Skip to content
PostHog logo

PostHog MCP server

Open-source product analytics

PostHog is not a separate install. One Activepieces MCP server exposes it alongside 760+ other apps, behind a single URL.

Tools
5
Works with
Any MCP client
Auth
Custom auth
License
MIT, open source
Updated
August 2026

About the PostHog MCP server

Connect PostHog once in Activepieces and every action it ships becomes a tool your assistant can call, behind the same server URL as the rest of your apps. Your agent reaches PostHog and 760+ other apps over a single connection, on our cloud or a self-hosted install.

Tools

PostHog tools your AI can run

Once connected, your assistant can call any of these PostHog actions by asking in plain language.

  • Capture Event

    Capture a custom event in PostHog

    3 fields

  • Create Project

    Create a new PostHog project in your organization

    3 fields

  • Get Feature Flags

    List all feature flags in your PostHog project

    1 field

  • List Persons

    Get a list of identified users in your PostHog project

    2 fields

  • Custom API Call

    Make a custom API call to a specific endpoint

    10 fields

Triggers

PostHog events your agent can watch

These start a run the moment something happens in PostHog, so work gets picked up on its own.

  • New Event

    Triggers when a new event is captured in PostHog

    1 field

PostHog MCP, answered.

No. That is the point of it. One Activepieces server exposes PostHog alongside every other piece you connect, so your client keeps a single connection.

Yes. Activepieces is open source and free to start, and the MCP server is included on every plan, from the free cloud tier to any self-hosted deployment.

Connect PostHog in Activepieces, enable the server under Settings → MCP Server, then paste your server URL into your client config. It authenticates over OAuth on first use.

It can call 5 tools, including Capture Event, Create Project, Get Feature Flags, and chain them with steps in other apps inside the same run.

Connections use OAuth2 with limited scopes and are stored under 256-bit encryption, with no API to read them back, so an agent gets scoped access rather than your keys.