWF is “Required”), let the user know that changes cannot be made on the default branch and they will have to first create a new branch and make changes on that.NOTES BY PROPERTY TYPE:
  • group: Group properties describe attributes of a group type (e.g., company name, plan tier). Accepts a group type name (e.g., “org id”, “Company”) — the tool resolves it to the correct ID internally. If no branch is specified, defaults to the main branch.
EXAMPLES:
  • Event property (global): { “propertyType”: “event”, “projectId”: “123”, “properties”: [{ “name”: “page_url”, “type”: “string” }] }
  • Event property (event-scoped): { “propertyType”: “event”, “projectId”: “123”, “properties”: [{ “name”: “button_name”, “eventType”: “Button Clicked”, “type”: “string” }] }
  • Event properties (mixed: one fresh, one add-to-plan, on a feature branch): { “propertyType”: “event”, “projectId”: “123”, “branchName”: “marketing-edits”, “properties”: [{ “name”: “page_url”, “type”: “string” }, { “name”: “button_name”, “eventType”: “Button Clicked”, “isUnexpected”: true }] }
  • User property: { “propertyType”: “user”, “projectId”: “123”, “properties”: [{ “name”: “plan_type”, “type”: “string” }] }
  • Group properties: { “propertyType”: “group”, “projectId”: “123”, “groupType”: “Company”, “properties”: [{ “name”: “plan_tier”, “type”: “string” }] }
USER-INTERFACING LANGUAGE: When relaying results to the user, do not surface internal mechanics.
  • Refer to the default branch as “main”, not “default branch”.
  • Say “event property”, “user property”, or “group property” not “propertyType”.
  • Say “unexpected” or “unplanned” not “isUnexpected” when describing properties not yet in the plan.
  • Say “array type” not “isArrayType”, “hidden” not “isHidden”, “enum values” not “enumValues”, and “classification” not “classifications”.
  • Say “branch approval setting” not “approvalWF”.
  • Do not mention “mutations”, “versionId”, “stagingVersionId”, branch IDs, or GraphQL details to the user.

Input Parameters

string
Optional branch ID to target a non-default branch. If omitted, the project’s default branch is used. Mutually exclusive with branchName.
string
Name of the group type the properties belong to (e.g., “org id”, “Company”). The tool resolves this to the correct ID. Omit to create global group properties (not scoped to any group type).
string
required
Project ID to create event properties in. If the user has not specified a project, prompt the user to decide. Dont decide for them.
string
Optional branch name to target a non-default branch (e.g. “my-edits-branch”). If omitted, the project’s default branch is used. Mutually exclusive with branchId.
array
required
Array of event properties to create
string ("event" | "user" | "group")
required
Discriminator: determines which set of parameters applies (event | user | group)

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_DELETE_EVENT_PROPERTIESDelete one or more event properties in a project.Each requested property is routed by whether eventType is provided:
  • eventType provided → per-event delete (scoped to that one event):
    • live on this event → marked as deleted on this event (restorable).
    • planned on this event → the property-event link is removed on this event only (does NOT affect other events).
    • unexpected on this event → added to the plan as deleted on this event.
  • eventType omitted → plan-wide delete (across all events):
    • live → marked as deleted (restorable).
    • planned → removed entirely (NOT restorable; you’d have to recreate). Affects all events that used the property.
    • unexpected → added to the plan as deleted.
A single call may mix both — each entry is routed independently. Amplitude-owned properties cannot be deleted.
Before deleting
Before an event-property delete, pass includeDeleted: true when looking up which events are using the property so deleted attachments are also included.
Warning
Marking an ingested event property as deleted stops ingestion until restored (immediately on main; after merge on other branches). A delete on a non-main tracking-plan branch does not drop live ingest until that branch is merged into main. Removing a planned property does not stop ingestion — it was never ingested. Always surface this to the user before they confirm.
Confirmation
This is a destructive taxonomy mutation. Mark as deleted and remove both use the same confirmation gate — never skip it. The first call returns a confirmation_required response showing the bucketed actions, project, and branch; relay that and its warning field to the user. Only call again with confirmed: true after the user explicitly acknowledges. Do not pass confirmed: true on the first call.
Branch targeting
Unless specified, the default branch is used. To apply changes to a non-default branch, pass either branchId or branchName. If the user references a branch by name (e.g. “my-edits-branch”), use branchName. Pass only one.
Permissions
This tool requires the “Update Tracking Plan” permission and may fail with a 403. Don’t pre-warn the user; if it fails, surface the error and note that an admin may need to grant access.

Input Parameters

string
Optional branch ID to target a non-default branch. If omitted, the project’s default branch is used. Mutually exclusive with branchName.
boolean
Set to true only after the user has explicitly acknowledged the actions and branch shown in the prior confirmation_required response. Required for mark as deleted and remove alike. Omit (or pass false) on the first call.
string
required
Project ID to delete event properties from. If the user has not specified a project, prompt the user to decide. Dont decide for them.
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
string
Optional branch name to target a non-default branch (e.g. “my-edits-branch”). If omitted, the project’s default branch is used. Mutually exclusive with branchId.
array
required
Array of event properties to delete

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_DELETE_USER_PROPERTIESDelete one or more user properties in a project.Properties that are planned and ingested are marked as deleted (restorable). Properties that are planned but never ingested are removed. Properties ingested but not in the plan are added to the plan as deleted. When a name exists as both customer and Amplitude, only the customer property is targeted.
Warning
Marking ingested properties as deleted (toMarkAsDeleted) stops ingestion until restored (immediately on main; after merge on other branches). A delete on a non-main tracking-plan branch does not drop live ingest until that branch is merged into main. Removing planned properties (toRemove) does not stop ingestion — they were never ingested and cannot be restored. Always surface both buckets and this warning to the user before they confirm.This tool only deletes customer-defined user properties. Amplitude-owned user properties cannot be deleted and are always skipped — tell the user if any were requested.
Confirmation
This is a destructive taxonomy mutation. Mark as deleted and remove both use the same confirmation gate — never skip it. The first call returns a confirmation_required response listing the bucketed properties, project, and branch; relay that and its warning field to the user. Only call again with confirmed: true after they explicitly acknowledge. Do not pass confirmed: true on the first call.
Branch targeting
Unless specified, the default branch is used. To apply changes to a non-default branch, pass either branchId or branchName. If the user references a branch by name (e.g. “my-edits-branch”), use branchName. Pass only one.
Permissions
This tool requires the “Update Tracking Plan” permission and may fail with a 403. Don’t pre-warn the user; if it fails, surface the error and note that an admin may need to grant access.

Input Parameters

string
Optional branch ID to target a non-default branch. If omitted, the project’s default branch is used. Mutually exclusive with branchName.
boolean
Set to true only after the user has explicitly acknowledged the properties and branch shown in the prior confirmation_required response. Required for mark as deleted and remove alike. Omit (or pass false) on the first call.
string
required
Project ID to delete user properties from. If the user has not specified a project, prompt the user to decide. Dont decide for them.
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
string
Optional branch name to target a non-default branch (e.g. “my-edits-branch”). If omitted, the project’s default branch is used. Mutually exclusive with branchId.
array
required
Array of user property names to delete

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_GET_AGENT_RESULTSRetrieve results from AI agents that have analyzed your dashboards or session replays.This is NOT for searching dashboards, charts, or notebooks — use ‘search’ for that. This is specifically for retrieving the AI-generated insights and analyses that agents produced.This tool handles both searching for agent analyses and fetching full results in a single call.MODES:
  1. Search mode (no session_id): Search agent analyses with filters. Returns preview summaries.
  2. Direct fetch mode (session_id provided): Fetch full artifact data for a specific session.
  3. Auto-expand: If search returns exactly 1 session, full artifacts are included automatically.
SEARCH STRATEGY (important — follow this order):
  1. If you have a specific session_id, use direct fetch mode.
  2. For dashboard analyses, pass agent_params with dashboard_id (cheap exact-match).
  3. For session replay insights, use agent_params with category and/or impact (cheap exact-match).
  4. Use “query” ONLY for natural language / fuzzy search when exact filters aren’t sufficient.
WHEN TO USE:
  • “What are my dashboard agents?” → agent_type: dashboard_explorer
  • “Show my agent results” → agent_type: dashboard_explorer (or session_replay_explorer)
  • “What agents have I run?” → agent_type: dashboard_explorer
  • “What analyses exist for dashboard xyz?” → agent_type: dashboard_explorer, agent_params: { dashboard_id: “xyz” }
  • “Show me high-impact session replay insights” → agent_type: session_replay_explorer, agent_params: { impact: “High” }
  • “Friction hotspots in the checkout flow” → agent_type: session_replay_explorer, agent_params: { category: “Friction Hotspots” }, query: “checkout flow”
  • “What did the AI find about rage clicks?” → agent_type: session_replay_explorer, query: “rage clicks”
  • “Any dashboard insights about revenue?” → agent_type: dashboard_explorer, query: “revenue”
  • “Show me insights from last week” → agent_type: session_replay_explorer, created_after: “2026-03-16T00:00:00Z”
  • “What did I analyze recently?” → agent_type: dashboard_explorer
DO NOT USE FOR:
  • Finding or listing dashboards, charts, or notebooks → use ‘search’ instead
  • Running new analyses or queries → use ‘query_dataset’ or ‘query_charts’ instead
  • Creating dashboards → use ‘create_dashboard’ instead
RETURNS:
  • Search mode: List of analysis sessions with preview summaries, URLs, and pagination info
  • Direct fetch mode: Full artifact data for the session
  • Links to view each session in the Amplitude UI are included

Input Parameters

integer
Maximum number of results to return (default: 10).
string
Free-text semantic search query (uses vector embeddings). Best for natural language discovery: “rage clicks on save button”, “dashboard showing revenue drop”, “friction in onboarding flow”. This is EXPENSIVE (generates an embedding) — prefer exact filters when you have specific values.
integer
Pagination offset. Use with limit to page through results. Start at 0 (default).
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
string ("dashboard_explorer" | "session_replay_explorer")
required
Type of agent analysis to search for. “dashboard_explorer” finds AI-generated dashboard analysis summaries. “session_replay_explorer” finds AI-generated UX insights from session replay analysis.
string
Specific session ID to fetch full artifacts for. When provided, returns full artifact data and other filters are ignored. Get session IDs from a previous search.
object
Agent-type-specific filter parameters as a JSON object. For dashboard_explorer: { “dashboard_id”: “xyz” }. For session_replay_explorer: { “category”: “Friction Hotspots”, “impact”: “High” }. Valid categories: Journeys & Navigation, Forms & Input, Content, Conversion, Friction Hotspots, Retention. Valid impacts: Low, Medium, High.
string
ISO 8601 date string. Only return sessions with analysis artifacts created after this date. Filters by artifact time, not session creation time. Example: “2025-03-01T00:00:00Z” for analyses run since March 2025.
string
ISO 8601 date string. Only return sessions with analysis artifacts created before this date. Use with created_after for a date range.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_GET_AMPLITUDE_AGENT_ANALYTICS_INFOSingle read entry point for Amplitude Agent Analytics (AI/LLM session investigation).NOT FOR: Customer product feedback (use use_amplitude_ai_feedback) or browser Session Replay.Set view to choose the read route (each view has its own parameters in the tool schema):
  • schema — fields, rubrics, taxonomy, filter_options. Use only when an exact filter identifier is not already known; request only the needed filterOptionTypes.
  • sessions — filtered session lists and groupBy aggregations (replaces metrics/timeseries tools).
  • conversation — full transcript; sessionId is required.
  • spans — per-operation trace; sessionId or traceId is required (no org-wide scans).
  • tool_reliability — metrics enum is only tool_stats | tool_definitions.
REMOVED (use sessions filters instead):
  • search_agent_analytics_conversations (ILIKE scans)
  • query_agent_analytics_metrics quality/cost/topics/timeseries enums
EXAMPLES:
  • Agent names: { “view”: “schema”, “projectId”: “12345”, “include”: [“filter_options”], “filterOptionTypes”: [“agent_names”] }
  • Failed sessions: { “view”: “sessions”, “projectId”: “12345”, “hasTechnicalFailure”: true, “agentNames”: [“global-chat”] }
  • Transcript: { “view”: “conversation”, “projectId”: “12345”, “sessionId”: “abc-123” }
  • Tool reliability: { “view”: “tool_reliability”, “projectId”: “12345”, “metrics”: [“tool_stats”,“tool_definitions”], “agentNames”: [“global-chat”] }

Input Parameters

string ("schema" | "sessions" | "conversation" | "spans" | "tool_reliability")
required
Discriminator: determines which set of parameters applies (schema | sessions | conversation | spans | tool_reliability)
integer
Max sessions per page (1-50, default 50). Use cursor for additional pages.
string
Pagination cursor from previous response
string
Filter by session status (e.g., “open”, “closed”)
string
ISO 8601 end date (e.g., “2026-02-01”). Defaults to now.
array
Group by session-level field for aggregations. Options: agent_name, customer_org_id, user_id, project_id, parent_agent_name, source_system.
array
Sections to return. Enum: fields | rubrics | taxonomy | filter_options. Pass a JSON array, not a string.
array
Only tool_stats and/or tool_definitions (not quality, cost, or timeseries — use view=sessions for those).
string
DEPRECATED for enrichment sorts (quality_score, sentiment_score). Default ordering is session_start DESC.
string
Trace whose spans to fetch. Required unless sessionId is set.
array
Filter by user IDs (e.g., [“user@example.com”])
string
Filter by tool name
array
Filter to sessions whose user belongs to ANY of these Amplitude cohort IDs. Requires projectId.
string
Filter to sessions in a specific gold dataset (by dataset ID). Use get_agent_analytics_schema to discover dataset IDs and names.
string
Filter by model name
string
required
Amplitude project id to scope filter_options to. Required. Call get_amplitude_context with no arguments first to list the projects you can access, then pass an id from that list — do NOT guess project ids.
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
string
The session ID to get conversation turns for (required)
string
ISO 8601 start date (e.g., “2026-01-01”). Defaults to 7 days ago.
array
Filter by tool names used in sessions. Use get_agent_analytics_schema to discover available names.
array
Filter by agent names (e.g., [“global-chat”, “Chart Agent”])
number
Maximum total cost in USD
number
Minimum total cost in USD
array
Filter by specific session IDs
string
DEPRECATED — will error. Use evalFilters instead.
string
Filter to sessions in a gold dataset by name (case-insensitive exact match, else first substring match). Resolves to a dataset ID.
string
DEPRECATED — will error.
array
Primary filter: modular evaluator results. Example for GAE2 data mismatch: [{“evaluatorId”:“01KS3TGK1732EXA7EP0AAFVPN6”,“evaluatorType”:“categorical”,“values”:[“RESP_DATA_RESPONSE_MISMATCH”]}]
string
Restrict to sessions evaluated by any evaluator in this suite
string
Search filter: partial user_id match or exact session_id match. Prefix with - to exclude.
array
Filter by OOTB User Intent L1 labels from [Agent] Session Record (e.g. [“Information Request”, “Task Execution”]). NOT Topic Intelligence clusters — use clusterStableId for those.
string
Topic Intelligence clustering run id. Required when using clusterStableId or subStableClusterId.
string
Filter by customer org name (fuzzy match, e.g., “eBay” matches “eBay Inc”). Resolves name to org IDs.
integer
DEPRECATED — will error.
integer
DEPRECATED — will error.
string ("llm" | "tool" | "embedding")
Filter by span component type
integer
Maximum session duration in milliseconds
integer
Minimum session duration in milliseconds
array
DEPRECATED — will error. Use evalFilters instead.
array
Filter by customer org IDs (string IDs, e.g., [“12345”])
boolean
Filter sessions with task failures (compat shim → task_failure eval)
string ("concise" | "detailed")
‘concise’ returns session summaries. ‘detailed’ includes full enrichment data. Default: concise.
string
Filter to sessions in this Topic Intelligence L1 cluster. Requires clusterRunId from query_topic_clusters.
number
DEPRECATED — will error. Use evalFilters instead.
number
DEPRECATED — will error. Use evalFilters instead.
array
DEPRECATED — will error. Use evalFilters instead.
string
Filter by parent agent name (for sub-agent delegation sessions)
array
Filter option catalogs to fetch. Enum: agent_names | tool_names | evaluators | datasets. Request only the catalogs needed; omitted returns all.
boolean
Include per-turn category annotations (e.g., topic, intent)
number
DEPRECATED — will error. Use evalFilters instead.
number
DEPRECATED — will error. Use evalFilters instead.
boolean
Attach per-session human “comments” (notes) and “labels” (tags) to each returned session. Fetched for up to 100 returned sessions.
string
Filter to sessions in this Topic Intelligence L2 subtopic. Requires clusterRunId.
boolean
Filter sessions with negative feedback (compat shim → negative_feedback eval)
boolean
Filter sessions with/without technical failures (system-level crashes/exceptions)
string
Filter spans that used this tool-definitions hash
object
DEPRECATED — will error. Use evalFilters instead.
string ("none" | "summary" | "full")
Controls evaluator_results per session. ‘none’ skips them, ‘summary’ returns compact outcomes, and ‘full’ returns complete result JSON. Default: full for backward compatibility.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_GET_AMPLITUDE_CHARTSRead saved Amplitude charts by ID, or look up the chart-type schema. One tool with five output modes selected by include (default link).OUTPUT MODES:
  • link (default) → ‘get_chart_link’: validates each id exists, then returns the chart’s URL(s). Does not run the chart — cheap id lookup only.
  • typed → ‘lower_chart’: returns the chart as typed UI-shaped parameters (kind + events/where/group_by/…) — the same shape query_amplitude_data’s chart parameter accepts. Prefer this when creating a variant of an existing chart or preparing a modification: edit the typed object, then call query_amplitude_data with chart (+ chartId to fork/modify the saved chart).
  • definition → ‘get_charts’: returns the full raw Amplitude definition object(s). Use when typed cannot lower the chart (advanced features) or you need fields the typed model does not cover.
  • data → ‘query_charts’: runs the chart(s) and returns the result data. Use when you need the numbers.
  • guide → ‘get_chart_definition_params’: no ids needed. Pass chartType to get that type’s parameter schema, valid enum values, and a working example definition — use BEFORE calling query_amplitude_data if you are unsure of the shape, or to look up valid enum values (e.g. funnel modes, segmentation metrics). Omit chartType to list all supported chart types. NOTE: This schema describes chart STRUCTURE only (params, enums, example) — it does NOT validate event or property names against your project’s taxonomy. An unrecognized event/property key will NOT error; it silently returns a chart with empty data. Before building, confirm exact spelling via ‘search’, ‘get_properties’ (propertyType=“event”), or get_amplitude_charts include=‘definition’ on a similar existing chart — never guess a key name.
PREREQUISITES (required):
  • For link / typed / definition / data: you MUST have at least one concrete chartIds or chartEditIds entry. Do not call speculatively. Resolve ids FIRST via search (by name), get_from_url (from a chart link), or query_amplitude_data (for ad-hoc analysis, which returns a chart edit id).
  • For guide: no ids required; chartType is optional (omit to list all supported types).
INSTRUCTIONS:
  • Create a new chart: search (taxonomy) → build typed chart → query_amplitude_data.
  • Modify / fork a saved chart: search (find chart) → get_amplitude_charts include='typed' → edit the returned chart → query_amplitude_data with that chart and chartId set to the saved chart id.
  • Saved charts → chartIds. Chart edits (links ending in /chart/new/<edit_id> or /chart/<chart_id>/edit/<edit_id>) → chartEditIds.
  • typed and definition modes support chartIds only. For a chart edit’s data use data mode.
  • data mode accepts up to 3 ids/edits combined.
  • The data params (groupByLimit, excludeIncompleteDatapoints, timeSeriesLimit) only apply when include = 'data'. chartType only applies when include = 'guide'.
DO NOT USE FOR:
  • Ad-hoc analysis without a saved chart → use ‘query_amplitude_data’.
  • Finding charts by name → use ‘search’.

