Complete AI Training

MCP server · Notes

BaseMouse MCP server

by basemouse

Let your AI search your team's notes and save new ones, with sources and full history.

Flow diagram: you ask your AI “What does our release policy say?”, the BaseMouse MCP server connects it to BaseMouse, and you get back an answer with sources.

BaseMouse is a place to keep your team's notes and documents, built so AI assistants can read and write them. This MCP server connects your AI to that knowledge base. It is handy if you want your AI to answer from your own written material instead of guessing, and to keep a record of what it did.

What is an MCP server? The 30-second version

On its own, your AI can only chat with what it already knows. An MCP server is a small helper that gives your AI a new skill or a connection to another service. This one connects your AI to BaseMouse, your document and notes repository. Once connected, your AI can look things up there and save new notes for you when you ask.

What this MCP server does

You ask your AI a question, like what your release policy says. The AI sends that request to this helper, which searches your BaseMouse workspace. BaseMouse finds the matching documents and sends back a tidy bundle with the text, where each piece came from, and which version it is. Your AI then writes an answer for you using that material, and can also save a new note back into BaseMouse if you want.

Flow diagram: you ask your AI “What does our release policy say?”, the BaseMouse MCP server connects it to BaseMouse, and you get back an answer with sources. Click to zoom

What you can do with it

  • Search your BaseMouse documents by keyword
  • Pull a ready-made context pack your AI can read
  • Filter results by document type or tag
  • Save a new note or decision into your workspace
  • Update an existing document by its id
  • See the full history of changes to a document
  • Follow links between related documents

Try asking your AI

  • “Search BaseMouse for our release policy and summarise it”
  • “Pull a context pack about memory and cite the sources”
  • “Save this decision as a note called deploy-freeze in BaseMouse”
  • “What documents are tagged memory in our workspace”

What it gives back to you

You get answers written in the chat, built from your own documents. Each answer can come with citations showing the document id and title, plus a version and checksum so you know which copy was used. If you save something, the AI tells you whether it created a new document or updated an existing one.

Before you start

What you need

  • A BaseMouse account with a paid plan, or the public demo
  • A BaseMouse API key (a kind of password that starts with bm_)
  • An AI tool that supports MCP, like Claude Code or Cursor

Good to know

The save tool can create or change documents in your workspace, so check what your AI is about to write before you let it.

Install it with your AI

Add BaseMouse 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 BaseMouse 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 4,066 MCP servers here for you.

Sign in Become a member

Who it's for

Teams and individuals who keep notes, policies, or project docs and want their AI to answer from those instead of guessing.