MCP server · Notes
Kage MCP server
by kage-core
Gives your coding AI a shared, checked memory of your project so it stops forgetting what it learned.
Kage is a memory helper for coding agents. It saves what your AI learns about your project, like decisions, bug fixes and how things fit together, as plain text files inside your own project folder. It is handy if you keep re-explaining the same things to your AI, or if you work on a team and want everyone's AI to start from the same knowledge.
What is an MCP server? The 30-second version
On its own, your AI can only chat. It does not remember your project between sessions, and it cannot look anything up on its own. An MCP server is a small helper program that gives your AI a new skill or a connection to something. This one connects your AI to Kage, a memory store kept inside your project folder, so your AI can read what was learned before and write down what it learns now.
What this MCP server does
You ask your AI to work on your project, and before it starts, Kage quietly hands it the notes that are still true about your code. As the AI works, Kage writes down the useful things it figures out, like why a fix was made or how a tricky deploy is done. Each note points at the actual files it talks about, and Kage checks those files really exist. If the code later changes and a note no longer matches, Kage stops showing that note until someone fixes it. You get an AI that starts each session already knowing your project, instead of a blank slate.
Click to zoomWhat you can do with it
- Recall what your team already decided about a part of the code
- Save a new lesson or decision so the next session knows it
- Check that saved notes still match the real code
- See which notes went stale after a change
- Turn a repeated procedure into a skill file your AI loads automatically
- See how much re-explaining Kage saved you
- Open a local dashboard of your project's memory
Try asking your AI
- “What do we already know about how the login flow works?”
- “Remember that we switched from Redis to Postgres for sessions, and why.”
- “Which of our saved notes are out of date after this change?”
- “How do I run the tests in this project?”
What it gives back to you
You get answers in the chat, drawn from notes that were checked against your real files. You also get short summaries of what was saved or what went stale, and lists of the files each note points to. If you ask for a dashboard, it opens in your browser and shows the notes, the links to code, and what is happening live. Nothing is a black box: every note is a plain text file you can open and read.
Before you start
What you need
- Node.js 18 or newer installed on your computer
- Your project folder, ideally one kept in git
- A coding AI that supports MCP, like Claude Code, Cursor or Claude Desktop
Good to know
Kage can write notes into your project folder and, through its orchestrator, run coding agents that change files, so try it on a project you can undo with git.
Install it with your AI
Add Kage 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 Kage 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.
Who it's for
Developers and small teams who use a coding AI every day and are tired of repeating the same context.
