MCP server · Notes

RTFM MCP server

Let your AI search your whole project, code, docs and PDFs, from one local index.

Notes Privacy Developer tools For it and development Knowledge & Memory

RTFM is a small helper that builds a searchable index of everything in your project folder: code files, documents, PDFs, spreadsheets, notes and more. Once it is connected, your AI can look things up in that index instead of guessing or reading file after file. It is handy if you work with a big folder of mixed files and want your AI to actually find the right passage.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. It cannot see your files unless you paste them in. An MCP server is a small helper program that gives your AI a new skill, here the skill of searching a local index of your project. So when you ask a question, the AI can look things up in your own files and answer from what it finds.

What this MCP server does

You ask your AI a question about your project. The AI uses this helper to search the index that RTFM built from your folder. The helper looks through your code, documents, PDFs and notes and returns a short ranked list of the best matching spots. Your AI then reads only the parts that matter and answers you. Everything stays on your computer, and there is no cloud service and no API key involved.

What you can do with it

Search across code, docs, PDFs and notes in one query
Find the right paragraph in a large folder of files
Remember notes from past sessions across your projects
Search an Obsidian vault by its notes and links
Re-index your project automatically when files change
Expand a search result to read just that section

Try asking your AI

“Find the authentication flow in this project”
“What did we decide about the OAuth setup last month”
“Search my notes for anything about tax rules for freelancers”
“Which document talks about the data retention policy”

What it gives back to you

You get a short list of matching places, each with a file name, a section title and a small score. Your AI reads that list and then pulls in only the parts it needs to answer you. In the chat you see the answer plus the file names it used. It can also show you the history of changes to a note over time.

Before you start

What you need

Python 3.10 or newer installed on your computer
Your project folder on the same machine
Claude Code, or another MCP client like Cursor or Claude Desktop

Good to know

It reads files in the folders you point it at, so only index folders you are comfortable having searched.

Install it with your AI

Add RTFM MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check RTFM MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,609 MCP servers here for you.