Input Parameters

string ("line" | "area" | "bar" | "pie" | "stackedbar")
data mode only: override the eventsSegmentation visualization type (line, area, bar, pie, stackedbar). Used by the chart widget vis switcher.
string ("light" | "dark")
data mode only: fetch only this theme of an eventsSegmentation Highcharts config. Used by the chart widget for active-theme-first rendering.
string ("link" | "typed" | "definition" | "data" | "guide")
What to return: ‘link’ (default, URL only — free), ‘typed’ (UI-shaped chart params for query_amplitude_data), ‘definition’ (raw chart config), ‘data’ (run the chart), or ‘guide’ (chart-type parameter schema/enums/example — no ids needed, use chartType).
array
Saved chart IDs to read.
string
guide mode only: the chart type to get parameter schema/enums/example for. Supported: eventsSegmentation, funnels, metricExplorer, retention, revenueLtv, sessions, stickiness. Omit to list all supported types instead.
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
array
Chart edit IDs to read (data mode only).
integer
data mode only: max group-by values to return (1-1000, default 10).
integer
data mode only: max group-by values that include per-interval rows (default 6; 0 = totals only).
array
data mode only: additional render-only information. Omit for compact analytics data; the chart app passes [“chartConfig”].
boolean
data mode only: exclude the current (incomplete) interval. Default false.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_GET_AMPLITUDE_CONTEXTUnified entry point for Amplitude context. Routes to one of two underlying tools based on whether a projectId is provided.ROUTES:
  • No projectId → ‘get_context’ route: returns the current user, organization (including org-level AI context), and the LIST of accessible projects as { appId, appName }. Use this to discover which projects exist and their ids.
  • projectId provided → ‘get_project_context’ route: returns that single project’s details — description, timezone, currency, session definition, source projects, and project-level AI context.
WHEN TO USE:
  • Session start, “what projects do I have access to?”, “show me my org details”, “what is my role?” → call with no arguments.
  • “what timezone / currency / session settings does project X use?”, “describe project X” → pass projectId.
CONTEXT DOCUMENTS (uploaded files):
  • org.aiContext / project aiContext are short text fields only. Customers also upload context files (CSV data dictionaries, PDFs, process docs) in Settings → AI Controls; those are indexed for search and never returned in full — only titles (opt-in) or search snippets.
  • listContextDocuments: true adds contextDocuments — document titles and ids only, no file contents. Use it when aiContext references an uploaded file by name (e.g. “always check <file> before answering”).
  • searchContextDocuments runs semantic search over the uploaded documents’ contents and adds contextDocumentSearch with matching text snippets. Use specific terms from the user’s question (event names, property names, column names).
  • Scope for both: without projectId, org-level documents only; with projectId, org-level plus that project’s documents.
EXAMPLES:
  • Session start: {}
  • Project settings: {“projectId”: 12345}
  • aiContext says “check the event dictionary file” → {“projectId”: 12345, “listContextDocuments”: true}
  • Look up a term from uploaded docs: {“projectId”: 12345, “searchContextDocuments”: “envelope_event_type_id”}
NOTES:
  • projectId is optional on purpose. Omit it to get the project list first, then call again with a real id from that list — do NOT guess project ids.
  • The two layers are meant to be loaded together: call once without projectId at session start for org context, then with a projectId to drill into a project. On conflict, project-level context overrides org-level.
  • Omit listContextDocuments and searchContextDocuments at session start — they add latency and are only useful once you know what to look for.
DO NOT USE FOR:
  • Running analytics queries → use ‘query_dataset’.
  • Finding charts/dashboards/cohorts → use ‘search’.

Input Parameters

integer
The project/app id to fetch detailed context for. Omit to get org context plus the list of projects you can access (the ‘get_context’ route); provide it to fetch one project’s settings (the ‘get_project_context’ route).
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
boolean
When true, adds contextDocuments: titles and ids of the customer’s uploaded context files (no file contents). Without projectId lists org-level documents; with projectId also includes that project’s documents. Omit at session start.
string
Semantic search query over the contents of uploaded context documents. Adds contextDocumentSearch with matching text snippets. Without projectId searches org-level documents; with projectId also searches that project’s documents.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_GET_AMP_SESSION_REPLAY_INFOUnified entry point for session replay data: find replays and inspect what happened in them. Replaces get_session_replays, list_session_replays, get_session_replay_events, and get_session_replay_timeline.ACTIONS:
  • search (default): find replays by event / user-property / cohort filters, by Amplitude user (userId), by ID (sessionReplayIds), or sample recent sessions with no filters (random slice from the last 24 hours).
  • list: simple paginated time-range listing via the public Session Replay API (start_time/end_time/page_size/page_token). Use search instead when filtering by events or user properties.
  • events: processed rrweb interaction timeline for one replay (sessionReplayId) — page navigations, clicks, inputs, scrolls.
  • timeline: full analytics event timeline for one replay (sessionReplayId) — every event the user fired during and around the session. PREFER THIS over user-timeline tools when you have a replay ID.
REQUIRED FOLLOW-UP — render_amp_session_replay:
  • After search/list return replay IDs, you MUST call render_amp_session_replay in the SAME turn whenever the user’s request implies viewing the replays (“show me”, “let me see”, “pull up”, “watch”, “play”, “open”, or any phrasing where seeing the replays is the deliverable). A list of IDs alone is not the answer the user wants.
  • ONLY skip the render call for raw data extraction (“just count them”, “export the IDs”). When in doubt, render.
INSTRUCTIONS:
  • Provide projectId for every action.
  • Replay IDs use the “<device_id>/<session_id>” format — pass them verbatim between actions.
  • search: filters are ANDed; reference real event names (call get_events first if unsure). userId and sessionReplayIds are mutually exclusive with each other and with filters.
  • list: use the returned next_page_token to fetch subsequent pages; keep sort_order consistent across pages. The list response’s start/end times describe the analytics session window, NOT the recorded replay length.
  • events vs timeline: events shows what the user DID in the recording (clicks/inputs/navigation from rrweb); timeline shows which analytics EVENTS fired (with properties). For “walk me through this session” prefer timeline.
EXAMPLES:
  • Sample recent sessions: { “projectId”: “12345” }
  • Users who hit checkout errors: { “action”: “search”, “projectId”: “12345”, “events”: [{ “name”: “Checkout”, “withProperty”: { “name”: “error_type”, “exists”: true } }] }
  • Replays for a user yesterday: { “action”: “search”, “projectId”: “12345”, “userId”: “98765”, “since”: “yesterday” }
  • Paginated listing: { “action”: “list”, “projectId”: “12345”, “page_size”: 50, “sort_order”: “desc” }
  • What the user did in a replay: { “action”: “events”, “projectId”: “12345”, “sessionReplayId”: “device-abc/1773235450374” }
  • Events fired during a replay: { “action”: “timeline”, “projectId”: “12345”, “sessionReplayId”: “device-abc/1773235450374”, “includeEventProperties”: true }
NOTES:
  • search defaults: 10 results; 30-day window for filtered queries, 24 hours otherwise. If a filtered search is empty, widen the window or relax filters instead of retrying unchanged.
  • list defaults to the last 48 hours when no time range is provided.
  • Cohort filters take numeric IDs only — resolve names with get_cohorts first.

Input Parameters

string
Single-day shorthand: “YYYY-MM-DD” or relative (“yesterday”, “today”). Expands to a 24-hour window centered on that day. Mutually exclusive with since/until.
integer
Max sessions to return. Defaults to 10.
string
Start of the search window. ISO 8601 (“2025-01-15T00:00:00Z”), Unix epoch ms or seconds, or a relative phrase (“yesterday”, “7 days ago”, “last week”). Defaults to 30 days ago for filtered queries; 24 hours ago for direct-ID lookups and the no-conditions sample.
string
End of the search window. Same flavors as since. Defaults to now.
string ("search" | "list" | "events" | "timeline")
Session replay operation: ‘search’ | ‘list’ | ‘events’ | ‘timeline’. Defaults to search.
array
Filter to sessions where the user performed these events. Each entry is ANDed within the same session by default (see matchScope).
string
Fetch sessions for one Amplitude user (the numeric amplitude_id). Mutually exclusive with sessionReplayIds and with filters.
array
Filter to users in these cohorts. Accepts numeric cohort IDs only — call get_cohorts to resolve a cohort name to its ID first.
number
events: recording format version, 3 (default) or 2 (legacy). Allowed values: 2, 3.
string
list: ISO 8601 upper bound. Defaults to now.
number
list: results per page (1-200, default 50).
string
required
The Amplitude project ID (appId) as a string (e.g. “12345”, “678910”). To find the project ID, check the URL or project context.
boolean
Shuffle results before returning. Use true for analysis sampling. Implied (with a 24-hour window) when no filters and no direct selectors are supplied.
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
number
timeline: max events to return (default 100, max 1000).
string ("session" | "user")
How to interpret multiple events. “session” (default) returns only replays where every event occurred in the same session — what users typically mean by “find sessions with X and Y”. “user” returns all replays of users who satisfied the filters somewhere in the time window, even if a given replay doesn’t contain every event. Has no effect when events is empty.
string
list: opaque pagination cursor from a previous response.
string ("asc" | "desc")
list: “asc” (oldest first) or “desc” (newest first, default).
string
list: ISO 8601 lower bound (e.g. “2024-01-01T00:00:00Z”). Defaults to 48 hours ago.
number
events: max interaction events to return (default 500).
string
list: filter replays to a specific Amplitude user ID. Mutually exclusive with sessionReplayIds.
array
Filter to sessions whose user matches these property conditions. Each entry is ANDed.
string
events/timeline: replay ID in “<device_id>/<session_id>” format, as returned by search/list.
array
search: fetch specific replays by “device_id/session_id” (max 100; mutually exclusive with userId and filters). list: filter the listing to these replay IDs (mutually exclusive with amplitude_id and page_token).
boolean
timeline: include full event properties (default false).
boolean
timeline: include [Experiment] assignment events (default false).

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_GET_AMP_TAXONOMYRead a project’s tracking plan: the events it defines, the properties on them, what a branch changes relative to main, and who changed what when.
WHEN TO USE — answer questions like:
  • “What events exist in project 12345?” → { action: “events”, projectId: “12345” }
  • “List the custom events” → { action: “events”, kind: “custom”, projectId }
  • “Show custom and labeled events together” → { action: “events”, kind: “all”, projectId }
  • “Which properties are on the Purchase event?” → { action: “properties”, propertyType: “event”, eventType: “Purchase”, projectId }
  • “Which events use button_name?” → { action: “properties”, propertyType: “event”, names: [“button_name”], projectId }
  • “What user properties are tracked?” → { action: “properties”, propertyType: “user”, projectId }
  • “What does branch feature/v2 change?” / “review this branch before merging” → { action: “branch_changes”, branchName: “feature/v2”, projectId }
  • “What changed in the tracking plan last week?” / “who deleted that event?” → { action: “activity”, since: “2026-09-01T00:00:00Z”, projectId }
  • Discovering valid event or property names before building a query_dataset filter or group_by
This is a fast schema lookup. Do NOT run query_dataset to discover which events or properties exist.
DO NOT USE FOR:
  • Metrics, counts, trends, funnels, retention → use ‘query_dataset’
  • Creating, updating or deleting taxonomy → use ‘manage_amp_events’ / ‘manage_amp_properties’
ACTIONS:INSTRUCTIONS:
  • Use get_amplitude_context first to get project IDs. If the user has not specified a project, prompt them to decide.
  • Raw events and custom/labeled events take different identifiers: eventTypes for raw, customEventNames / customEventIds for custom and labeled. Passing the wrong one is rejected rather than ignored.
  • Only raw-event reads are branch-aware and take fields; custom and labeled events are neither branch-scoped nor field-projected.
  • Where branch-aware, omit branchId/branchName for the default branch; otherwise pass exactly one selector.
  • Event and property semantics are unchanged from the tools this replaces — same statuses, same transformation folding, same field projection via fields.
  • activity reports current state nowhere: use it for “what changed”, and events/properties for “what exists now”.
  • activity is NOT a complete audit of everything that changed — say so rather than implying it is. Custom, labeled and autotrack event edits deliberately write no activity record; transformations live in a separate service with no activity log; derived and computed properties are not tracking-plan entities; and newly ingested unexpected events and properties never appear (read firstSeen from an events or properties read instead). Passing entityTypes or changeActions narrows further, dropping changes whose activity type has no mapping — sources, tags, group types, and edits made through the API — so an unfiltered query is the only complete view.
  • activity history belongs to the Data workspace, not the project, so every project sharing that workspace (its dev, staging and EU environments) returns the same rows. The response echoes workspaceId and branch — state that scope.
  • branch_changes requires exactly one branch selector, and always reports a comparison field. “3-way” compares against the point the branch was cut and also returns mainDrift and conflicts; “2-way” is used when no review is open, may include changes main made after the branch was cut, and cannot report drift or conflicts. Relay that caveat rather than presenting a 2-way result as the branch’s own edits.

Input Parameters

string ("event" | "custom" | "labeled" | "all")
events: which event surface. “event” (default) = raw tracking-plan events. “custom” / “labeled” = the custom-or-labeled surface. “all” = custom and labeled together. Same vocabulary as manage_amp_events.
string
properties + propertyType=user: exact user property name.
number
Page size. Prefer exact-name filters over exhaustive listing. action=activity caps at 200.
array
properties + propertyType=event|derived|channel|persisted: exact names. For event, mutually exclusive with eventType; each row lists the events that use it.
string
activity: inclusive start of the change window, ISO 8601 timestamp.
string
activity: inclusive end of the change window, ISO 8601 timestamp.
string ("events" | "properties" | "branch_changes" | "activity")
required
Which part of the tracking plan to read: “events”, “properties”, “branch_changes” or “activity”.
string
Pagination cursor.
boolean
branch_changes: include per-field before/after for updated entities, plus tag, source and property-group deltas. activity: include each change’s stored before/after values. Off by default on both.
array
Select response row fields. Valid values depend on the action and propertyType; omit for that surface’s defaults. For action=events the default is the slim set name, displayName, description, status — pass fields to widen it.
array
properties + propertyType=user: filter by property source.
string
Optional branch id (mutually exclusive with branchName).
array
activity: only changes attributed to these Amplitude login IDs.
array
branch_changes: expand only these entities, by name or id, across every bucket. Use the ids or names from a previous summary. Implies detail, and is not capped — use this when the unfiltered expansion truncates. Unresolvable names come back in detailForUnmatched.
string
properties + propertyType=event: scope to one event; omit to list project-wide.
string
Numeric Amplitude project ID. Optional only when the user has exactly one accessible project.
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
string
Optional branch name (mutually exclusive with branchId).
array
events + kind=event: exact event names to filter to (raw events only).
array
properties + propertyType=group: filter to these group types.
array
activity: restrict to these entity types. Omit for every recorded change — filtering drops changes whose activity type has no entity mapping (sources, tags, group types, API edits).
string ("event" | "user" | "group" | "derived" | "lookup" | "channel" | "persisted")
properties: which property surface to read. Defaults to “event”.
array
activity: restrict to these change kinds. Omit for every recorded change; same mapping caveat as entityTypes.
boolean
properties: include hidden rows. Defaults true.
array
events + kind=custom|labeled|all: filter by custom/labeled event ids.
boolean
properties: include blocked rows. Defaults true.
boolean
Include deleted rows. Defaults false. Pass true before recommending or executing an event-property delete so deleted event–property links are also surfaced.
string
properties + propertyType=lookup: filter to one lookup table.
array
events + kind=custom|labeled|all: filter by exact display names (include punctuation/brackets as shown in the UI).
boolean
branch_changes: also list the entities main changed since the branch was cut, not just the count. Off by default — on a long-lived branch this can exceed the branch’s own diff.
string ("all" | "configured" | "unconfigured")
properties + propertyType=lookup: configuration status.
string ("event" | "user")
properties + propertyType=derived: narrow to one level.
boolean
properties + propertyType=event|user: include transformations. Defaults true.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_GET_AMP_USER_DATALook up Amplitude users. One tool with modes selected by include (default profile).TWO KINDS OF “USER”:
  • Product users (default): people in project analytics data — use amplitudeId / userId / email / deviceId.
  • Org teammates (include='org'): people with Amplitude login accounts in your org — emails for sharing charts/dashboards/notebooks.
PRODUCT LOOKUPS — identify with exactly one of:
  • amplitudeId → exact lookup (fastest, no resolution step).
  • userId → your product’s user id; resolved to an amplitudeId first.
  • email → resolved to an amplitudeId (most projects use the email as the user id; a fallback search covers the rest).
  • deviceId → resolved via device-id match (anonymous / pre-login users).
  • amplitudeIds → batch form (max 10); profile mode only.
OUTPUT MODES (include):
  • id → ‘resolve_user_id’: resolve identifier to amplitudeId only.
  • profile (default) → ‘get_user_profile’: identity, properties, groups, usage stats.
  • timeline → ‘get_user_timeline’: recent event stream.
  • both → profile + timeline.
  • org → ‘get_org_users’: list org login emails/names for sharing. No product identifier or projectId needed. Pass returned loginId values to share tools.
INSTRUCTIONS:
  • projectId is required for product modes (id/profile/timeline/both); omit it for include='org'.
  • If a product identifier matches multiple users, the response lists candidates (status ‘ambiguous’) — re-call with amplitudeId.
  • Experiment-prefixed properties/events are excluded by default; set includeExperimentData when debugging experiments.
DO NOT USE FOR:
  • Enumerating product users who performed an event → use ‘use_amplitude_cohorts’ (action=‘find’).
  • Aggregate counts or trends → use ‘query_dataset’.
  • Org role / group / RBAC admin reads → use ‘get_org_users’ with the matching admin action.

