Happy slice of mcp pizzaMCP.pizza

rtfm

MCP.Pizza Chef: roomi-fields

RTFM lets your AI assistant instantly find the right information across your entire project, including code, documents, PDFs, legal texts, and research files. It indexes everything locally on your computer, so your data stays private and you avoid cloud or API costs. Compatible with apps like Claude Desktop and Cursor, it provides fast, accurate retrieval with semantic search and knowledge graph features. Setup requires some technical steps but delivers a powerful, free, open-source retrieval layer for smarter AI coding assistance.

Coding
Files/PDF
Other

Use This MCP server To

Search my entire project code and docs instantly Find specific sections in PDFs and legal documents Get precise context for AI coding assistants Index and query research papers and notes Use semantic search to find relevant info Keep all my project knowledge local and private Expand search results progressively for better answers

README

RTFM

Retrieve The Forgotten Memory

The open retrieval layer your AI agent was missing

Index everything in your project — code, docs, PDFs, legal texts, research, data — and your agent finds the right context instantly. No hallucinations. No cloud. No API costs.

Free · Local · Open Source · MIT


RTFM vs vanilla Claude Code — same task, same model, who pays the bill?


PyPI version License: MIT Python MCP Claude Code GitHub stars

The problem

Your AI agent is flying blind.

It greps through thousands of files, misses the doc that answers the question, invents modules that don't exist, forgets what you decided last session. The bigger the project, the worse it gets. You've added a smarter model. It didn't help. Because the bottleneck isn't intelligence — it's retrieval.

Code indexers (Augment, Sourcegraph, Cursor) only see code. But your project isn't just code. It's specs, PRs, architecture decisions, research papers, PDFs, regulations, vault notes — the context your agent needs to stop guessing.

Why I built this

rtfm FAQ

Can I use this to search and retrieve relevant code and documentation in my project?
Yes — RTFM indexes your entire project including code, docs, PDFs, and more, letting your AI find precise context instantly.
Can I use RTFM with Claude Desktop and Cursor?
Yes — it supports Claude.ai, Claude Desktop, and Cursor clients.
Do I need an API key or cloud account to use RTFM?
No — it runs locally on your machine, free and open source, with no API keys or cloud needed.
How hard is it to set up RTFM?
Setup is developer-level — you install it via pip or plugin commands and initialize your project, which may require some technical steps.
Can RTFM handle PDFs and legal documents?
Yes — it supports 22 file formats including PDFs, EPUB, DOCX, and legal texts with semantic search.
Does RTFM keep my data private?
Yes — everything runs locally on your computer, so your data stays with you.
Can I add semantic search capabilities?
Yes — optional extras like semantic search and PDF parsing can be installed on demand within isolated environments.