PostHog
Product analytics, flags, insights
About PostHog
PostHog is an open-source product analytics suite with events, session replay, feature flags, and experiments. Its remote MCP server lets assistants query analytics with natural language or HogQL, manage flags, and investigate product behavior conversationally.
Connection details
https://mcp.posthog.com/mcp- Transport
- Streamable HTTP
- Authentication
- OAuth
Setup
claude mcp add posthog --transport http https://mcp.posthog.com/mcpFrequently asked questions
What is the PostHog remote MCP server?
The PostHog remote MCP server is a hosted Model Context Protocol endpoint at https://mcp.posthog.com/mcp, so AI assistants can connect to it without installing or running anything locally. PostHog is an open-source product analytics suite with events, session replay, feature flags, and experiments. Its remote MCP server lets assistants query analytics with natural language or HogQL, manage flags, and investigate product behavior conversationally.
How do I connect to the PostHog MCP server?
Add the endpoint https://mcp.posthog.com/mcp to any MCP-compatible client such as Claude Code, Codex, Cursor, or VS Code. The setup snippets on this page configure each client in one step.
Does the PostHog MCP server require authentication?
Yes. PostHog uses OAuth: the first time you connect, your MCP client opens a browser window to sign in and authorize access, then reuses the credentials for future sessions.
Which transport does the PostHog MCP server use?
PostHog exposes a Streamable HTTP endpoint, the current standard transport for the Model Context Protocol, supported by all major MCP clients.
More remote MCP servers

