MCP server · Notes
RouteMind MCP server
by CSP911
Your AI walks a human-written map of your documents to find the exact right page.
RouteMind is a helper that lets your AI find the right document by following a map that people write and keep up to date. Instead of guessing by similarity, the AI reads a short list of areas, picks one, and walks down to the page. It is handy if your team keeps getting answers from the wrong revision or a neighbouring row.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to something outside the chat. This one connects your AI to your own RouteMind map, which lives in a git repository you control. Once it is connected, your AI can read the map, read documents, and place new documents there when you ask.
What this MCP server does
You ask your AI a question about your documents. The AI uses this helper to read the top of your map, which is a short list of areas and one sentence each about when to come to them. The AI picks an area, then walks down short lines until it reaches the document. You get the answer back in the chat, and the map records why each step was taken.
What you can do with it
- Read the top-level list of areas in your map
- Walk down to a specific document by following the map
- Read the full text of a document once it is found
- Place a new document into the map and create a holder for it
- Read another RouteMind map for one session
- Replay a past walk from the last six hours
- See the exact text the AI was given at each step
Try asking your AI
- “What is the rule for using the corporate card on a business trip?”
- “Find the policy about receipts for expenses.”
- “Which approval chain applies to a purchase over 5000?”
- “Place this new document about payroll deductions into the map.”
What it gives back to you
You get answers in the chat, drawn from the exact document the AI walked to. The AI can also show you the list of areas it considered, the steps it took, and the text it read at each step. If it places a document, you get a confirmation that the map was updated with a new commit.
Before you start
What you need
- A RouteMind install running (the quickstart uses Docker)
- An MCP client like Claude Code or another tool that can talk to MCP servers
- A git repository for your map (the example back office is offered on first install)
Good to know
The map is a single point of failure: if a line in it is wrong, the AI will follow it confidently, and nothing flags it.
Install it with your AI
Add RouteMind 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 RouteMind 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.
Who it's for
Teams whose documents look alike, like policy revisions or rows that differ by a code, and who keep getting answers from the wrong page.