Input Parameters

string
Email address to resolve to an amplitudeId.
string
Your product’s user id; resolved to an amplitudeId first.
string ("id" | "profile" | "timeline" | "both" | "org")
What to return: ‘id’, ‘profile’ (default), ‘timeline’, ‘both’, or ‘org’ (org teammate directory for sharing).
string
Device ID to resolve to an amplitudeId (anonymous users).
string
Project ID (appId). Required for product modes; omit when include=‘org’.
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
string
timeline/both: ISO 8601 timestamp to anchor the timeline — events before it are returned (default: now).
integer
timeline/both: number of events to return (default 50, max 1000).
string
Amplitude ID for exact lookup (provide exactly one identifier).
array
Batch of Amplitude IDs (max 10); profile mode only.
array
timeline/both: only include events with these exact event types.
boolean
Include [Experiment]-prefixed properties (profile) and assignment events (timeline). Default false.
boolean
timeline/both: include full event properties (default false for concise output).

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_GET_DATA_WAREHOUSE_DESTINATIONSList the Data Warehouse export destinations configured for a project.WHEN TO USE:
  • You want to see where a project exports its data (Snowflake, BigQuery, S3, etc.), their type, status, and last-export timing.
  • You need a destination’s connection id to inspect its export jobs by passing that id to use_amplitude_data_connections (view: ‘jobs’, as dataSourceId) — or to get_data_warehouse_jobs if that standalone tool is available in this session.
  • This is the export-side counterpart of the ingestion-source listing (which lists the import sources feeding the project).
INSTRUCTIONS:
  • Provide the projectId (appId) to list all configured export destinations.
  • Narrow the list with the optional type (matches eventDestinationType case-insensitively, whole value, so “SNOWFLAKE” does NOT match SNOWFLAKE_EXPORT_DATASHARE) and enabled filters instead of listing everything and scanning client-side. When either is set the response carries filteredFrom, the pre-filter count: an empty destinations with a non-zero filteredFrom means “none matched your filter”, NOT “this project has no destinations”. Report it that way.
  • Each destination’s id is a ready-to-use falcon:{id} — pass it as the dataSourceId to use_amplitude_data_connections (view: ‘jobs’), or as the connectionId to the standalone get_data_warehouse_jobs tool if that is the one available, to see that destination’s export jobs.
TIMING FIELDS (three different measurements — NOT three views of one job, and NOT reconcilable 1:1 with get_data_warehouse_jobs):
  • latestSuccessfulJobStartTime / latestFailedJobStartTime: START (enqueue) time of the most recent successful/failed automatic job, INCLUDING successful runs that exported 0 rows. Format ‘YYYY-MM-DD HH:MM:SS’ with fractional seconds and no timezone (effectively UTC).
  • latestExportCompletionTime: a data-export watermark — the COMPLETION time of the most recent successful run that actually exported data. Empty (0-row) successes and failures do NOT advance it, so it can legitimately lag latestSuccessfulJobStartTime by days or months when no new data has arrived. ISO-8601 with ‘T’ separator, no timezone designator (effectively UTC) — a different format from the two fields above.
  • RECONCILIATION CAVEAT: get_data_warehouse_jobs hides successful export jobs that exported 0 rows, so a destination can show latestSuccessfulJobStartTime = today while get_data_warehouse_jobs returns no recent SUCCESS job for the same connection. That is expected, not a contradiction. Do not treat these fields as ground truth against the jobs list, and do not conclude from them alone that a data-bearing export ran recently — use latestExportCompletionTime together with the jobs list to confirm actual data delivery.
NOTES:
  • Destinations only (exports); import/ingestion sources are listed separately.
  • Two kinds of destination are returned. falcon:{id} supports job history; gyrfalcon:{id} (Snowflake CUSTOM_EVENTS / EVENT_TRANSFORMATIONS, Databricks) does NOT yet — asking for its jobs returns supported: false, which does NOT mean it never ran. Judge those on latestSuccessfulJobStartTime / latestFailedJobStartTime / latestError (present only on gyrfalcon rows with a recorded error; its absence elsewhere means the backend cannot report one, not that all is well).
  • If note is present, part of the list could not be fetched — say so rather than reporting it as complete.
  • Responses never include credential fields — only type, status, timing (see TIMING FIELDS), and count fields when Falcon has populated them (see COUNT FIELDS).
  • COUNT FIELDS: latestRowsUnloadedCount / latestResolvedUserCount come from Falcon and are often unset. Null is omitted from the response (not a failure). For export row counts, inspect job history via use_amplitude_data_connections (view: ‘jobs’) or get_data_warehouse_jobs if that standalone tool is available — do not chase missing destination-level counts.

Input Parameters

string
Optional: keep only destinations whose eventDestinationType matches this value, case-insensitively (e.g. “SNOWFLAKE”, “BIGQUERY”, “AMAZON_S3”). Exact match on the whole value — “SNOWFLAKE” does NOT match SNOWFLAKE_EXPORT_DATASHARE.
boolean
Optional: keep only destinations whose enabled flag equals this. Destinations reporting a null enabled flag are excluded by either value, since neither true nor false is known to hold.
string
required
The project ID (appId) to list export destinations for.
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_GET_FROM_URLRetrieve objects from Amplitude URLsWHEN TO USE:
  • CRITICAL: Only use this tool for full Amplitude app URLs on supported hosts (app.amplitude.com, app.eu.amplitude.com, apps.stag2.amplitude.com, local.amplitude.com)
  • You have an Amplitude URL and want to get the full object definition
  • User shares a link to a dashboard, chart, notebook, experiment, etc.
INSTRUCTIONS:
  • Provide the full Amplitude URL (e.g., https://app.amplitude.com/analytics/myorg/chart/456 or https://app.eu.amplitude.com/analytics/myorg/chart/456)
  • The tool will parse the URL, validate the organization, and return the full object
  • Works with charts, dashboards, notebooks, experiments, flags, cohorts, metrics, and opportunities
  • /chart/new/{id} URLs may refer to a chart draft or a temporary chart edit (from query tools); both are resolved automatically
  • Agent session URLs (/agents/session/{id}) are not resolvable here — use get_agent_results with the session_id instead

Input Parameters

string
required
Full Amplitude URL to retrieve the object from
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_GET_GROUP_TYPESList available group types for a project. Group types are the categories of groups (e.g., “Company”, “Team”, “Account”) — NOT the properties/attributes of those groups.WHEN TO USE:
  • Use this tool to discover what group types exist (e.g., “Company”, “Team”).
  • Use get_properties with propertyType “group” instead if the user is generally asking for group properties (e.g., company_name, plan_tier).
NOTES:
  • Returns group types from the latest staging version of the default branch.

Input Parameters

string
required
Project ID (appId) to list group types for. Prompt the user if not specified.
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_GET_SESSION_REPLAY_DURATIONAPP SUPPORT ONLY. Do not call this tool from the LLM or agent.The session replay app calls this tool to hydrate replay duration metadata without downloading the full replay. Prefer list_session_replays, get_session_replays, get_session_replay_events, or render_amp_session_replay for user-facing tasks.APP INSTRUCTIONS:
  • Provide projectId and sessionReplayId in “<device_id>/<session_id>” format (as returned by list_session_replays / get_session_replays).
  • Returns durationMs: last event timestamp minus first event timestamp.
  • Returns null durationMs for empty or single-frame recordings.

Input Parameters

string
required
The Amplitude project ID (appId) as a string (e.g. “12345”, “678910”) the replay belongs to
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
string
required
Session replay ID in “<device_id>/<session_id>” format. Returned from list_session_replays / get_session_replays.

Output

string
boolean
required
number
Slug: AMPLITUDE_MCP_GET_SESSION_REPLAY_STREAMAPP SUPPORT ONLY. Do not call this tool from the LLM or agent.The session replay app calls this tool to stream rrweb events for inline playback. The response is base64-encoded gzipped NDJSON and is not useful for text reasoning.If you need to understand what happened in a replay, use get_session_replay_events instead.APP INSTRUCTIONS:
  • First call: pass projectId + sessionReplayId. Response includes durationMs, events (file 0), and nextCursor.
  • Continue with nextCursor until it is null.
  • For duration-only hydration, pass metadataOnly: true.

Input Parameters

string
Opaque cursor returned by the previous call as nextCursor. Omit on the first call.
string
required
The Amplitude project ID (appId) as a string (e.g. “12345”, “678910”) the replay belongs to
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
boolean
If true, return only durationMs (no event chunks). Used by the sessions panel to hydrate per-row durations cheaply.
string
required
Session replay ID in “<device_id>/<session_id>” format. Returned from list_session_replays / get_session_replays.

Output

string
string
boolean
required
number
string
number
number
Slug: AMPLITUDE_MCP_GET_SESSION_REPLAY_TIMELINEAPP SUPPORT ONLY. Do not call this tool from the LLM or agent. The session replay app calls this tool to hydrate the events panel and user identities. Use get_amp_session_replay_info (action timeline) for user-facing tasks.

Input Parameters

string
required
The Amplitude project ID (appId) as a string (e.g. “12345”, “678910”)
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
number
Max number of events to return (default 100, max 1000)
string
required
Session replay ID in the format “<device_id>/<session_id>”, e.g. “0c650142-4a68-4f82-ad6a-4f154fee5265/1773235450374”
boolean
Whether to include full event properties (default false for concise output)
boolean
Whether to include [Experiment] assignment events (default false)

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_GET_TRACKING_PLAN_SOURCESList the sources configured on a project’s tracking plan (e.g. iOS, Android, Web, Server).WHEN TO USE:
  • You need source IDs before adding sources to an event in the tracking plan.
  • The user asks what sources are configured on their tracking plan.
INSTRUCTIONS:
  • Pass projectId.
  • Returns each source’s id and name. Use the id when modifying event sources.
NOTES:
  • The Sources UI merges tracking-plan labels with pipeline connections, but this tool returns only the tracking-plan catalog (id + name) for assigning sources to events. Use get_data_ingestion_sources for ingestion status, volumes, and warehouse/import connections.

Input Parameters

string
required
Project ID to list tracking plan sources for. If the user has not specified a project, prompt the user to decide. Don’t decide for them.
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_GET_TRANSFORMATIONSRetrieve data transformations from a project. Transformations are data cleaning operations that merge events, merge properties, or map property values.WHEN TO USE:
  • Use this tool to see what transformations are configured for a project.
  • Use this tool to understand how events or properties are being merged or remapped.
  • Use this tool to audit data cleaning rules applied to a project.
WHAT IT RETURNS:
  • A list of transformations with their type, name, description, and configuration details.
  • Transform types include: merge (merge events), merge_events_derived_prop (merge events with derived property), merge_event_properties, merge_user_properties, map_event_property_values, map_user_property_values.
INSTRUCTIONS:
  • Get the project ID from the context tool.
  • Optionally filter by transform type to narrow results.
  • Use pagination to retrieve large lists of transformations.

Input Parameters

number
Maximum number of transformations to return (1-500). Use this in conjunction with cursor to paginate through results.
string
Pagination cursor for retrieving the next page of results. Use this in conjunction with limit to paginate through results.
string
required
Project ID to get transformations from. If the user has not specified a project, prompt the user to decide. Dont decide for them.
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
string ("merge" | "merge_events_derived_prop" | "merge_event_properties" | "merge_user_properties" | "map_event_property_values" | "map_user_property_values")
Optional filter by transformation type. Values: merge, merge_events_derived_prop, merge_event_properties, merge_user_properties, map_event_property_values, map_user_property_values.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_MANAGE_AMP_CONTEXTManage AI context. Actions: set_org_context and set_project_context replace customer AI context. Use get_amplitude_context to read your current org, projects, and context.

Input Parameters

string ("set_org_context" | "set_project_context")
required
Discriminator: determines which set of parameters applies (set_org_context | set_project_context)
string
required
New org AI context.
number
Project ID.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_MANAGE_AMP_ENTITIESCreate a shared (team) space, rename a space or change its members, or move charts, dashboards, notebooks, or cohorts into a shared space. Opens a confirmation card the user approves. Selected by route.ROUTES:
  • create_space: create a new shared space. Opens a compact form prefilled with the proposed name and members (spaceName, members).
  • manage_space: update an existing shared space’s name, description, or members. Requires spaceId.
  • move_to_space: move charts, dashboards, notebooks, or cohorts into an existing shared space. Renders a destination picker over the entities you pass.
  • search_members, validate_confirmation, and commit: reserved for the confirmation card. Do not call them yourself.
SPACE MANAGEMENT:
  • This is the only tool for creating, updating, or moving content into shared spaces.
  • If the needed destination does not exist, use create_space first. Do not create a destination inside move_to_space.
INSTRUCTIONS:
  • For move_to_space, prefer objects and pass each entity’s id plus the display name already established in the conversation or source tool output. This is especially important for unnamed chart edits: preserve the useful name you gave the chart instead of showing “Untitled chart”. Do not use one title for multiple objects.
  • Resolve entity ids with search_amp_entities, or pass chart edit ids straight from query_amplitude_data. objectIds and objectId remain compatibility fallbacks when no display name is available.
  • objectType is optional for charts (saved vs unsaved is detected from the id) and required for dashboards, notebooks, and cohorts.
  • Set title to a short line explaining why the app opened, in the user’s own words.
  • Nothing is written when a launch route returns. The user confirms in the app, which applies the change and reports back.
DO NOT USE FOR:
  • Archiving flags or cohorts: no archive route exists yet.
  • Sharing individual charts or dashboards, or org invites: use share_amp_entities.

