Amplitude MCP
Amplitude MCP lets authorized agents analyze product data, manage charts, dashboards, cohorts, experiments, taxonomy, and related Amplitude workspace resources.
Verdict
Common use cases
- Pull chart links for weekly product reviews
- Create event properties in tracking plan
- Delete unused user properties at cleanup
- Fetch AI agent insights on dashboard trends
- Inspect group types before migration
Integration
- Vendor
- Amplitude MCP
- Category
- other
- Auth
- OAUTH2
- Tools
- 48
- Composio slug
amplitude_mcp
Tools
- Create group types
Create 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", "Worksp
- Create properties
Create one or more properties in a project's tracking plan. Use propertyType to select which kind of properties to create. PROPERTY TYPES: | propertyType | What it creates | Key params | |---|---|---| | event | Event properties (global or
- Delete event propertiesdestructive
Delete 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 ev
- Delete user propertiesdestructive
Delete 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
- Get agent results
Retrieve 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 an
- Get amplitude agent analytics info
Single 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
- Get amplitude charts
Read 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 ch
- Get amplitude context
Unified 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 con
- Get amp session replay info
Unified 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): fin
- Get amp taxonomy
Read 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: "e
- Get amp user data
Look 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 (`inclu
- Get data warehouse destinations
List 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 c
- Get from url
Retrieve objects from Amplitude URLs WHEN 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 Amplitud
- Get group types
List 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.,
- Get session replay duration
APP 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_re
- Get session replay stream
APP 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 n
- Get session replay timeline
APP 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.
- Get tracking plan sources
List 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 trac
- Get transformations
Retrieve 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.
- Manage amp context
Manage 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.
- Manage amp entities
Create 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
- Manage amp events
Write 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 ingeste
- Manage amp taxonomy
Read 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,
- Query amplitude data
Run 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 | s
- Rename chart
Rename a chart that has already been saved WHEN 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
- Render amplitude chart
Render 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
- Render amp session replay
Render 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 want
- Restore event properties
Restore 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. -
- Restore user properties
Restore 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 res
- Save chart edits
Promote 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
- Search amp data taxonomy
Semantic 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 FIRS
- Search amp entities
Search 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 a
- Share amp entities
Manage 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 view
- Track ui render response
Internal telemetry tool used by MCP UI components to report render latency and errors. NOT FOR DIRECT MODEL USE.
- Update properties
Update 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
- Use amp ai visibility
Use 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, promp
- Use amp comments
Read 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 insid
- Use amp dashboards
Read 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 dashb
- Use amp experiments
Unified 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 exp
- Use amp flags
Unified 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 flag
- Use amp guides surveys
List 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
- Use amplitude ai feedback
Read 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, transcr
- Use amplitude chart monitors
Read 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 c
- Use amplitude cohorts
Work 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 thi
- Use amplitude data connections
Unified 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 pr
- Use amplitude metrics
Unified 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 US
- Use amp notebooks
Read 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`: cre
- Use amp skill
Load 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, repl
Setup
Setup guide
- 11. In Switchy, open your workspace settings and click 'Add Integration' under the MCP section. 2. Select 'Amplitude MCP' from the catalog and click 'Connect'. 3. You'll be redirected to Amplitude's OAuth consent screen — sign in with your Amplitude account and grant read/write access to projects, tracking plans, and analytics data. 4. After authorization, Switchy redirects you back and displays a green 'Connected' badge next to Amplitude MCP. 5. Open any Project in your workspace and type '@Amplitude' in the chat to confirm the connection — you should see a list of available tools in the autocomplete dropdown. 6. Test the integration by pasting this prompt: '@Amplitude retrieve the chart link for chart ID 12345' (replace 12345 with a real chart ID from your workspace). 7. If the MCP returns a valid link or error message, setup is complete and you can start invoking tools in your workflows.
What teammates see: by default, memories from Amplitude MCP are scoped to the Project (PROJECT visibility) - you can mark any memory PRIVATE or share it ORG-wide.
Works well with
Top models
Compatibility data appears once enough Projects have used this MCP together with a given model.
How Switchy teams use it
Starter prompts
Retrieve Chart Link
@Amplitude get the chart link for chart ID 98765. Return the URL so I can share it with the team.
Create Event Property
@Amplitude create an event property called 'checkout_step' with type string in project ID 54321. Mark it as required and add a description: 'Current step in checkout flow'.
Delete User Property
@Amplitude delete the user property 'legacy_tier' from project ID 54321. Confirm it's marked as deleted and restorable.
Fetch Agent Analysis
@Amplitude get agent results for project ID 54321 from the last 7 days. Summarize any anomalies or trends the agent flagged.
List Group Types
@Amplitude list all group types in project ID 54321. Show their names, statuses, and whether they're in the tracking plan.
Example outputs
Illustrative - representative of the model's voice and quality, not literal recordings.
@amplitude show me the top 5 user properties by event volume in project 12345 over the last 30 days
Based on the tracking plan for project 12345, here are the top 5 user properties by event volume (last 30 days): 1. **user_id** — 2.4M events (core identifier, present on all authenticated events) 2. **device_type** — 2.1M events (mobile/desktop/tablet segmentation) 3. **subscription_tier** — 890K events (free/pro/enterprise) 4. **signup_date** — 890K events (cohort analysis anchor) 5. **last_active_feature** — 720K events (engagement tracking) This is an illustrative example. Actual property volume depends on your instrumentation coverage and the date range queried.
This example uses the 'Get amplitude context' or property-listing tools to surface tracking plan metadata. Requires read access to the project's tracking plan. Amplitude's API returns property schemas, not live event counts — pair with chart queries for volume metrics.
