Context Autopilot is a Model Context Protocol (MCP) server: Mines your Claude Code and Cursor sessions into evidence-based CLAUDE.md / AGENTS.md rules. In practice that means any MCP-compatible AI assistant can call Context Autopilot's tools directly — the model decides when to use them in a conversation or agent run.
It runs locally: the npm package context-autopilot speaks MCP over stdio on your machine. No credentials are required — it works out of the box. The current release is v0.6.0, with source at ChiragBachani/context-autopilot on GitHub.
Context Autopilot is listed under Development on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Context Autopilot for ChiragBachani, claim this listing to verify ownership, earn the Verified badge, and keep the details current.