Input Parameters

string
string ("create_space" | "manage_space" | "move_to_space" | "search_members" | "validate_confirmation" | "commit")
required
Discriminator: determines which set of parameters applies (create_space | manage_space | move_to_space | search_members | validate_confirmation | commit)
string
Short heading explaining why the app opened, in the user’s words.
array
Org teammate login emails to preselect. The user can change them before confirming.
array
Preferred move input. Pair every entity id with its established display name so the confirmation stays recognizable.
string
Existing shared space to update.
object
Space details submitted by the create_space app route.
string
Singular alias for objectIds.
array
Entity ids to act on. Saved entity ids, or chart edit ids from query_amplitude_data.
string
Suggested space name to prefill in the app.
string ("CHART" | "DASHBOARD" | "NOTEBOOK" | "COHORT")
CHART, DASHBOARD, NOTEBOOK, or COHORT (uppercase). Optional for charts; required for the others.
array
Entity ids the user left selected.
object
Update the token-bound shared space.
string
Existing space to move the selection into.
string
Suggested space description to prefill in the app.
string

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_MANAGE_AMP_EVENTSWrite to a project’s tracking-plan events — raw ingested events, custom events, and labeled (autotrack) events — in one tool selected by action + kind. Reading events lives in get_amp_taxonomy.KINDS:
  • event (default): raw ingested / planned event types in the tracking plan (Purchase, Page Viewed, …). Identified by eventTypes.
  • custom: virtual events composed of one or more raw source events with optional filters (isAutotrack=false). Identified by customEventNames / customEventIds.
  • labeled: autotrack / labeled events (isAutotrack=true). Same identifiers as custom. Update and delete — MCP cannot create labeled events.
ACTION + KIND MATRIX (key params per combo):
  • create + event → events: [{ name, isUnexpected, … }] (isUnexpected: true adds an already-ingested unexpected event to the plan; false creates a brand-new planned event)
  • create + custom → name + definition (raw source events)
  • update + event → maps keyed by exact raw event name (descriptions, newNames, categories, sources, tags, visibility, owners, …)
  • update + custom|labeled → maps keyed by id / display name / ce:<name> (descriptions, newNames, categories, isOfficial, eventDefinitions)
  • delete + event → eventTypes; mark as deleted (ingested) / removed (planned); two-step with confirmed
  • delete + custom|labeled → customEventNames / customEventIds; permanently removed (same as UI); two-step with confirmed
  • restore + event only → eventTypes (custom/labeled cannot be restored)
COMMON MISTAKES (seen in production — avoid these):
  • Using eventTypes with kind custom/labeled, or customEventNames with kind event. Raw events → eventTypes; custom/labeled → customEventNames/customEventIds.
  • Sending kind: "all". It is no longer a valid kind here — it only ever meant “custom and labeled together” on a read. Use get_amp_taxonomy (action: events) to read both, or pick custom or labeled for a write.
  • Omitting action. It is required now; it used to default to get, which no longer exists on this tool.
  • Putting ce:<name> values in a custom event definition — source events must be raw event types; custom events cannot nest, and labeled events as sources are not supported yet.
  • create + event failing with “name already exists”: the event was likely already ingested (unexpected) — retry with isUnexpected: true to add it to the plan instead.
  • Setting description/category/isOfficial on an event with isUnexpected: true — add to plan first, then update.
  • update + event on events not yet in the tracking plan — only planned/live events can be updated; add unexpected events to the plan first.
  • Creating a custom event whose definition duplicates an existing one — the API rejects duplicates and returns the existing event; reuse it instead.
HOW TO FIND THE EVENTS YOU ARE ABOUT TO CHANGE:
  1. Discover names with search (entityTypes: ["EVENT"] or ["CUSTOM_EVENT"]). That is the primary path.
  2. Hydrate them with get_amp_taxonomy (action: events) before writing — it returns status, category, activity, visibility, and ingestion timestamps, and confirms the exact name to key update maps by.
DELETE / RESTORE:
  • For kind:event, delete is a two-step confirmation gate for every target — mark as deleted and remove alike. Never skip confirmation.
  • Marking as deleted stops ingestion immediately on main; on any other tracking-plan branch, ingest is unchanged until merge. Removing a planned event does not stop ingestion (the event was never ingested).
  • Restore: on main, ingestion resumes immediately; on any other branch, the restore is staged until merge. Only events that were marked as deleted can be restored; removed planned events must be recreated.
  • Custom/labeled delete is permanent and does not use this branch-ingest rule.
TYPICAL FLOWS:
  • Add raw events on a branch: manage_amp_taxonomy create_branch (if main protected) → create with kind event + branchName → update metadata as needed.
  • Build a custom event: get_amp_taxonomy for the raw source events → create with kind custom + definition (source events).
  • Delete raw events (not custom/labeled): delete with kind event (confirmation_required first), then confirmed: true after the user acknowledges the buckets and branch. Ingested events are marked as deleted (restorable); planned events are removed (not restorable).
  • Permanently remove a custom/labeled event: delete with kind custom|labeled + customEventNames/Ids (confirmation_required first), then confirmed: true. Cannot be restored.
  • Restore a deleted raw (not custom/labeled) event: get_amp_taxonomy with action: events + includeDeleted: true to find it, then restore with its exact eventTypes.
PROJECT ID:
  • Pass numeric projectId. Get it from get_amplitude_context if needed.
  • If omitted and the user has exactly one accessible project, that project is used automatically.
DO NOT USE FOR:
  • Reading events → get_amp_taxonomy (action: events)
  • Fuzzy discovery → search
  • Properties → manage_amp_properties (writes) / get_amp_taxonomy (reads)
  • Branch governance → manage_amp_taxonomy (or legacy branch tools)

Input Parameters

string ("event" | "custom" | "labeled")
event = raw tracking-plan events (default). custom / labeled = custom-or-labeled surface.
string
create kind=custom: display name for the new custom event.
string
update kind=event: tags to add.
string ("create" | "update" | "delete" | "restore")
required
Event write operation. Required — reads live in get_amp_taxonomy.
array
create kind=event: array of { name, isUnexpected?, description?, category?, isOfficial? }. name is the exact ingested event name (same as get_events name).
object
update kind=event: name -> owner login ID (typically the user email). Same identifier as get_amp_taxonomy owner; values are trimmed and lowercased. Assigns the tracking-plan owner; does not clear an existing owner. Not supported for custom/labeled events or properties.
object
update kind=event: source IDs to add (use get_tracking_plan_sources).
string
create/update/delete/restore kind=event: optional branch id (mutually exclusive with branchName).
string
create kind=custom: optional category.
object
update: rename map.
boolean
delete kind=event|custom|labeled: set true only after the user acknowledges the prior confirmation_required response. Required for every delete — not only ingested events marked as deleted.
string
Numeric Amplitude project ID (e.g. “123456”). Optional only when the user has exactly one accessible project.
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
string
create/update/delete/restore kind=event: optional branch name (mutually exclusive with branchId).
string
update: category map.
array
create kind=custom: source events [{ event_type, filters? }, …]. At least one required.
array
delete / restore kind=event: exact ingested event names to act on.
string
create kind=custom: boolean official flag. update: map of exact raw event name or custom id_or_name → boolean.
string
update kind=event: tags to remove.
object
update kind=event: name -> { hiddenFromDropdowns?, hiddenFromPersonaResults?, hiddenFromPathfinderAndJourneys?, hiddenFromEventStreams? }. Omitted flags remain unchanged. get_amp_taxonomy returns read-shaped hiddenFrom surface lists; use these flags to change visibility.
string
create kind=custom: optional description.
object
update: descriptions map (raw event name or custom id_or_name).
object
update kind=event: source IDs to remove.
array
update / delete kind=custom|labeled: custom/labeled event ids.
object
update kind=event: name -> boolean active/inactive state. Same field name as isActiveAction on get_amp_taxonomy output.
array
update / delete kind=custom|labeled: exact display names (include punctuation/brackets as shown in UI).
object
update kind=custom|labeled: id_or_name → SourceEvent[] definition replacements.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_MANAGE_AMP_TAXONOMYRead Data workspace governance settings and manage tracking-plan branches for a project. One tool selected by action (default get).TYPICAL FLOW (most common production path):
  1. get first — learn mainProtected, naming conventions, approval workflow, and environments before changing the plan.
  2. If mainProtected is true (or the user wants an isolated change), create_branch — do not mutate main. Optionally get again / check branches first so you do not recreate an existing name.
  3. Apply tracking-plan edits with the taxonomy mutation tools (create_events, create_properties, update_event, …) and pass branchName / branchId to target that branch — those tools are separate from this one.
  4. Finish with merge_branch (two-step confirmed) when the user wants changes on main, or delete_branch (two-step confirmed) to abandon. Many sessions stop after step 3 with work left on the feature branch — that is normal.
  5. Less common: refresh_branch (pull main into the feature branch; two-step), review_branch (approve/unapprove when approvals are required), update_branch (description only).
ACTIONS:
  • get (default): workspace settings + environments + branches in one response. Includes mainProtected (true when approvalWF is “Required” — changes must go on a feature branch, not main) and workflowHint.
  • create_branch: create a branch off main. Requires name.
  • update_branch: update a branch description (not name). Requires branchName or branchId + description.
  • delete_branch: delete a non-main branch. Two-step: call once, then again with confirmed: true after the user acknowledges.
  • merge_branch: merge a feature branch into main. Two-step with confirmed. If approvals are required and missing, reports status instead of merging.
  • refresh_branch: pull latest main into a feature branch. Two-step with confirmed; conflicts overwrite the feature-branch version.
  • review_branch: approve or unapprove a branch for merge. Pass reviewDecision (“approve” | “unapprove”). Prefer after the branch has pending changes — empty branches cannot be approved.
PROJECT ID:
  • Pass numeric projectId (e.g. “123456”). Get it from get_amplitude_context if you do not already have one.
  • If omitted and the user has exactly one accessible project, that project is used automatically.
  • Do not invent project ids. Do not use project names.
DO NOT USE FOR:
  • General org/user/project discovery → get_amplitude_context
  • Creating or updating events/properties → the taxonomy mutation tools (create_events, create_properties, …) with branchName when on a feature branch
  • Listing events/properties → get_events / get_properties

Input Parameters

string
create_branch: unique name for the new branch.
string ("get" | "create_branch" | "update_branch" | "delete_branch" | "merge_branch" | "refresh_branch" | "review_branch")
Workspace/branch operation. Defaults to get.
string
Branch ID for update/delete/merge/refresh/review. Use either branchId or branchName.
boolean
delete_branch / merge_branch / refresh_branch: set true only after the user explicitly confirms.
string
Numeric Amplitude project ID (e.g. “123456”). Get it from get_amplitude_context. Optional only when the user has exactly one accessible project.
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
string
Branch name for update/delete/merge/refresh/review. Use either branchId or branchName.
string
create_branch: optional branch description. update_branch: new description (required for that action).
string ("approve" | "unapprove")
review_branch: whether to approve or withdraw approval. Defaults to approve.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_QUERY_AMPLITUDE_DATARun analytics queries to answer data questions about users, events, funnels, and retention — and to create or modify charts via the typed chart parameter.PREFERRED: pass the typed chart parameter (segmentation | funnel | retention | sessions | data_table). It is a small, UI-shaped model (events, where, group_by, measured_as, segments, date_range) that is deterministically compiled server-side into a validated chart definition — compile errors come back with a fix-oriented hint, so you never need to hand-build raw definition JSON.FALLBACK: pass a raw definition only for chart types the typed model does not cover (composition, revenueLtv) or advanced params the typed model has no field for. Raw definitions are validated inline; on failure the response includes chartTypeSchema with the parameter schema, valid enums, a working example, and coercion rules.Provide exactly one of chart or definition.
WHEN TO USE - Answer questions like:
  • “How many active users did we have last week?”
  • “Show me a funnel from sign up to purchase”
  • “What is the retention rate for new users?”
  • “Create a chart…” / “Modify chart X to…”
  • Any question asking for metrics, counts, trends, funnels, or retention analysis
DO NOT USE FOR:
  • Finding existing charts/dashboards → use ‘search’ or ‘get_amplitude_charts’ instead
  • Project settings (timezone, currency) → use ‘get_amplitude_context’ with projectId instead
STRATEGIES
  1. Discover event/property names with ‘search’ (or search_amp_data_taxonomy) — never guess them.
  2. Create: build the typed chart (events + date_range required; add where/group_by/segments as asked) → call this tool.
  3. Modify / fork a saved chart: search to find the chart id → get_amplitude_charts include='typed' → edit the returned chart → call this tool with that chart AND chartId set to the saved chart id (links the edit to the parent; parent params fill gaps the typed model omits — including date_range, which may be left out to keep the parent’s window).
  4. Call query_amplitude_data — compile and validation errors are actionable; fix the named field and retry.
  5. To show the result visually, call ‘render_amplitude_chart’ with the returned chartEditId.
GENERAL GUIDELINES
  • Don’t guess event or property names — discover them first, and use the exact name and scope returned.
  • ALWAYS set a descriptive “name” (becomes the chart title) and an explicit date_range (except when modifying with chartId and the parent’s window should be kept).
  • Relative date_range windows support an Offset suffix for day-over-day / historical comparisons: “Last 0 Days Offset 1” (yesterday), “Last 0 Days Offset 7” (same day last week), “Last 7 Days Offset 7” (the prior week).
  • On errors, follow the hint in the message; the compiler names the offending field.
Chart types supported by raw definition: eventsSegmentation, funnels, metricExplorer, retention, revenueLtv, sessions, stickinessRESPONSE FORMAT: Returns {isCsvResponse: bool, csvResponse or jsonResponse, definition}. Only ONE response type present. When jsonResponse is present, “seriesNames” (string[]) gives the human-readable name of each timeSeries entry in order — use it instead of the numeric seriesLabels for ungrouped segments. Check the isCsvResponse flag to determine which response format to parseCRITICAL — NON-ADDITIVE METRICS (uniques, pct_dau):
  • These metrics cannot be summed across intervals. The chart UI plots per-interval values, not a running total.
  • Additive metrics (totals, sums) CAN be summed across intervals.
How to read the JSON response, by metric type:
  1. COUNT metrics (“uniques”):
    • Use “overallSeries” — it is the TRUE deduped unique count across the full date range.
    • Do NOT sum “timeSeries” values — that overstates the count due to user overlap across intervals.
  2. RATIO metrics (“pct_dau” only):
    • Use “timeSeriesAverage” (mean of per-interval values) — this matches what the chart UI displays. For “current” reporting, also consider the most recent N intervals from “timeSeries”.
    • Do NOT use “overallSeries” for pct_dau over multi-interval ranges. For pct_dau, “overallSeries” is a long-range aggregate (deduped numerator over the full range / deduped denominator over the full range). Over many intervals the denominator dedupes a much larger pool than the numerator, which compresses the ratio — typically reporting roughly half of the per-interval values the chart shows. This is mathematically valid as a long-range aggregate but is NOT what users see in the chart.
    • Do NOT sum “timeSeries” values — ratios cannot be summed.
CSV Response Structure (when isCsvResponse is true):
  • Header rows: The top rows contain metadata including chart name, description, events, formulas, and other chart configuration details
  • Data header row: A single row containing column labels for the data points below (typically includes dates or time periods)
  • Data rows: Each row contains:
    • Label columns: First few columns contain row labels identifying the data series
    • Value columns: Numerical data organized under the corresponding date/time columns from the data header row
  • Parse by: Skip metadata rows, identify the data header row, then extract labels from first columns and values from remaining columns
  • Cells in the CSV response are delimited by commas and may be prepended with a character Example below measures uniques of custom event “Valuable Tweaking” over 3 days (2025-08-23, 2025-08-24, 2025-08-25) for all users. The data points are 614, 1769, and 4132 for the 3 days respectively. IMPORTANT: The overall unique users is 5642 (NOT 614+1769+4132=6515), because users overlap across days. data: ” Example chart name” ” Formula”,” UNIQUES(A)” ” A:”,” [Custom] ‘Valuable Tweaking’”
” Segment”,” 2025-08-23”,” 2025-08-24”,” 2025-08-25” ” All Non-Amplitude Users”,“614”,“1769”,“4132” definition: { “app”: “APP_ID”, “params”: { “countGroup”: “User”, “end”: 1756166399, “events”: [ { “event_type”: “ce:‘Valuable Tweaking’”, “filters”: [], “group_by”: [] } ], “groupBy”: [], “interval”: 1, “metric”: “uniques”, “segments”: [], “start”: 1755907200, }, “type”: “eventsSegmentation”, }JSON Response Structure (when isCsvResponse is false):
  • Parse using the following structure:
    • timeSeries: Array of arrays, each containing data points for a given time period with a “value” property
    • overallSeries: Array of arrays, each containing the overall data point across the entire range under the “value” property. IMPORTANT — interpretation depends on the metric:
      • For “uniques” (count): this is the TRUE deduped unique count over the full date range. Use this.
      • For “pct_dau” (ratio): this is a long-range aggregate ratio (deduped numerator over range / deduped denominator over range). It does NOT match the per-interval values the chart UI plots and is typically much smaller. Do NOT report it as the headline number — use “timeSeriesAverage” instead.
    • timeSeriesAverage: Present only for “pct_dau”. Array of arrays, one per series, each containing a single {value} that is the mean of “timeSeries” values for that series. Use this as the headline ratio when the chart spans multiple intervals — it matches what users see in the chart UI.
    • seriesMetadata: Array of objects containing metadata for each series
    • xValuesForTimeSeries: Array of strings representing the x-axis values (dates) for the time series
  • Use the dataset definition to be able to parse referenced events, properties, and segments.
Example below is a JSON response is for the same query as the CSV example above. { “timeSeries”: [[\{"value": 614\}, \{"value": 1769\}, \{"value": 4132\}]], “overallSeries”: [[\{"value": 5642\}]], “seriesMetadata”: [{“segmentIndex”: 0, “formulaIndex”: 0, “formula”: “UNIQUES(A)”}], “xValuesForTimeSeries”: [“2025-08-23T00:00:00”, “2025-08-24T00:00:00”, “2025-08-25T00:00:00”] } Note: 614+1769+4132=6515, but overallSeries shows 5642. This is because unique users overlap across days. For “uniques”, always use overallSeries for the total.Example below is a “pct_dau” query over 3 weeks (a ratio metric): { “timeSeries”: [[\{"value": 0.1402\}, \{"value": 0.1421\}, \{"value": 0.1444\}]], “overallSeries”: [[\{"value": 0.0712\}]], “timeSeriesAverage”: [[\{"value": 0.1422\}]], “seriesMetadata”: [{“segmentIndex”: 0, “formulaIndex”: 0, “formula”: “PCT_DAU(A)”}], “xValuesForTimeSeries”: [“2026-04-06T00:00:00”, “2026-04-13T00:00:00”, “2026-04-20T00:00:00”] } Note: the chart UI shows ~14% per week. timeSeriesAverage (14.22%) matches that. overallSeries (7.12%) is the deduped 3-week aggregate ratio and would HALVE the reported value if used as the headline — never report it as “the number” for “pct_dau”. Always use timeSeriesAverage for “pct_dau”.Event Segmentation with Insights (anomaly detection / confidence intervals):
  • When params.insights.isOn is true, Event Segmentation charts queried via query_charts or query_dataset return BOTH chartConfig (Highcharts) AND jsonResponse with joinable band data.
  • jsonResponse.seriesIntervals maps stringified seriesMetadata keys to { low, high, yhat } arrays (parallel to xValuesForTimeSeries). Use seriesMetadata + xValuesForTimeSeries to join bands to series.
  • Metric Explorer charts with Insights return seriesIntervals inside each data[] entry instead.