@amplitude create a new event property called 'checkout_funnel_step' for the 'Add to Cart' event in project 12345, type string, required
Created event property **checkout_funnel_step** for event 'Add to Cart' in project 12345: - **Type:** string - **Required:** Yes - **Status:** Planned (will appear in tracking plan immediately; mark as 'ingested' once instrumentation is live) - **Scope:** Per-event property (only attached to 'Add to Cart', not global) Next step: Update your client-side instrumentation to send this property with every 'Add to Cart' event. The tracking plan now enforces this field.
This example uses 'Create properties' to add a schema entry to the tracking plan. The property won't appear in historical data — it's a forward-looking schema change. Requires write access to the project. Side-effect: downstream teams see the new required field in the tracking plan and must update instrumentation.
@amplitude summarize the last 3 AI agent analyses for dashboard 'Q1 Retention Cohorts' and tell me if any flagged anomalies
Retrieved 3 recent AI agent analyses for dashboard 'Q1 Retention Cohorts': 1. **Jan 15, 2025** — Flagged a 12% drop in Day-7 retention for the Jan 1-7 cohort vs. prior week. Agent noted correlation with a spike in 'app_crash' events on Android. 2. **Jan 8, 2025** — No anomalies. Retention curves tracking within 2% of forecast. 3. **Jan 1, 2025** — Highlighted unusually high Day-1 retention (68% vs. 58% baseline) for users acquired via paid social, suggesting campaign quality improvement. This is an illustrative summary. Actual agent output includes confidence scores and drill-down links.
This example uses 'Get agent results' to surface AI-generated insights from Amplitude's analytics agent. Requires the AI agent feature to be enabled on your plan (not available on all tiers). The agent runs asynchronously — results may lag dashboard updates by hours.
Use-case deep-dives
When Amplitude MCP fixes tracking plan chaos before your next funding round
A 12-person product team at a Series A SaaS company realizes their event taxonomy is a mess: duplicate properties, orphaned group types, and 40% of tracked events never used in dashboards. The Amplitude MCP lets them bulk-create standardized properties, delete dead event properties per-event-type, and restore group types that were accidentally marked unexpected—all from a shared Switchy workspace where the PM, analytics lead, and two engineers can see the same audit checklist. The 48 tools cover the full CRUD surface of Amplitude's tracking plan API, so you're not context-switching to the web UI for every fix. This works when your tracking plan is under 500 events; beyond that, you'll want a dedicated data governance tool. If your team is cleaning up analytics debt in a sprint, this MCP is the fastest path to a mergeable tracking plan.
How Amplitude MCP surfaces AI agent insights without leaving standup
A 5-person leadership team at a B2B startup runs a weekly dashboard review every Monday at 9am. They used to screenshot Amplitude charts and paste them into Slack, losing the underlying data and any AI-generated insights Amplitude's agent had flagged. With the Amplitude MCP in Switchy, the ops lead pulls saved charts by ID, retrieves agent results that analyzed conversion funnels over the weekend, and shares both in the same thread where the CEO is asking follow-up questions. The get_amplitude_charts and get_agent_results tools are the workhorses here; OAuth2 auth means no API key rotation when someone leaves. This setup wins when your exec team actually reads the dashboards—if they don't, no MCP will fix that. For teams that live in their analytics, this MCP turns Amplitude into a first-class participant in your daily workflow.
Why Amplitude MCP is overkill for support—unless you're debugging user behavior
A 3-person support team at a mobile app company gets tickets like 'why did my trial expire early' and needs to see what events the user actually triggered. The Amplitude MCP's get_amplitude_context tool can surface user-level analytics, but the 48-tool surface is built for tracking plan management, not ad-hoc user lookups. If your support flow is 'check the user's event stream and close the ticket,' you're better off with Amplitude's native support integrations or a lighter webhook setup. The MCP wins when support escalates to product and they need to bulk-audit properties or compare cohort definitions—scenarios where the full CRUD toolset justifies the OAuth2 setup cost. For pure support lookup, this MCP is a detour. For support-to-product handoffs where you're editing the tracking plan in the same session, it's the right call.
Frequently asked
What does the Amplitude MCP let me do in Switchy?
It connects your Amplitude analytics workspace so AI agents can read charts, query event data, manage tracking plans, and retrieve AI-generated insights from session replays. You can ask questions about user behavior, funnel drop-offs, or cohort trends without leaving Switchy. The MCP exposes 48 tools covering everything from property creation to dashboard search.
Do I need admin access to connect Amplitude via OAuth?
You need OAuth credentials that grant read access to projects, charts, and cohorts, plus write access if you want agents to modify tracking plans or create properties. Amplitude's OAuth flow will show exactly which scopes are requested. If you only want read-only analytics queries, ensure your OAuth app is configured accordingly before connecting.
Can the MCP create new events or send tracking data to Amplitude?
No. The MCP manages your tracking plan schema and reads analytics data, but it doesn't send live event ingestion. If you need to log events from Switchy workflows, use Amplitude's HTTP API directly or trigger it via a webhook tool. This MCP is for querying and planning, not for instrumentation.
How is this different from exporting Amplitude charts to Slack or email?
Static exports show a snapshot. The MCP lets AI agents query live data, compare cohorts, drill into funnels, and answer follow-up questions in the same conversation. You get dynamic analysis instead of a PNG. It's faster for exploratory work but won't replace scheduled reports if your team needs those.
Which team member should connect our Amplitude account?
Whoever owns your Amplitude workspace and understands which projects contain production data. They'll authorize OAuth and choose which projects Switchy can access. If multiple people need to query different projects, connect separate Amplitude instances or ensure the OAuth token covers all relevant projects upfront.