PostHog MCP Server for Claude

Content

PostHog MCP Server is PostHog's official Model Context Protocol server for connecting Claude and other MCP-capable clients to a PostHog project. It is documented as a hosted endpoint at https://mcp.posthog.com/mcp, with an EU endpoint at https://mcp-eu.posthog.com/mcp, and the server source lives in the PostHog monorepo under services/mcp.

The server is useful when a product, growth, support, or engineering workflow needs current PostHog context inside the assistant: recent trends, dashboard state, feature flag configuration, experiment results, error groups, event schemas, logs, LLM analytics, surveys, and project configuration. Because the same MCP surface can also create or change PostHog resources, start with a small feature set and a scoped personal API key.

Features

• Official PostHog documentation page for MCP setup, available tools, filtering, data processing, self-hosted use, and examples.
• Hosted Streamable HTTP endpoint at https://mcp.posthog.com/mcp.
• EU endpoint at https://mcp-eu.posthog.com/mcp.
• Public server source in PostHog/posthog under services/mcp.
• Quick install through the official PostHog wizard.
• Manual MCP configuration through mcp-remote and an Authorization header.
• Feature filtering with the features query parameter.
• Exact tool allowlisting with the tools query parameter.
• tools mode for one MCP tool per PostHog tool and cli mode for a single CLI-like wrapper tool.
• Consumer attribution through query parameters or headers for plugin and proxy installers.
• Local development and self-hosting path with POSTHOG_BASE_URL.

Tool Surface

PostHog documents feature groups for workspace and project management, actions, activity logs, alerts, annotations, cohorts, dashboards, data schema, data warehouse, docs search, early access features, error tracking, events, experiments, feature flags, CDP functions, insights, LLM analytics, prompts, logs, notebooks, persons, reverse proxy records, search, SQL, surveys, and workflows.

Many tools are read-only, but not all. The source schema marks some tools with write scopes and destructive hints, including deletion, workflow execution, workflow scheduling, feature management, and product-configuration changes.

Installation

Quick Install

Use the official PostHog wizard to install the MCP server into supported clients:

npx @posthog/wizard@latest mcp add

The wizard can install into Cursor, Claude, Claude Code, VS Code, and Zed.

Manual MCP Config

Create a personal API key using PostHog's MCP Server preset, then configure a compatible client with mcp-remote:

{
  "mcpServers": {
    "posthog": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://mcp.posthog.com/mcp?features=docs,insights,error_tracking,events,data_schema",
        "--header",
        "Authorization:${POSTHOG_AUTH_HEADER}"
      ],
      "env": {
        "POSTHOG_AUTH_HEADER": "Bearer phx_your_personal_api_key"
      }
    }
  }
}

The example above narrows the starting feature set. To expose a different surface, change the features list or use PostHog's exact tools allowlist:

https://mcp.posthog.com/mcp?tools=dashboard-get,feature-flag-get-all,execute-sql

For EU PostHog projects, use:

https://mcp-eu.posthog.com/mcp

Use Cases

• Ask Claude to summarize signup, activation, retention, or funnel movement from current PostHog insights.
• Review recent errors and affected user counts while triaging a regression.
• Inspect active feature flags before planning a rollout or cleanup.
• Draft a dashboard or insight plan after searching existing dashboards and event schemas.
• Compare experiment status and conversion metrics before writing a release update.
• Query logs, LLM analytics, or prompt performance while debugging an AI product workflow.
• Search PostHog docs from the same MCP client when implementing analytics, flags, replay, or warehouse changes.
• Use a local or self-hosted MCP server with POSTHOG_BASE_URL for self-hosted PostHog instances.

Safety Checklist

• Create a dedicated personal API key for MCP use.
• Grant only the required PostHog scopes and rotate the key after temporary work.
• Start with feature or tool filtering instead of exposing every PostHog tool.
• Confirm the active PostHog project and region before approving queries.
• Keep approval prompts enabled for writes, deletes, workflow runs, alerts, surveys, experiments, and feature flag changes.
• Use short date ranges and row limits for SQL, logs, warehouse, person, and event queries.
• Avoid unrestricted production access while testing a new client setup.
• Replace placeholder keys in config files and never commit real POSTHOG_AUTH_HEADER values.

Source Links

• PostHog MCP docs: https://posthog.com/docs/model-context-protocol
• Server source: https://github.com/PostHog/posthog/tree/master/services/mcp
• Installer package: https://www.npmjs.com/package/@posthog/wizard
• MCP specification: https://modelcontextprotocol.io/specification/2025-06-18/