Input Parameters

string
PREFERRED. Typed, UI-shaped chart parameters, discriminated on kind (segmentation | funnel | retention | sessions | data_table). Compiled server-side into a validated definition — no raw definition JSON needed. Provide exactly one of chart or definition.
string
Optional parent chart ID for modify/fork. When provided, the parent chart’s params (segments, filters, countGroup, groupBy, etc.) are used as defaults — only params you explicitly provide will override. Typical modify flow: get_amplitude_charts include=‘typed’ → edit chart → query_amplitude_data({ chart, chartId }).
string
required
Project ID to query data from
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
object
FALLBACK — prefer the typed chart parameter. Raw chart definition for types/params the typed model does not cover (e.g. composition, revenueLtv). Validated inline — on failure the response includes chartTypeSchema (params, enums, example, coercion rules) so you can fix and retry. Use canonical chart types only: - “eventsSegmentation” - “funnels” - “retention” - “sessions” - “revenueLtv” - “dataTableV2” Do not use aliases like: - “segmentation” - “event_segmentation” - “events” - “funnel” TIME RANGE — three accepted shapes, mutually exclusive with each other: - “range” preset (e.g. “Last 30 Days”, “Last 12 Weeks”, “This Month”, “Yesterday”) - “start” + “end” for a bounded custom range - “start” alone for an open-ended “since <date>” range (renders as Amplitude’s “Since” view) - Timestamps may be Unix seconds, ISO 8601 strings, or relative strings like “now-7d” / “now” - Do not combine “range” with “start”/“end”. Do not provide “end” without “start” - Do not use invalid placeholders like “Custom”, “Daily”, or “All Time” VISUALIZATION TYPE (top-level “vis”, optional): - Set “vis” when the user explicitly asks for a specific chart shape (e.g. “as a bar chart”, “show as a pie”, “stacked bar by country”). Otherwise omit and the system picks a sensible default. - Valid values for eventsSegmentation: “line” (default trend), “area”, “bar” (vertical), “column” (horizontal), “stackedbar”, “pie”, “kpi” (single number). - Valid values for funnels: “line”, “bar”. - Valid values for sessions: “line”, “bar”, “totalSessions”, “average”. - “vis” goes at the TOP LEVEL of the definition, NOT inside “params”. COMMON GUARDRAILS: - “dataTableV2” requires “params.table” - “sessions” requires “params.sessions” - “customerJourney” has a maximum of 5 steps when using PATH_TREE or SINGLE_PATH visualization - event lists should use canonical event objects with “event_type”, “filters”, and “group_by” - include a descriptive top-level “name” whenever possible MINIMAL EXAMPLES: - eventsSegmentation (default line): {“type”:“eventsSegmentation”,“app”:“123”,“name”:“Active Users Last 30 Days”,“params”:{“range”:“Last 30 Days”,“events”:[{“event_type”:“_active”,“filters”:[],“group_by”:[]}],“metric”:“uniques”,“countGroup”:“User”,“groupBy”:[],“interval”:1,“segments”:[{“conditions”:[]}]}} - eventsSegmentation as bar chart (user said “show as a bar chart”): {“type”:“eventsSegmentation”,“app”:“123”,“name”:“Purchases by Country”,“vis”:“bar”,“params”:{“range”:“Last 30 Days”,“events”:[{“event_type”:“Purchase”,“filters”:[],“group_by”:[{“type”:“event”,“value”:“country”}]}],“metric”:“totals”,“countGroup”:“User”,“groupBy”:[],“interval”:1,“segments”:[{“conditions”:[]}]}} - funnels: {“type”:“funnels”,“app”:“123”,“name”:“Signup Funnel”,“params”:{“range”:“Last 30 Days”,“events”:[{“event_type”:“View Signup”,“filters”:[],“group_by”:[]},{“event_type”:“Complete Signup”,“filters”:[],“group_by”:[]}],“countGroup”:“User”,“segments”:[{“conditions”:[]}]}} - revenueLtv (cumulative revenue from users NEW in the selected date range — empty results usually mean no new users were acquired in the period, not broken revenue instrumentation): {“type”:“revenueLtv”,“app”:“123”,“name”:“Revenue LTV - Total Revenue”,“vis”:“line”,“params”:{“range”:“Last 90 Days”,“metric”:“2”,“event”:{“event_type”:“_any_revenue_event”,“filters”:[],“group_by”:[]},“revenueProperty”:“$revenue”,“groupBy”:[],“countGroup”:“User”,“interval”:1,“segments”:[{“conditions”:[]}]}}
number
Maximum number of group by values to return (1-1000, defaults to 10)
integer
Maximum number of group-by values that include per-interval time-series rows in the CSV response. All group-by values always include their aggregate “Total” row. Groups beyond this limit only return their Total row, which dramatically reduces response size for charts with many group-by values over long date ranges. Set to 0 for totals-only. Defaults to 3.
array
Additional render-only information to include. Omit for compact analytics data.
boolean
Optional flag to exclude incomplete data points from results. When true, the current time interval will be excluded from the results to avoid incomplete data points. Defaults to false.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_RENAME_CHARTRename a chart that has already been savedWHEN TO USE:
  • A chart was saved (e.g. via save_chart_edits) and the user wants a different name on that same chart
IMPORTANT:
  • Updates the existing chart in place and records a version-history entry; it does not create a copy
  • Requires edit access to the chart and write access to its project
  • To save a new chart from an ad-hoc edit, use save_chart_edits instead

Input Parameters

string
required
New name for the chart
string
required
ID of the saved chart to rename (e.g. from /chart/abc123)
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
string
New description. Omit to leave the existing one untouched

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_RENDER_AMPLITUDE_CHARTRender an interactive Amplitude chart UI for a saved chart or a chart edit by ID. This is the way to SHOW a chart to the user — it spins up the chart widget; the widget fetches the chart’s data itself and draws it.

SUPPORTED CHART TYPES

eventsSegmentation, funnels, retention, metricExplorer.
  • dataTableV2 CANNOT be rendered in the chart widget. Present query results directly instead.

WHEN TO USE

  • The user wants to SEE a chart and you already have a chartId (saved chart) or chartEditId (ad-hoc chart edit).
  • Right after query_dataset returns a chartEditId for a non-empty result — pass that chartEditId here to render it.
  • Right after search / get_from_url resolves a saved chartId the user asked to see.

WHEN NOT TO USE — DO NOT CALL WITHOUT AN ID

  • You do NOT have a chartId or chartEditId yet. Resolve one FIRST:
    • query_dataset (returns a chartEditId for an ad-hoc definition)
    • search with entityTypes: ["CHART"] (finds a saved chartId)
    • get_from_url (parses an id out of an Amplitude chart URL)
  • The query you ran returned empty / all-zero data — tell the user, do NOT render an empty chart.

INSTRUCTIONS

  • Provide exactly one of chartId (saved chart) or chartEditId (chart edit). If you have both, prefer chartEditId.
  • When rendering a chart edit from query_dataset, pass its returned title so the widget displays the requested chart title.
  • This tool does NOT return chart data to you — it only renders the widget. To reason about the numbers, call get_amplitude_charts (include=‘data’) / query_dataset for the data.

Input Parameters

string
Chart title to display. Pass the title returned by query_dataset when rendering a chart edit.
string
Saved chart ID to render (e.g. from search or get_from_url).
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
string
Chart edit ID to render. Returned by query_dataset, or parsed from links ending in /chart/new/<edit_id> or /chart/<chart_id>/edit/<edit_id>.

Output

string
string
string
string
boolean
required
string
boolean
boolean
required
Slug: AMPLITUDE_MCP_RENDER_AMP_SESSION_REPLAYRender an interactive session replay player UI for one or more session replays. This is the ONLY way to actually show a session replay to the user — text descriptions are not a substitute.WHEN TO USE (call this tool whenever the user wants to SEE a replay):
  • Any user request with a viewing verb: “show me”, “render”, “play”, “watch”, “let me see”, “pull up”, “open”, “display”, “view”, “I want to see”, “can I see” + “session replay(s)” / “session(s)” / “recording(s)” / “the replay” / “those sessions”.
  • Any time the user asks to look at, observe, or visually inspect session activity, even without an explicit verb (e.g. “the session for jane@acme.com”, “that recording”, “those replays from yesterday”).
  • Immediately after a session replay search returns replay IDs in response to such a request — chain directly into render_amp_session_replay with the returned IDs. Do NOT stop at listing IDs in text when the user asked to see the replays.
  • If the user asks to see replays but you don’t have IDs yet, FIRST find them with the session replay search tool available to you (get_amp_session_replay_info, else get_session_replays / list_session_replays), THEN call this tool with the results — in the same turn.
  • Call ONCE with a list of IDs to render multiple replays the user can switch between — do NOT call this tool separately per replay.
WHEN NOT TO USE:
  • The user is asking for a count, summary, or analysis of replay events without wanting to watch them (“how many replays…”, “what did the user do in…”, “summarize…”). Use the timeline / events tools instead.
INSTRUCTIONS:
  • Provide projectId and one or more sessionReplayIds.
  • sessionReplayId format is “<device_id>/<session_id>” (e.g. “0c650142-4a68-4f82-ad6a-4f154fee5265/1773235450374”) — use the ids returned from the search/list tools verbatim.
  • This tool is an MCP App: it ships the player manifest through structuredContent/_meta, so hosts treat it as a UI render rather than a data read.
  • Maximum 20 IDs per call. The UI hydrates the rrweb player on demand for each replay.
  • Set title to a short, human-readable summary of WHY you’re rendering these replays based on the user’s request (3–8 words). This is shown as the heading above the player. Examples: “Recent web sessions for nvidia.com”, “Sessions where users hit checkout errors”, “Top 3 longest sessions yesterday”. Do NOT echo IDs or device info — that lives in the player itself. If the user gave no specific framing, omit title.
EXAMPLES:
  • Single replay: { “projectId”: “678910”, “sessionReplayIds”: [“0c650142-4a68-4f82-ad6a-4f154fee5265/1773235450374”], “title”: “Most recent session for jane@acme.com” }
  • Multiple replays: { “projectId”: “678910”, “sessionReplayIds”: [“abc/111”, “def/222”], “title”: “Sessions where users abandoned checkout” }
  • No framing context: { “projectId”: “678910”, “sessionReplayIds”: [“abc/111”] }
NOTES:
  • The UI plays the replay inline (rrweb-based) with a tree-style event list — the model does NOT need to summarize that data in text.
  • This tool is UI-only. Do not rely on its response for reasoning about the replays.

Input Parameters

string
Short, human-readable heading for the player UI describing WHY these replays are being shown (3–8 words). Examples: “Recent web sessions for nvidia.com”, “Sessions where users hit checkout errors”. Omit if there is no specific framing.
string
required
The Amplitude project ID (appId) as a string (e.g. “12345”, “678910”) the replays belong to
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
array
required
List of session replay IDs in the format “<device_id>/<session_id>”. Returned from the session replay search tools.

Output

string
string
boolean
required
array
string
string
boolean
required
Slug: AMPLITUDE_MCP_RESTORE_EVENT_PROPERTIESRestore event properties that were previously marked as deleted in a project.Each requested property is routed by whether eventType is provided:
  • eventType provided → per-event restore: restore the property on that specific event only.
  • eventType omitted → plan-wide restore: restore the property across the tracking plan.
A single call may mix both — each entry is routed independently. Amplitude-owned properties cannot be restored (they cannot be deleted in the first place).
Note
On the main branch, ingestion for a restored event property resumes immediately. On any other branch, the restore is staged on that branch and only takes effect on ingestion once the branch is merged into main. Always warn the user about this.
Branch targeting
Unless specified, the default branch is used. To apply changes to a non-default branch, pass either branchId or branchName. If the user references a branch by name (e.g. “my-edits-branch”), use branchName. Pass only one.
Permissions
This tool requires the “Update Tracking Plan” permission and may fail with a 403. Don’t pre-warn the user; if it fails, surface the error and note that an admin may need to grant access.
Caveats
Properties that were removed (planned but never ingested at the time of deletion) cannot be restored — they have to be recreated via create_properties. Only properties that were marked as deleted can be restored.

Input Parameters

string
Optional branch ID to target a non-default branch. If omitted, the project’s default branch is used. Mutually exclusive with branchName.
string
required
Project ID to restore event properties in. If the user has not specified a project, prompt the user to decide. Dont decide for them.
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
string
Optional branch name to target a non-default branch (e.g. “my-edits-branch”). If omitted, the project’s default branch is used. Mutually exclusive with branchId.
array
required
Array of event properties to restore

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_RESTORE_USER_PROPERTIESRestore user properties that were previously marked as deleted in a project.
Note
On the main branch, ingestion for a restored user property resumes immediately — incoming data with this property will be accepted again as soon as the restore succeeds. On any other branch, the restore is staged on that branch and only takes effect on ingestion once the branch is merged into main. Always warn the user about this.This tool only restores customer-defined user properties. Amplitude-owned user properties cannot be restored and are always skipped — tell the user if any were requested. When a name exists as both customer and Amplitude, only the customer property is targeted.
Branch targeting
Unless specified, the default branch is used. To apply changes to a non-default branch, pass either branchId or branchName. If the user references a branch by name (e.g. “my-edits-branch”), use branchName. Pass only one.
Permissions
This tool requires the “Update Tracking Plan” permission and may fail with a 403. Don’t pre-warn the user; if it fails, surface the error and note that an admin may need to grant access.
Caveats
Properties that were removed (planned but never ingested at the time of deletion) cannot be restored — they have to be recreated via create_properties. Only properties that were marked as deleted can be restored.

Input Parameters

string
Optional branch ID to target a non-default branch. If omitted, the project’s default branch is used. Mutually exclusive with branchName.
string
required
Project ID to restore user properties in. If the user has not specified a project, prompt the user to decide. Dont decide for them.
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
string
Optional branch name to target a non-default branch (e.g. “my-edits-branch”). If omitted, the project’s default branch is used. Mutually exclusive with branchId.
array
required
Array of user property names to restore

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_SAVE_CHART_EDITSPromote chart edits to saved charts — Save as (new chartId) or Save in place (same chartId).WHEN TO USE:
  • You have a chartEditId from query_amplitude_data and need a permanent chartId
  • The user asked to update an existing chart and keep the same chartId / links
MODES (per item in charts[]):
  • Save as (default): omit chartId → creates a new unpublished chart in personal space
  • Save in place: chartId + expectedLastModified → overwrites that chart (same chartId; updates all dashboards/notebooks referencing it) → ONLY when the user explicitly asked to update the existing chart — never infer from context → Requires a two-step confirm flow (probe, then confirm) — see workflow below
WORKFLOW — save as new:
  1. query_amplitude_data → chartEditId
  2. save_chart_edits({ charts: [{ editId, name }] })
  3. Use returned chartId in dashboards/notebooks
WORKFLOW — update existing chart (two-step — always confirm with the user):
  1. get_amplitude_charts({ chartIds, include: “definition” }) → lastModified
  2. query_amplitude_data({ chart, chartId }) → chartEditId
  3. Probe (no confirm flags): save_chart_edits({ charts: [{ editId, name, chartId, expectedLastModified }] }) → returns overwriteImpact (chart name, URL, dashboards, published status) → present this to the user and ask whether to update in place or save as new
  4. Confirm (only if user explicitly wants in-place): re-call with confirmOverwrite: true → if requiresSharedChartConfirmation, also add confirmSharedImpact: true after user reviews sharedChartImpact
IMPORTANT:
  • Never set confirmOverwrite on the first in-place call — the probe response exists so you can double-check with the user
  • Default to save-as-new unless the user clearly wants the same chartId updated
  • Having chartId from a URL or prior query does NOT mean in-place save is allowed
  • Save-as-new charts default to unpublished in your personal space until a human publishes
  • To collaborate on save-as-new, pass destination {“kind”:“space”,“spaceId”:”…”} using a space id from the user or a shared-space URL. You must have permission to add to that space. To create a space or move already-saved charts, use manage_amp_entities
  • The response echoes where charts landed in savedTo (kind, spaceName, published, notified). Report that to the user rather than assuming the requested destination was used
  • In-place save requires edit access, matching edit provenance, and a fresh expectedLastModified (409 conflict if stale)
  • Prefer save in place when the user explicitly asks to update a chart others reference; use save as for new analyses

Input Parameters

array
required
Chart edits to promote. Omit chartId on each item to save as new. For in-place update: probe with chartId + expectedLastModified (no confirm flags), show impact to the user, then re-call with confirmOverwrite.
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
string
Where to save. Omit for the personal space (previous behavior).

