An MCP server that exposes llms.txt files to IDEs for context-aware development.
mcpdoc is easy to set up with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo view langchain-ai/mcpdoc --webOpen the official repository or website.
Check the README for package manager, auth, and platform requirements.
Try it in a small test task inside your agent workflow.
This tool helps AI coding assistants like Cursor or Claude Code read documentation from llms.txt files. It gives developers full control over which documentation sources are used and allows auditing of every tool call. You can point it to any llms.txt URL or local file, and it will fetch the linked pages securely.
mcpdoc is an open-source MCP (Model Context Protocol) server that bridges the gap between AI-powered IDEs and structured documentation. It allows developers to define a list of llms.txt files—standardized website indexes for LLMs—and provides a simple `fetch_docs` tool that reads URLs within those files. This enables MCP host applications like Cursor, Windsurf, and Claude Code/Desktop to retrieve context for tasks with full transparency and auditability. The server implements strict domain access controls for security: remote llms.txt files automatically restrict fetching to their own domain, while local files require explicit domain whitelisting. It supports both SSE and stdio transports, making it easy to integrate into various workflows. Built by LangChain, it is ideal for teams that want to ensure their AI assistants use only approved documentation sources.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 36 days ago.
998 GitHub stars indicate community interest.
14 open issues signal maintenance load.
MIT license detected.
Provide AI coding assistants with up-to-date library documentation from llms.txt files.
Audit and control which documentation sources your AI tools can access.
Integrate custom or private documentation into AI-powered IDEs securely.
Enable context-aware code generation by feeding relevant docs to LLMs.
Standardize documentation retrieval across multiple AI tools in a team.
If allowed-domains is set to '*', the tool can fetch from any URL, posing a security risk.
Local llms.txt files require explicit domain whitelisting; misconfiguration may block legitimate docs.
998
Stars
121
Forks
14
Issues
MIT
License
Open-source GEO audit engine to optimize websites for AI search visibility and citability.
11 opinionated Claude skills for SEO: page audits, content briefs, article writing, link building, and more.
Connect Google Search Console to AI assistants for natural language SEO analysis.
2 security/trust notes recorded.
Setup difficulty is 2/5.