
Connects Claude to Amplitude's analytics API through the Pipeworx gateway. You get five tools covering the usual product analytics workflow: pull event counts and breakdowns by date range, track daily/weekly/monthly active users, measure cohort retention over time, search for users by ID or properties, and grab individual activity timelines. The ask_pipeworx wrapper lets you query in plain English instead of calling tools directly. Useful when you're analyzing user behavior, debugging drop-offs, or need to pull retention metrics without leaving your editor. Part of a larger gateway offering 673+ data sources if you need to correlate Amplitude data with other platforms.
Sponsors
Amplitude MCP Pack
Part of Pipeworx — an MCP gateway connecting AI agents to 1861+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.
| Tool | Description |
|---|---|
amp_get_events | Get event counts and breakdowns for a date range (e.g., "2024-01-01" to "2024-01-31"). Returns frequency, user segments, and trends by event name. |
amp_get_active_users | Get active user counts by granularity (daily, weekly, or monthly) for a date range. Returns totals and trend data. |
amp_get_retention | Get user retention metrics for a cohort over time. Returns retention percentages by time period (e.g., day 1, day 7, day 30). |
amp_user_search | Search for users by ID or property (e.g., email, user_id). Returns matching profiles with properties, event history, and segments. |
amp_get_user_activity | Get recent event activity timeline for a specific user. Returns events with timestamps, properties, and interactions. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"amplitude": {
"url": "https://gateway.pipeworx.io/amplitude/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/amplitude/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1861+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
This pack takes your own API key (_apiKey) — we don't front one for it, so there's no curl here that would run without it. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/amp_get_events. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.
@pipeworx/mcp-amplitude is a local stdio bridge to the Pipeworx gateway: your MCP client
starts it with npx, and it forwards every call to the same
https://gateway.pipeworx.io/amplitude/mcp endpoint shown above. It needs network access;
there is no offline mode.
{
"mcpServers": {
"amplitude": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-amplitude"]
}
}
}
Without a key it calls anonymously, capped at 50 calls a day. A free account
raises that to 200 a day: get a key at https://pipeworx.io/signup and add
"env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry.
The key is sent as a Bearer token, the same way a hosted connection sends it,
so calls are metered and billed exactly as they are there.
It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to
also list ask_pipeworx and the other gateway-wide tools.
Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by
default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check
your Node version's documentation.
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Amplitude data" })
The gateway picks the right tool and fills the arguments automatically.
MIT