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_SEARCH_AMP_DATA_TAXONOMYSemantic search over a project’s data taxonomy: discover events, properties, and property values by describing what you’re looking for in natural language. Batches many searches into ONE call.INSTRUCTIONS:
  • Use get_amplitude_context FIRST to get the projectId.
  • Batch your entire discovery plan into a single call (one search per concept, up to 16) instead of calling this tool repeatedly.
  • Populate each search based on its kind:
    • “events”: set ‘description’ to one event concept (e.g. “user completes a purchase”).
    • “properties”: set ‘descriptions’ to 1-2 concise phrasings of the property (e.g. [“subscription plan”, “pricing tier”]).
    • “property_values”: set ‘propertyName’ to the EXACT property name (find it with a “properties” search first); set ‘eventType’ when it is an event property.
  • Per-search ‘limit’ is 1-50 hits (default 10). Raise it only for broad concepts where the default may miss the right entity; larger limits cost context.
USING THE RESULTS:
  • Results come back in the same order as the input searches. A failed search returns an ‘error’ entry without failing the others.
  • Hits are semantically ranked; the top hit is not guaranteed to be correct. Use the returned names EXACTLY as spelled — never guess variants.
  • An ‘ambiguity’ block on a result means several hits scored similar confidence — surface those candidates and ask which the user means rather than silently picking one, whenever the choice is load-bearing for the answer.
  • Reason from whatever extra signal a hit carries instead of taking rank 1 on faith: ‘query_volume’ (how often the org actually queries it) is the strongest tiebreaker between similar names, ‘last_seen’ exposes stale or deprecated entities, and a property’s ‘scope’ (event vs. user vs. group) decides where a filter belongs.
  • Report taxonomy quality problems back to the user — near-duplicate events for one concept, several casing variants of the same value, hits with no recent volume, or an ‘ambiguity’ block you had to guess past. Say which one you picked and why. These are fixable data issues, and staying silent means every later answer quietly inherits the same ambiguity.
  • ‘detail’ controls response verbosity — pick the cheapest level that answers the question:
    • “compact” (default): names, descriptions, ranking hints only — cheapest, right for most lookups.
    • “stats”: adds usage/recency metrics per hit. ‘volume’ (+ _30d/_180d) = ingested event counts; ‘query_volume’ = how often the org uses it in charts/queries (the strongest tiebreaker between similar hits); ‘first_seen’/‘last_seen’ = recency (an old last_seen means stale/deprecated — avoid building new analyses on it).
    • “full”: nothing stripped (tags, category, importance scores, all stats) — most tokens, only when you need governance metadata.
  • Need just one or two stat fields? Stay on “compact” and name them in ‘extraFields’ (e.g. [“query_volume”]) — cheaper than “stats” or “full”.
  • Use ‘maxResponseChars’ to hard-cap the payload when context is tight; results are truncated per search so every search stays represented.
EXAMPLES:
  • Ground a funnel: {“projectId”: “123456”, “searches”: [{“kind”: “events”, “description”: “user signs up”}, {“kind”: “events”, “description”: “user completes checkout”}]}
  • Find a property then its values: {“projectId”: “123456”, “searches”: [{“kind”: “properties”, “descriptions”: [“subscription plan”]}]} then {“projectId”: “123456”, “searches”: [{“kind”: “property_values”, “propertyName”: “plan_type”, “eventType”: “Subscription Started”}]}
  • Rank by usage: {“projectId”: “123456”, “searches”: [{“kind”: “events”, “description”: “purchase”}], “detail”: “stats”}
  • Compact but keep one stat: {“projectId”: “123456”, “searches”: [{“kind”: “events”, “description”: “purchase”}], “extraFields”: [“query_volume”]}
  • Tight context budget: {“projectId”: “123456”, “searches”: [{“kind”: “events”, “description”: “purchase”}], “maxResponseChars”: 4000}
NOTES:
  • Hits are already ranked by a hybrid of semantic and keyword search — a single ranking, not two lists to reconcile.
  • ‘source’ says which backend served the batch. ‘langley’ is the normal path. ‘unisearch_fallback’ means that backend was unreachable, so results are keyword-only and lower quality; the response carries a ‘degradedReason’, the fallback cannot serve ‘property_values’ searches, and it ignores ‘detail’ and ‘extraFields’ (always compact hits). Treat a fallback answer as provisional and say so when it materially affects your conclusion.

Input Parameters

string ("compact" | "stats" | "full")
Response verbosity. ‘compact’ (default): names, descriptions, and ranking hints only — right for most lookups. ‘stats’: adds usage/recency metrics per hit (‘volume’, ‘query_volume’, ‘first_seen’, ‘last_seen’ + _30d/_180d windows) — use when ranking similar candidates or checking freshness. ‘full’: nothing stripped (also tags, category, importance scores) — most tokens; only for governance metadata.
array
required
1-16 searches, run in parallel in one call. Batch the whole discovery plan (all event concepts, properties, and value lookups) instead of calling this tool repeatedly.
string
required
Amplitude project ID to search within (required).
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
array
Keep only these normally-stripped hit fields while staying compact — cheaper than detail=‘stats’/‘full’ when you need one or two extras (e.g. [“query_volume”]). Ignored when detail=‘full’.
integer
Hard cap on total response size in characters (0 = uncapped; server default ~90000). When the cap binds, hits are dropped per search so every search stays represented. Set it when your context budget is tight.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_SEARCH_AMP_ENTITIESSearch for dashboards, charts, notebooks, experiments, docs, and other content in Amplitude.INSTRUCTIONS:
  • Use this as your primary tool to discover and explore available analytics content before diving into specific analyses.
  • If you are not sure what to search for, use the default search query.
  • Do not specify appIds/projectIds in the input unless the user explicitly asks to search within a specific app/project.
  • To search Amplitude’s official product documentation (SDK setup guides, API reference, help articles), include ‘AMPLITUDE_DOCS’ in entityTypes. This searches the public docs corpus — NOT your org’s content — and returns doc pages with browsable URLs. Pair it with a natural-language query (e.g. “how to track revenue in the browser SDK”).
DO NOT USE FOR:
  • AI agent results, agent analyses, or agent runs → use ‘get_agent_results’ instead
  • Getting full dashboard definitions with chart details → use ‘get_dashboard’ with the IDs from search results
  • Running queries or analysis → use ‘query_dataset’ or ‘query_charts’
ADDITIONAL INFORMATION:
  • Results are personalized to the user you are making the request on behalf of.
  • Results do not include the full object definition. You will need to use other tools to get the full object definition when needed.
  • Best practice is to query for a single entity type, unless the user’s request is open ended.
  • The response includes an isOfficial flag in contentMeta to identify content that has been marked as official by the organization.

Input Parameters

array
Array of app/project IDs to search within. If not provided, search will be for all apps the user has access to.
array
Filter by owners (array of login IDs)
array
Array of search query strings. If not provided or empty, search will return results based on relevance to the user. Multiple queries are executed in parallel and results are deduplicated using Reciprocal Rank Fusion (RRF).
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
string ("relevance" | "lastModified" | "viewCount" | "name")
Sort order for results
boolean
Filter by official content only
array
Types of entities to search for. Will be converted to camelCase internally for entityRef field access. ‘AMPLITUDE_DOCS’ is special: it searches Amplitude’s public product documentation (via the docs search endpoint) instead of your org’s content, and can be combined with org entity types in a single call.
string
What you are looking for and what you plan to do with the results. Example: “Find the main retention dashboard to answer a question about churn.”
array
Filter out content by specific owners (array of login IDs)
number
Maximum number of results to return per query. Results from multiple queries are deduplicated before being returned. We recommend starting with the default of 50, even if you are using multiple queries.
string ("ASC" | "DESC")
Sort direction for results
Whether to use semantic search in addition to keyword search
boolean
Whether to include archived entities
boolean
Whether to include AI-generated entites
number
Filter to entities last viewed before this epoch timestamp (in seconds). Useful for finding stale or unused content.
number
Filter to entities modified after this epoch timestamp (in seconds). Useful for finding recently active content, e.g. charts modified in the last 7 days.

Output

array
required
Array of search results
number
required
Total number of matching results
Slug: AMPLITUDE_MCP_SHARE_AMP_ENTITIESManage sharing and org invites for Amplitude entities. One outcome-based tool selected by action.ACTIONS:
  • get: list owners/viewers for a CHART / DASHBOARD / NOTEBOOK / COHORT (objectId + objectType).
  • share: add users as viewers (userIds or singular userId). Existing editors are not downgraded.
  • update_role: set one user’s role to CAN_EDIT / CAN_VIEW / NOT_ADDED (userId + shareRole).
  • invite: invite people to the org by email (optional chart access at invite time). Requires org role Manager or higher.
INSTRUCTIONS:
  • Resolve object IDs with search_amp_entities first. Object types are uppercase enums (not “space”).
  • Resolve recipients with get_amp_user_data include=org. Pass returned loginId emails as recipients. If the user did not name a teammate, ask for an email instead of guessing.
  • Prefer update_role with CAN_EDIT to promote a viewer to editor; share only adds viewers.
  • Callers need edit access on the object to share or change roles.
DO NOT USE FOR:
  • Creating a shared space, renaming it, changing space members, or moving content into a space: use manage_amp_entities.
  • Comments on objects: use use_amp_comments.
  • Product analytics end-user lookup: use get_amp_user_data with include id/profile/timeline.

Input Parameters

string ("get" | "share" | "update_role" | "invite")
required
Discriminator: determines which set of parameters applies (get | share | update_role | invite)
array
Email addresses to invite.
string
Singular login ID alias for userIds.
string
Optional notification message.
string ("VIEWER" | "MEMBER" | "MANAGER" | "ORG_ADMIN")
Org role to grant. Defaults to VIEWER.
array
Login IDs (emails) to add as viewers. Resolve with get_amp_user_data include=‘org’.
string
Entity ID. Resolve the entity with search_amp_entities, then pass its id as objectId with objectType CHART, DASHBOARD, NOTEBOOK, or COHORT.
string ("CAN_EDIT" | "CAN_VIEW" | "NOT_ADDED")
CAN_EDIT (editor), CAN_VIEW (viewer), or NOT_ADDED (remove).
string
Optional absolute URL the invite email should send users to.
string ("CHART" | "DASHBOARD" | "NOTEBOOK" | "COHORT")
CHART, DASHBOARD, NOTEBOOK, or COHORT (uppercase).
array
Optional permission group IDs to add invited users to.
object
Optional legacy project role map keyed by project/app ID. Values are VIEWER, MEMBER, MANAGER, or ORG_ADMIN.
boolean
Whether this invite is from a first-time setup flow.
string
Optional RBAC role UUID to assign across assignedProjectIds.
string
Optional default project/app ID for the invited users.
array
Optional project/app IDs to assign when using projectRoleUuid.
array
Optional chart permissions granted when the invite is accepted.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_TRACK_UI_RENDER_RESPONSEInternal telemetry tool used by MCP UI components to report render latency and errors.NOT FOR DIRECT MODEL USE.

Input Parameters

string
Chart ID or edit ID associated with the render
string
Chart definition type (e.g., eventsSegmentation, funnel, retention)
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
string
Amplitude project name
string
required
UI component identifier (e.g., amplitude-chart)
string
required
Render status: “success” or error message
number
required
UI render latency in milliseconds

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_UPDATE_PROPERTIESUpdate property description, isOfficial, category, and/or name in a project’s tracking plan. Use propertyType to select which kind of properties to update.This tool CANNOT be used to update property visibility or type. It can also NOT be used to set event properties to required.PROPERTY TYPES:INSTRUCTIONS:
  • Use get_properties first to verify property names and status before updating.
  • Call this tool only after the user has explicitly confirmed the properties to change and the exact new values.
  • Do not auto-apply speculative or inferred changes.
  • If the user has not specified a project, prompt them to decide. Don’t decide for them.
  • This tool requires the “Update Tracking Plan” permission. If it fails with 403, note that an admin may need to grant access.
  • Make sure you have used the get_workspace_context tool to get information on workspace settings and environments for specified projectId. If there is more than one environment in the workspace, warn the user that the change will apply across multiple environments. If the workspace has main branch protected (indicated by approvalWF being “Required”), let the user know that changes cannot be made on the default branch and they will have to first create a new branch and make changes on that.
  • This tool only updates properties that are already in the tracking plan (status: planned, live, blocked). Unexpected properties (auto-detected from ingested data, isPlanned: false) are skipped. To edit an unexpected property’s metadata, first add it to the plan with create_properties by setting properties[].isUnexpected: true on that item, then call update_properties.
WHEN UPDATING EVENT PROPERTIES:
  • Do not try to update the properties globally if it failed on the event-scoped update, or vice-versa. Always confirm with the user whether the event property should be updated on a global or event-scoped basis.
WHEN UPDATING USER PROPERTIES:
  • Remove the gp: prefix, if present, from user property names when requesting updates with this tool.
EXAMPLES:
  • Event properties (global): { “propertyType”: “event”, “projectId”: “123”, “metadataScope”: “global”, “descriptions”: { “revenue”: “USD amount” } }
  • Event properties (event-scoped): { “propertyType”: “event”, “projectId”: “123”, “metadataScope”: “event”, “eventType”: “Purchase”, “descriptions”: { “line_items”: “JSON array” } }
  • User properties: { “propertyType”: “user”, “projectId”: “123”, “descriptions”: { “plan_tier”: “Customer subscription tier” } }

Input Parameters

string
Optional branch ID to target a non-default branch. If omitted, the project’s default branch is used. Mutually exclusive with branchName.
object
Map of current property names to new names (property_name -> new_name). Global-only: pass with metadataScope “global”. Only valid for planned properties.
string
Required when metadataScope is “event”: the event type name whose properties to update. Ignored when metadataScope is “global”.
string
required
Project ID. If the user has not specified a project, prompt the user to decide. Dont decide for them.
string
Optional branch name to target a non-default branch (e.g. “my-edits-branch”). If omitted, the project’s default branch is used. Mutually exclusive with branchId.
object
Map of property names to category names (property_name -> category). Pass an empty string to clear the category.
object
Map of property names to official status (property_name -> isOfficial). Global-only: pass with metadataScope “global”.
object
Map of property names to their descriptions (property_name -> description)
string ("event" | "user")
required
Discriminator: determines which set of parameters applies (event | user)
string ("global" | "event")
Whether updates apply to global (plan-wide) event properties or to properties local to a single event type. Use “event” only when the user wants changes scoped to one event; use “global” for shared definitions. When “event”, eventType is required.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_USE_AMP_AI_VISIBILITYUse Amplitude AI Visibility.Set action:
  • list_brands: list tracked brands and get orgBrandId. Start here when the brand is unknown.
  • read: read a brand using orgBrandId plus view: scores, scores_over_time, reports, topics, prompts, prompt_responses, competitors, aliases, models, pages, sentiment, or sources.
  • update_page_view_config: set a project’s page-view event, referrer property, and page-URL property.

Input Parameters

string ("scores" | "scores_over_time" | "reports" | "topics" | "prompts" | "prompt_responses" | "competitors" | "aliases" | "models" | "pages" | "sentiment" | "sources")
Discriminator: determines which set of parameters applies (scores | scores_over_time | reports | topics | prompts | prompt_responses | competitors | aliases | models | pages | sentiment | sources)
number
Maximum rows to return (default: 100, max: 100)
string ("read" | "list_brands" | "update_page_view_config")
required
Discriminator: determines which set of parameters applies (read | list_brands | update_page_view_config)
string
Pagination cursor returned by the previous call
string ("visibility" | "citationRate")
Metric to trend over time
string ("responseCount" | "visibility" | "avgRank" | "relevancy" | "citationCount" | "promptCount" | "topicName" | "prompt" | "brandName" | "url" | "brandMentionPercent" | "domain")
Optional sort field
number
Optional brand ID. Takes precedence over brandName.
string
Optional end date in yyyy-mm-dd
string ("score" | "topic" | "competitor" | "citationDomain")
Optional grouping for the timeline
number
Optional topic ID
number
Optional prompt ID
number
Optional report ID. Omit it to use the latest report.
string
Optional brand name when brandId is not provided
integer
Maximum nested pages to return per source (default: 20, max: 100)
string
Project ID whose AI Visibility page view config should update.
array
Optional prompt IDs
string
Why this call is needed.
string ("positive" | "neutral" | "negative" | "both")
Optional sentiment filter
string
Optional start date in yyyy-mm-dd
number
Org brand ID to score within
integer
Optional max number of series to return (default: 20)
integer
Maximum sentiment themes to return (default: 100, max: 100)
array
Optional model family filters
string
Optional keyword match against a citation domain, URL, or title
number
Optional brand ID to exclude
string
Optional sentiment theme filter
number
Optional brand ID that cited sources must mention
string
Event property name on the page view event that contains the page URL.
integer
Maximum response characters to return (default: 1000, max: 5000)
string
Event property name on the page view event that contains the referrer.
string
Optional brand name that cited sources must mention when mentionsBrandId is not provided
string
Event type/name that represents a website page view.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_USE_AMP_COMMENTSRead and add plain-text comments on Amplitude charts, dashboards, and notebooks. One outcome-based tool selected by action.ACTIONS:
  • get: read comments for source + id. Dashboards/notebooks also roll up comments from charts inside them.
  • add: leave a plain-text comment (content). Prefixed with the AI client name automatically.
INSTRUCTIONS:
  • source, id, and projectId are required on every call. Resolve the object with search_amp_entities, then pass its id as id with source CHART, DASHBOARD, or NOTEBOOK. projectId comes from get_amplitude_context.
  • Call get before add to avoid duplicates.
  • Comments are plain text only (no mentions/reactions).
DO NOT USE FOR:
  • Opportunity / Wave comments: use opportunity tools.
  • Sharing access: use share_amp_entities.

Input Parameters

string
required
Chart, dashboard, or notebook ID from search_amp_entities.
string ("get" | "add")
required
Discriminator: determines which set of parameters applies (get | add)
string ("CHART" | "DASHBOARD" | "NOTEBOOK")
required
Object type: CHART, DASHBOARD, NOTEBOOK.
string
Plain-text comment body.
string
required
Amplitude project ID from get_amplitude_context.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_USE_AMP_DASHBOARDSRead and manage Amplitude dashboards. One outcome-based tool selected by action.ACTIONS:
  • get: read up to three dashboards by dashboardIds. Resolve IDs with search_amp_entities (entityTypes: DASHBOARD).
  • create: create a dashboard. Row items accept saved chart IDs and temporary chart edit IDs interchangeably in chartId; edit IDs are saved as permanent charts automatically before the dashboard is created. Optionally pass chartEdits to control the saved name and description of each edit. If the events the user asked about are not instrumented, explain the gap and confirm before building a proxy dashboard from substitute events. Never pass placeholder or invented chart IDs.
  • edit: update dashboard metadata or layout. Read the dashboard first and pass its lastModified as expectedLastModified. Rows in set_rows / update_row / insert_row accept saved chart IDs and temporary chart edit IDs interchangeably, same as create — use this to add a freshly queried chart to an existing dashboard.
  • replace_properties: discover or replace chart properties across a dashboard.
  • subscribe / edit_subscription: create or edit a recurring email, Slack, or Teams dashboard delivery.
SUBSCRIPTIONS:
  • Use top-level notificationType, sendWeek, sendDay, and sendHourUtc; do not send nested JSON strings.
  • For email, email defaults to the current user; never ask the user for their own email address. For Slack or Teams, provide recipientType and recipientId; Teams also needs recipientTeamId.
  • If the user has not given a delivery channel or cadence, ask instead of assuming defaults.
DO NOT USE FOR:
  • Finding dashboards by name: use search.
  • Creating a shared space, changing space members, or moving an existing dashboard into a space: use manage_amp_entities.
  • Creating or querying chart data: use the chart tools.

