PostHog MCP Server
Query product analytics with HogQL, manage feature flags and experiments, investigate errors with stack traces, and triage issues directly in PostHog.
Frequently asked questions
What is the PostHog MCP server?
It is a Model Context Protocol (MCP) server — a small piece of software that gives AI assistants like Claude a secure, governed connection to PostHog. Query product analytics with HogQL, manage feature flags and experiments, investigate errors with stack traces, and triage issues directly in PostHog.
Is there an official PostHog MCP server?
The PostHog MCP server is an official integration, maintained by the vendor or the Model Context Protocol project, which makes it the safest default for business use.
What can an AI assistant actually do with PostHog?
Through this server an assistant can work with analytics queries, feature flags, error tracking, experiments — reading from and acting on PostHog directly instead of you copy-pasting between windows. What you allow it to do is controlled by the permissions you grant.
How do I set this up for my business?
Technically-minded teams can connect an MCP server themselves — our plain-English guide to MCP explains how the pieces fit. If you want it done with governance, permissions, and support handled, that is exactly what Crox's Build engagement covers.
New to MCP? Start with our plain-English guide to the Model Context Protocol or see how to connect AI to your business tools without writing code .
Want this connected to your business — with governance handled?
Crox maps your processes, connects AI to the tools you already use, and keeps it working as models change. Start with a readiness assessment or talk to us about a build.