# Grounded Docs

An MCP server that indexes official documentation from websites, GitHub, npm, PyPI and local files, so an AI coding assistant can query the exact library version a project depends on.

Grounded Docs is a Model Context Protocol server that gives an AI coding assistant a personal, always-current documentation index. It fetches official docs from websites, GitHub repositories, npm, PyPI and local files or zip and tar archives, and lets the assistant query the exact version of a library that a project actually uses instead of relying on outdated training data.

It reads many document and code formats, including PDF, Word, Excel, PowerPoint, OpenDocument, RTF, EPUB, Jupyter notebooks, HTML, Markdown and more than ninety programming languages. It runs on the user's own machine, works with any MCP-compatible client, and is written in TypeScript with a command-line interface for indexing sources and querying the results.

Website: https://grounded.tools