Input Parameters

string
One layout operation from the dashboard returned by get.
string
Dashboard name.
array
Dashboard layout rows. Item chartId accepts a saved chart ID or a temporary chart edit ID; edit IDs are saved automatically.
string
Email recipient. Defaults to the current user’s email when omitted.
string ("get" | "create" | "edit" | "replace_properties" | "subscribe" | "edit_subscription")
required
Discriminator: determines which set of parameters applies (get | create | edit | replace_properties | subscribe | edit_subscription)
boolean
Preview changes without saving.
string ("every" | "monday" | "tuesday" | "wednesday" | "thursday" | "friday" | "saturday" | "sunday")
Delivery weekday.
object
Dashboard metadata updates.
string ("every" | "first" | "second" | "third" | "last")
Delivery cadence week.
boolean
Attach CSV to email deliveries.
array
Optional names and descriptions for chart edits referenced in rows. Without an entry, an edit referenced in rows is saved using the name from its definition.
object
Optional display configuration keyed by saved chart ID.
string
Dashboard ID. Resolve dashboard IDs with search_amp_entities (entityTypes: [‘DASHBOARD’]).
string
Dashboard description.
string
Where to save. Omit for the personal space (previous behavior).
string
Slack or Teams recipient ID.
integer
UTC delivery hour.
array
Dashboard IDs to read (array of 1 to 3 strings, e.g. [‘abc1234’]). Resolve with search_amp_entities (entityTypes: [‘DASHBOARD’]).
array
Array of replacement definitions from discovery mode.
string ("channel" | "user")
Slack or Teams recipient type.
string
Subscription ID.
string
Teams team ID.
string ("email" | "slack" | "teams")
Delivery channel.
integer
lastModified returned by get. Read the dashboard first.
boolean
Confirm updates to charts used elsewhere.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_USE_AMP_EXPERIMENTSUnified entry point for experiments: read, analyze, create, and set metrics. Replaces get_experiments, query_experiment, create_experiment, and update_experiment.ACTIONS:
  • get (default): fetch experiments by ids.
  • analyze: run experiment analysis for id (same as query_experiment). Omit metricIds unless the user asks for specific/secondary metrics.
  • create: create an experiment across projects (same fields as create_experiment).
  • update: replace experiment metrics (experimentId + metrics). For name/variants/testers/deployments/links on an experiment, use use_amp_flags action update — experiments are flags.
INSTRUCTIONS:
  • Resolve experiment IDs with search (entityTypes: [“EXPERIMENT”]) before get/analyze/update.
  • Resolve deployment IDs with use_amp_flags action list_deployments before passing deploymentIds.
  • Resolve metric IDs with use_amplitude_metrics before passing metrics or projectMetrics.
  • On create, strongly prefer setting proxyExposureEvent to the event where users hit the tested surface. Without it, pre-launch planning falls back to Any Active Event and can wildly overstate the required duration.
  • ALWAYS reference queried experiments by their Amplitude link in analyses.
  • Metrics for update fully replace the existing set; create metrics first via use_amplitude_metrics.
DO NOT USE FOR:
  • Feature flags → use_amp_flags.
  • Metric definitions → use_amplitude_metrics.
  • Chart / dataset queries → chart query tools.

Input Parameters

string
analyze: experiment ID to query.
array
get: experiment IDs to retrieve.
string
create: unique experiment key.
string
create: human-readable experiment name.
Links to associate with the experiment (e.g., design docs, tickets, PRs). Each link requires a url and title.
string ("get" | "analyze" | "create" | "update")
Experiment operation: ‘get’ | ‘analyze’ | ‘create’ | ‘update’. Defaults to get.
array
analyze: optional metric filters.
array
analyze: optional group-by, e.g. [{“type”:“user”,“value”:“device type”,“group_type”:“User”}].
array
update: full replacement metric set. Empty array clears metrics.
array
create: variants (defaults to control + treatment if omitted).
array
analyze: ONLY if the user explicitly requests specific or all metrics. Omit for primary/recommended metric only.
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
array
create: project IDs (prompt the user if unspecified).
string
Experiment description explaining what is being tested
string ("user_id" | "device_id" | "amplitude_id")
Property used to bucket users into variants. One of “user_id”, “device_id”, “amplitude_id”. Omit unless the user asks — Amplitude then picks the right default (“amplitude_id” for remote, “device_id” for local). Group-level bucketing (group_id/group_name) requires bucketingGroupType and is not supported via MCP yet.
string
update: experiment ID whose metrics to replace.
array
create: deployment (API key) IDs to associate. List available IDs with use_amp_flags action list_deployments. Single-project creates only.
string ("local" | "remote")
Defaults to “remote”. Set to “local” if specified by the user
array
Metrics to attach to the experiment for analysis
object
Proxy exposure event used for pre-launch planning (duration estimator, control mean, sample size). Set it to the event where users first encounter the tested surface (e.g. the screen-viewed event for the screen being changed). Strongly recommended for funnel/conversion metrics: without it, planning falls back to Any Active Event and denominates the baseline against all active users. Does not change the running experiment’s exposure event.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_USE_AMP_FLAGSUnified entry point for feature flags and deployments. Replaces get_flags, create_flags, update_flag, and get_deployments.ACTIONS:
  • get (default): fetch flags by flagIds (numeric IDs or flag keys).
  • create: create one or more flags (flags array — same shape as create_flags). Supports evaluationMode, bucketingKey, percentage, rolloutWeights, targetSegments, testers, deploymentIds.
  • update: update a flag or experiment (flagId + only the fields to change). Supports flagConfig (name/description/enabled), evaluationMode, bucketingKey, percentage, rolloutWeights, targetSegments, variants, testers, deployments, links. Experiments are flags — use this for shell/rollout changes on experiments too.
  • list_deployments: list deployments (API keys) for the current project. Deployments are shared by flags and experiments — this is the only place to list them.
INSTRUCTIONS:
  • Resolve IDs with search (entityTypes: [“FLAG”] or [“EXPERIMENT”]) before get/update.
  • Use list_deployments before create/update when associating deployment IDs.
  • Only include update sections you intend to change.
  • evaluationMode is “local” or “remote”; bucketingKey is “user_id”, “device_id”, or “amplitude_id”.
  • For update rollout: percentage / rolloutWeights apply to “All Other Users”; omit targetSegments to keep existing conditional segments, pass [] to clear them, or pass a full array to replace them.
  • To GA a flag: {"action":"update","flagId":"...","percentage":100,"rolloutWeights":{"on":1}} (optionally "targetSegments":[] to drop prior segments).
DO NOT USE FOR:
  • Experiment analysis → use_amp_experiments action analyze.
  • Attaching experiment metrics → use_amp_experiments action update.
  • Creating experiments → use_amp_experiments action create.

Input Parameters

array
create: flags to create (same shape as create_flags).
Link operations
string ("get" | "create" | "update" | "list_deployments")
Flag operation: ‘get’ | ‘create’ | ‘update’ | ‘list_deployments’. Defaults to get.
string
update: ID of the flag or experiment to update.
array
get: flag IDs or keys to retrieve.
object
Tester operations
object
Variant operations
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
object
Flag configuration updates
number
Default rollout percentage for “All Other Users” (0-100). Set to 100 to enable for everyone.
object
Deployment operations
string
Property used to bucket users into variants. One of “user_id”, “device_id”, “amplitude_id”. Group-level bucketing (group_id/group_name) requires bucketingGroupType and is not supported via MCP yet.
string
Evaluation mode: “local” or “remote”.
object
Default variant weight distribution for “All Other Users” (e.g., {“on”: 1} for 100% to “on” variant).
array
Target segments for conditional rollout. Replaces existing conditional segments when provided; omit to keep them; pass [] to clear them.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_USE_AMP_GUIDES_SURVEYSList Guides and Surveys or get one by ID. Use action: "list" for filtered discovery and rollout summaries; use action: "get" for full content, targeting, variants, steps, and rollout details. Both require projectId; get also requires nudgeId.

Input Parameters

integer
Maximum number of items to return per page. Defaults to 50, capped at 200.
array
Types to include. Defaults to both Guides and Surveys.
string ("list" | "get")
required
Discriminator: determines which set of parameters applies (list | get)
string
Opaque cursor from a previous response’s nextCursor. Omit for the first page.
string
ID of the nudge (guide or survey) to retrieve.
string ("web" | "ios" | "android" | "react-native" | "desktop" | "flutter")
Filter by target platform. ‘web’ also matches rows with no platform set.
string
Filter by the email (or login id) of the user who created the guide/survey. Exact match against the stored createdBy value.
string
required
Project ID (appId) to list Guides and Surveys for. Prompt the user if not specified.
string
Why this Guides and Surveys read is needed.
string
ISO 8601 lower bound on created timestamp (inclusive).
string
ISO 8601 upper bound on created timestamp (inclusive).
boolean
Include archived (soft-deleted) items. Defaults to false.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_USE_AMPLITUDE_AI_FEEDBACKRead Amplitude AI Feedback (customer VoC) for a project — surveys, support tickets, app reviews, and grouped themes.This is CUSTOMER product feedback (what users said in connected sources). NOT for:
  • AI/LLM agent session quality, transcripts, or agent analytics → use get_amplitude_agent_analytics_info
  • Reporting that you (the agent) are stuck → use report_agent_feedback (requires user approval)
Set facet to choose what to read:
  • sources → connected feedback integrations + sourceIds (call first when you need sourceIds for filters)
  • comments → raw feedback comments with search, categories, pagination
  • insights → grouped themes (requests, complaints, loved features, …) sorted by popularity
  • mentions → drill into comments behind ONE insightId or trendId (do not call for every insight)
  • trends → saved themes tracked over time
TYPICAL WORKFLOWS:
  1. Bootstrap: facet=sources → facet=comments or facet=insights
  2. Themes: facet=insights → facet=mentions with insightId when user asks for examples
  3. Tracked themes: facet=trends → facet=mentions with trendId
EXAMPLES:
  • Connected sources: {“facet”: “sources”, “projectId”: “123456”}
  • Complaints this month: {“facet”: “insights”, “projectId”: “123456”, “types”: [“complaint”], “dateStart”: “2026-06-01”, “dateEnd”: “2026-06-30”}
  • What are customers saying about pricing: {“facet”: “comments”, “projectId”: “123456”, “search”: [“pricing”, “price”]}
  • Show comments behind insight 42: {“facet”: “mentions”, “projectId”: “123456”, “insightId”: 42}

Input Parameters

integer
Optional page number for pagination (default: 1)
string
Optional Amplitude user ID to filter insights by specific amplitude user
string ("sources" | "comments" | "insights" | "mentions" | "trends")
required
Discriminator: determines which set of parameters applies (sources | comments | insights | mentions | trends)
array
Array of insight types to filter by
Search term(s) to filter comments by body text. Multiple terms are OR-matched. Pass granular synonyms for better recall.
string
Optional end date for filtering comments (ISO date string)
number
The trend ID to retrieve mentions for (required if insightId not provided)
string
Optional category filter (e.g., request, complaint, lovedFeature). Legacy values (bug, painPoint, takeaway) are still accepted for backwards compatibility.
integer
Optional page size for pagination (default: 50, max: 50)
number
Source ID to filter mentions by - should match get_feedback_insights query
string
Optional start date for filtering comments (ISO date string)
number
The insight ID to retrieve mentions for (required if trendId not provided)
string
required
The project ID (appId) to get feedback sources for
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
array
Optional source IDs to scope comments to specific feedback sources (default: all sources). Get IDs from get_feedback_sources.
array
Optional insight categories (e.g. [“complaint”,“request”]). Keeps only comments with an extracted point in one of these categories. Pass all categories to keep only actionable comments (drop noise with no insights).
array
Optional label filters as “labelKey:valueKey” tokens (e.g. [“product_area:onboarding_flow”, “severity:high”]). Multiple values for the same labelKey are OR-matched; different labelKeys are AND-matched. Use the value keys returned in a comment’s labels field, not display names.
string ("asc" | "desc")
Optional sort direction by mention count (default: desc)

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_USE_AMPLITUDE_CHART_MONITORSRead and manage chart alert monitors. One tool with eight actions selected by action (default get_alerts).ACTIONS:
  • get_alerts (default) → recent alert anomalies for a chart (chartId) or project (projectId).
  • list → custom chart monitors you created or are subscribed to (email / Slack / Teams). Includes ones others created if you are a recipient. Chart name + short summary + alertsLast30Days. Optional projectId. Does not need chartId.
  • get_config → a chart’s monitor configuration + subscribers when chartId is set. Omit chartId to list (same as list). Charts with no monitor return hasMonitor=false — then use create.
  • create → add a monitor on a chart that does not have one. Requires chartId. Defaults to smart anomaly detection (99% CI, above or below) and emails the current user.
  • history → audit trail of monitor config changes (who changed what, when). Requires monitorId or chartId. Not alert firings — use get_alerts for those.
  • subscribe / unsubscribe → add/remove an alert subscription (email for the current user, or a Slack/Teams channel). Requires monitorId and deliveryMethod.
  • update → enable or disable a monitor. Requires monitorId and enabled.
INSTRUCTIONS:
  • If the user asks what chart alerts or monitors they have, call list (or get_config without chartId). That returns monitors they created or are subscribed to — not every monitor in the org.
  • If get_config returns hasMonitor=false, call create with that chartId instead of telling the user to use the Amplitude UI.
  • Resolve a monitorId first with get_config (from a chartId) before subscribe / unsubscribe / update. For history, you may pass chartId directly instead of monitorId.
  • For get_alerts and list, projectId is optional when you have access to exactly one project; otherwise provide it to scope. Pass chartId to scope get_alerts to one chart.
  • Email subscriptions only manage the current user; for Slack/Teams pass deliveryChannel (and deliveryWorkspaceId when needed).
DO NOT USE FOR:
  • Reading chart data → use ‘get_amplitude_charts’ (include=‘data’) or ‘query_dataset’.

Input Parameters

string
create: optional monitor name. Defaults to the chart name.
integer
get_alerts: max alerts (default 20). list: max monitors per group (default 50). 1-100.
string ("get_alerts" | "list" | "get_config" | "create" | "history" | "subscribe" | "unsubscribe" | "update")
What to do: ‘get_alerts’ (default), ‘list’, ‘get_config’, ‘create’, ‘history’, ‘subscribe’, ‘unsubscribe’, or ‘update’.
string
Chart ID. Scopes get_alerts to one chart; required for create; for get_config, omit to list monitors. Optional for history (resolves monitorId).
boolean
update: true enables the monitor, false disables it.
string ("daily" | "hourly")
create: ‘daily’ (default) or ‘hourly’.
string
history / subscribe / unsubscribe / update: the monitor to act on. For history, chartId is an alternative to monitorId.
string
Project ID. Scopes get_alerts and list. Optional with single-project access.
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
array
create: alert conditions. Defaults to smart anomaly detection at 99% CI, above or below.
boolean
get_alerts: return only alerts not yet marked seen.
string ("email" | "slack" | "teams")
subscribe / unsubscribe: delivery method (email, slack, or teams).
string
subscribe / unsubscribe: Slack channel ID or Teams conversation ID (omit for email).
array
create: emails to notify. Defaults to the current user. Pass [] for none.
string
subscribe / unsubscribe: optional workspace/tenant context for Slack or Teams.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_USE_AMPLITUDE_COHORTSWork with Amplitude cohorts end to end. One tool with eleven actions selected by action (default list).DISCOVER & READ:
  • list (default) → browse/search the project’s cohorts by name (projectId required, optional query). Use this FIRST when you don’t have cohort ids — never guess or use placeholder ids.
  • get → full cohort definitions/metadata for known ids (cohortIds, max 50).
  • find → ad-hoc audience: individual users who performed an event (projectId; optional event, defaults to any active user; optional timeRange, limit). Returns user records + session replays, without creating a cohort.
  • membership → is a user in these cohorts? (cohortIds max 5 + one of amplitudeId / userId / email).
CREATE:
  • create → save a new cohort (projectId, name, definition). Definition uses andClauses/orClauses condition sets.
SYNC & EXPORT:
  • get_destinations → configured sync destinations for a project (projectId). Call BEFORE sync.
  • get_syncs → sync jobs + status (projectId for the whole project, or cohortIds).
  • get_history → execution logs for one cohort’s syncs (cohortId, projectId, target).
  • sync → trigger a one-time sync now (cohortId + targetId from get_destinations; partner too for classic integrations). Two-step confirm: first call returns a preview, re-call with confirmed: true. Cohorts under 10k sync synchronously; 10k+ return submitted — tell the user it was queued, then poll get_history.
  • export_submit → start a CSV export of members (cohortId), returns exportRequestId.
  • export_download → poll export status / fetch CSV url (cohortId + exportRequestId).
INSTRUCTIONS:
  • Resolve cohort ids with list before get/membership/sync/export_*.
  • For sync: always call get_destinations first — a targetId is only unique within a partner.
  • membership accepts userId/email directly (resolved to an amplitudeId automatically, cached).
DO NOT USE FOR:
  • Aggregate counts/trends over a cohort → use ‘query_dataset’ with a cohort segment filter.
  • One user’s profile or event timeline → use ‘get_amp_user_data’.

Input Parameters

string
create: name of the new cohort.
string
membership: email to check (resolved to an amplitudeId automatically).
object
find: event the users performed (defaults to “_active” — any active user). Call get_events first to confirm exact event names.
integer
list: max cohorts to return (default 20). find: max users to return (default 10).
string
list: text to match against cohort names (omit to browse by recency).
string ("find" | "list" | "get" | "membership" | "create" | "get_destinations" | "get_syncs" | "get_history" | "sync" | "export_submit" | "export_download")
What to do: ‘list’ (default), ‘get’, ‘find’, ‘membership’, ‘create’, ‘get_destinations’, ‘get_syncs’, ‘get_history’, ‘sync’, ‘export_submit’, or ‘export_download’.
string
get_history: sync destination to read logs for (e.g. “braze”, “s3”, “salesforce”).
string
membership: user id to check (resolved to an amplitudeId automatically).
string
sync: partner/integration type of a classic destination (e.g. “braze”), from get_destinations. Omit for Connector Manager destinations.
string
Single cohort ID for sync / get_history / export_submit / export_download.
integer
get_history: results per page (default 20, max 100).
array
export_submit: specific user properties to include.
string
sync: destination target from get_destinations (with partner for classic integrations; alone for Connector Manager destinations). get_history: optional instance filter.
array
Cohort IDs for get (max 50), membership (max 5), or to scope get_syncs (max 10). Resolve real ids via list first — never pass placeholders.
boolean
sync: set true only after the user reviewed the confirmation preview returned by the first call.
boolean
get_history: only return failed sync executions.
string
Project/app ID. Required for list / find / create / get_destinations; required for get_syncs when cohortIds is omitted; required for get_history.
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
object
find: time window (defaults to Last 30 Days).
string ("redshift" | "clause_based_fine_grained_time" | "cluster" | "funnels" | "sessions")
create: computation engine (default “redshift” — only set for specialized cohort types).
object
create: cohort definition (andClauses of condition sets, countGroup, version).
integer
get_history: page number (default 1).
string
membership: Amplitude ID of the user to check.
string
create: owner of the cohort (defaults to the current user).
string
export_download: the id returned by export_submit.
boolean
export_submit: include user properties in the CSV (may slow the export).

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_USE_AMPLITUDE_DATA_CONNECTIONSUnified entry point for everything to do with a project’s data connections — ingestion sources, import/export job history, Snowflake credentials, live Snowflake warehouse browsing, and Amplitude import-config recommendations. Replaces 10 previously separate tools (get_data_ingestion_sources, get_data_source_details, get_data_warehouse_jobs, get_data_warehouse_health, get_falcon_integrations, get_snowflake_warehouse_databases/_schemas/_tables/_columns/_rows, recommend_falcon_import_config).ROUTES (action=‘read’, selected by view):
  • omit dataSourceId and view → list every configured source for the project (‘data_connections.list (get_data_ingestion_sources)’). Start here.
  • dataSourceId set, view omitted or ‘summary’ → detail for that one source (‘data_connections.summary (get_data_source_details)’).
  • view: 'connections' → list the project’s Snowflake credentials/integrations (‘data_connections.connections (get_falcon_integrations)’). Use this to find an integrationId for the browsing views below.
  • view: 'jobs' → import/export batch job history for one connection (‘data_connections.jobs (get_data_warehouse_jobs)’). Requires dataSourceId in vacuum:{id} / falcon:{id} / gyrfalcon:{id} form (as returned by the list route; gyrfalcon: answers supported: false — no per-run history yet, not “never ran”); auto-resolved when the project has exactly one configured source.
  • view: 'health' → project-wide health of EVERY import and export connection in one call (‘data_connections.health (get_data_warehouse_health)’): which are failing, degraded, running, healthy, idle or unknown, worst first, with last-success age per connection. No dataSourceId. Optional direction (imports or exports only), since (failure-counting window, default 7 days) and maxConnections. Use this instead of listing sources and destinations and then calling ‘jobs’ per connection.
  • view: 'databases' | 'schemas' | 'tables' | 'columns' | 'rows' → live Snowflake warehouse browsing, one drill-down level at a time (‘data_connections.databases (get_snowflake_warehouse_databases)’ etc.). Needs a connection reference (integrationId or sourceDestinationId) — auto-resolved via ‘connections’ when the project has exactly one Snowflake credential. Snowflake-only today; other warehouse types will extend this enum, not rename the tool.
ROUTES (action=‘recommend_import’):
  • Generates a heuristic Amplitude import config + ready-to-run SQL for one or more warehouse tables (‘data_connections.recommend_import (recommend_falcon_import_config)’). This is the ONLY correct way to produce warehouse-import SQL — never hand-write it.
WHEN TO USE:
  • Anything about “what’s sending data into my project”, “did this import/export succeed”, “are any of my pipelines failing / is anything broken or stale” (that is ‘health’), “what Snowflake credentials/connections exist”, “what’s in my Snowflake warehouse”, or “generate an import config/SQL for this table”.
INSTRUCTIONS:
  • Always provide projectId.
  • Prefer omitting dataSourceId/connection refs on the first call in a session — this tool auto-resolves the connection when there’s exactly one, and only asks you to disambiguate when there are several.
  • For ‘jobs’, pass the prefixed dataSourceId from the list route (e.g. vacuum:42, falcon:abc-123, gyrfalcon:c-9) — not a bare numeric id.
  • For ‘health’, omit dataSourceId; it inspects every connection. If the response says truncated: true, raise maxConnections or narrow with direction before concluding the project is healthy.
  • For browsing views, drill down one level per call: ‘databases’ → ‘schemas’ (needs database) → ‘tables’ (needs database+schema) → ‘columns’/‘rows’ (needs a read-only sql SELECT).
  • For ‘recommend_import’, provide tables (fully qualified dotted names) and either sourceDestinationId (preferred — lets Amplitude introspect the warehouse; NOT the same id as integrationId from ‘connections’) or warehouseKind for a dry run with caller-supplied columns/sampleRows.
EXAMPLES:
  • List sources: { “projectId”: “123456” }
  • Job history: { “projectId”: “123456”, “view”: “jobs”, “dataSourceId”: “vacuum:42” }
  • Health of every connection: { “projectId”: “123456”, “view”: “health” }
  • Browse tables: { “projectId”: “123456”, “view”: “tables”, “database”: “ANALYTICS”, “schema”: “PUBLIC” }
  • Recommend import: { “projectId”: “123456”, “action”: “recommend_import”, “sourceDestinationId”: “789”, “tables”: [{“fullyQualifiedName”: “ANALYTICS.PUBLIC.EVENTS”}] }
NOTES:
  • Sensitive credential fields are never returned; empty strings stand in for secrets.
  • Databricks/BigQuery/GA4 warehouse-native browsing isn’t implemented yet — only classic Snowflake. recommend_import returns a WAREHOUSE_NOT_SUPPORTED_YET error for other kinds; surface it without retrying.

Input Parameters

string
‘columns’/‘rows’ views. A read-only Snowflake SELECT statement (e.g. SELECT * FROM DB.SCHEMA.TABLE).
string ("summary" | "connections" | "jobs" | "health" | "databases" | "schemas" | "tables" | "columns" | "rows")
Which read outcome to fetch. Omit for the list/summary route. ‘connections’ lists Snowflake credentials. ‘jobs’ is batch job history for ONE connection; ‘health’ is a project-wide status report across every connection. ‘databases’|‘schemas’|‘tables’|‘columns’|‘rows’ drill into a live Snowflake connection one level at a time.
integer
‘jobs’ view only. Max jobs per page (1-100, default 25).
string
‘jobs’ and ‘health’ views. Inclusive lower bound on job time, as a date or ISO-8601 date-time. A value with no timezone is read as UTC. On ‘health’ it scopes the failure-counting window.
string
‘jobs’ view only. Exclusive upper bound on job time, same formats as since.
string ("read" | "recommend_import")
Defaults to ‘read’ (use view to pick the outcome). Set to ‘recommend_import’ to generate an Amplitude import config + SQL for warehouse tables — ignores view.
string
‘jobs’ view only. Opaque pagination token from a previous call.
string
‘tables’ view. The Snowflake schema to list tables for.
string ("SUCCESS" | "FAILURE" | "IN_PROGRESS" | "WAITING" | "COMPLETED_WITH_ERRORS" | "CANCELLED" | "ALL")
‘jobs’ view only. Filter by unified job status. Defaults to no filter.
array
One or more tables to generate import recommendations for.
string ("automatic" | "manual")
‘jobs’ view, export connections only. Defaults to ‘automatic’ (scheduled). Use ‘manual’ for manual/backfill export jobs.
integer
‘rows’ view only. Max sample rows to fetch (default 10 if omitted), capped at 1000.
object
Optional tuning for sampling, ranking, and diagnostics.
string
‘schemas’/‘tables’ views. The Snowflake database to drill into.
string ("import" | "export")
‘jobs’ and ‘health’ views. On ‘jobs’ it overrides the inferred connection direction; only pass it if the inference is wrong. On ‘health’ it restricts the report to import sources or export destinations.
string
required
The project ID (appId) to operate on. Call get_amplitude_context first if unknown — never guess.
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
string
The data source id. Omit for the list route. For ‘summary’ pass the id from the list route (e.g. library:ios-swift, vacuum:42). For ‘jobs’ pass the prefixed id (vacuum:{id} or falcon:{id}).
string
Browsing views ONLY. A Snowflake credential id from the ‘connections’ view. Provide this or sourceDestinationId — auto-resolved when the project has exactly one. NOT valid for recommend_import (use sourceDestinationId there instead).
string ("SNOWFLAKE_IMPORT" | "BIGQUERY_IMPORT" | "DATABRICKS_IMPORT" | "GA4_IMPORT")
Warehouse kind, required only when no connection exists yet (dry run from caller-supplied inputs). Provide exactly one of sourceDestinationId or warehouseKind. Only SNOWFLAKE_IMPORT is implemented today.
integer
‘health’ view only. Max connections to inspect in one call (1-50, default 25).
string
Browsing views: an import source/destination id identifying the Snowflake connection, or integrationId may be used instead. recommend_import: REQUIRED connection identifier — integrationId is not accepted here, they are different ids.
boolean
‘schemas’ view only. Include account-metadata schemas such as INFORMATION_SCHEMA. Off by default.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_USE_AMPLITUDE_METRICSUnified entry point for metric definitions, goals, and goal alerts in a project. Replaces get_metrics, create_metric, update_metric, delete_metric, get_metric_goals, the five goal write tools, and the four goal-alert CRUD tools.WHEN TO USE:
  • Anything about defining metrics, setting targets on metrics, listing goals/pacing, or configuring goal alerts.
  • NOT for querying metric values over time — use query_metric or query_dataset instead.
INSTRUCTIONS:
  • Select the operation with action.
  • Metric defs: resolve metricIds with search first; create_metric needs projectId, name, and metricType plus type-specific fields (same rules as the legacy create_metric tool).
  • Goals: use get_goals to discover goalIds before update / archive / restore / delete / alert actions.
  • update_metric may be two-step when changing a metric definition with dependents; delete_metric and delete_goal may also be two-step when dependents exist. For any of these operations, first call without confirmed, show the returned dependency payload to the user, then retry with confirmed: true only after user confirmation.
  • get_goals accepts either metricId OR projectId, not both.
DO NOT USE FOR:
  • Chart or experiment metric values → query_metric / query_dataset.
  • Experiments and flags → get_experiments / get_flags / create_experiment.

Input Parameters

string
Human-readable name for the metric
object
Event definition for single-event metrics (UNIQUES, TOTALS, PROPSUM, PROPAVG).
string ("get_metrics" | "create_metric" | "update_metric" | "delete_metric" | "get_goals" | "create_goal" | "update_goal" | "archive_goal" | "restore_goal" | "delete_goal" | "get_goal_alert" | "create_goal_alert" | "update_goal_alert" | "delete_goal_alert")
required
What to do — metric defs: ‘get_metrics’, ‘create_metric’, ‘update_metric’, ‘delete_metric’; goals: ‘get_goals’, ‘create_goal’, ‘update_goal’, ‘archive_goal’, ‘restore_goal’, ‘delete_goal’; alerts: ‘get_goal_alert’, ‘create_goal_alert’, ‘update_goal_alert’, ‘delete_goal_alert’.
integer
End of the goal timeframe, as a Unix timestamp in seconds. Must be after startsAt.
array
Array of event definitions for FORMULA metrics. Each event is referenced by letter (A, B, C…) in the formula.
string
Goal-scoped actions and goal alert actions.
string
Formula string for FORMULA metrics. Reference events by letter: A, B, C… Available functions: UNIQUES(A), TOTALS(A), PROPSUM(A), PROPAVG(A), PROPMIN(A), PROPMAX(A), PROPCOUNT(A), PROPCOUNTAVG(A), REVENUETOTAL(A). Example: “TOTALS(B)/TOTALS(A)”
string
update_metric / delete_metric: target metric. get_goals: list goals on one metric. create_goal: metric to attach the goal to.
integer
Number of days to return on for RETENTION metrics (1–30).
integer
Start of the goal timeframe, as a Unix timestamp in seconds.
boolean
update_metric when changing a metric definition with dependents / delete_metric / delete_goal: set true only after the user confirms.
array
get_metrics: metric IDs to fetch (required for get_metrics).
string
create_metric / update_metric / delete_metric: project ID. get_goals: list all goals in project (mutually exclusive with metricId).
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
string ("gte" | "lte")
Success direction: “gte” = metric should be at or above targetValue, “lte” = at or below.
string
What to count. “User” for unique users (default), “Event” for event totals.
string ("ordered" | "unordered" | "sequential")
How funnel steps relate: “ordered” (this order), “unordered” (any order), “sequential” (exact order).
boolean
Whether to mark this metric as official. Requires elevated permissions.
string ("UNIQUES" | "TOTALS" | "FORMULA" | "PROPSUM" | "PROPAVG" | "RETENTION" | "CONVERSION")
Type of metric. UNIQUES: unique users who performed the event. TOTALS: total event count. FORMULA: custom formula combining multiple events (supports PROPCOUNT, PROPMIN, PROPMAX, etc. as formula terms). PROPSUM: sum of a numeric property. PROPAVG: average of a numeric property. RETENTION: retention metrics. CONVERSION: funnel / multi-step conversion metrics.
object
Start event definition for RETENTION metrics.
string
Description of what this metric measures
object
Return event definition for RETENTION metrics.
number
The numeric value the metric should hit over the timeframe.
array
Ordered funnel steps for CONVERSION metrics (minimum 2 events). Each step is an event with optional filters. Not used for FORMULA — use “events” for formula metrics.
object
Full replacement of alert delivery channels. Omit to preserve delivery, pass null to clear all channels, or pass an object containing every desired channel.
integer
Metric dip percentage that triggers an alert. Required when shouldAlertOnDip is true.
boolean
get_goals: include archived goals when metricId is set.
integer
1 is for daily retention, 7 is for weekly retention, 30 is for monthly retention.
boolean
Send an alert when the metric dips by the configured threshold.
integer
Maximum time window to complete the funnel, in seconds (e.g. 86400 = 1 day, 604800 = 7 days).
boolean
Set to true when this metric is intended for use in an experiment. Enables experiment-specific formula validation rules.
object
Property to aggregate for PROPSUM and PROPAVG metrics. Specifies which numeric event/user/group property to compute the aggregation on.
string ("UNIQUES" | "TOTALS")
CONVERSION only: “UNIQUES” measures unique users who complete the funnel; “TOTALS” measures total conversion path counts.
object
CONVERSION only: numeric property on the last funnel step to aggregate (e.g. revenue). Use with funnelComputePropFunction.
array
CONVERSION only: properties held constant across funnel steps (same as funnel “holding constant” in the UI).
boolean
Send an alert when the goal target is reached.
string ("SUM" | "AVG")
CONVERSION only: how to aggregate funnelComputeProperty on the last step — “SUM” (default when property set) or “AVG”.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_USE_AMP_NOTEBOOKSRead and manage Amplitude notebooks. One outcome-based tool selected by action.ACTIONS:
  • get: read notebooks by notebookIds (or singular notebookId). Resolve IDs with search_amp_entities (entityTypes: NOTEBOOK).
  • create: create a notebook with name + rows. Chart cells accept saved chart IDs and temporary chart edit IDs interchangeably in chartId; edit IDs are saved as permanent charts automatically.
  • edit: update name and/or one layout edit. Call get first and pass its lastModifiedAt as expectedLastModifiedAt. Rows accept edit IDs the same way create does — use this to add a freshly queried chart to an existing notebook.
ROW ITEMS:
  • Types: chart, rich_text (markdown content), session_replay, video, image, cohort. Use rich_text, not markdown.
  • Width 3–12 columns per item; row total ≤ 12; max 4 items per row.
DO NOT USE FOR:
  • Finding notebooks by name: use search.
  • Creating a shared space, changing space members, or moving an existing notebook into a space: use manage_amp_entities.
  • Sharing / comments: use share_amp_entities / use_amp_comments.

Input Parameters

string
Optional single structural layout edit.
string
Notebook name.
array
Notebook layout rows.
string ("get" | "create" | "edit")
required
Discriminator: determines which set of parameters applies (get | create | edit)
object
Optional metadata updates (e.g. name).
string
Singular notebook ID alias for notebookIds:[id].
string
Where to save. Omit for the personal space (previous behavior).
array
Notebook IDs to read. Resolve with search_amp_entities (entityTypes: [‘NOTEBOOK’]).
integer
lastModifiedAt returned by get. Read the notebook first.

Output

array
required
Array of content blocks returned by the tool
Slug: AMPLITUDE_MCP_USE_AMP_SKILLLoad an Amplitude skill — a workflow playbook describing the optimal sequence of Amplitude tools for a task.Consult a skill BEFORE improvising a multi-step Amplitude workflow (analysis, chart or dashboard creation, experiment review, replay debugging, instrumentation).Actions:
  • list: every available skill with its description. Use to browse what exists, or to find the name of the skill you want.
  • get: exact skill name or skill:// URI → that skill’s full instructions.

Input Parameters

string ("get" | "list")
What to do: ‘list’ everything, or ‘get’ one skill by name.
string
Brief explanation of why you are calling this tool and what you expect to learn from the result.
string
Exact skill name (e.g. ‘analyze-chart’) or full skill:// URI. Required when action is ‘get’.

Output

array
required
Array of content blocks returned by the tool