MCP server · Developer tools
stalemap MCP server
by Umair
Tells your AI coding helper which npm packages changed after it learned them, so it stops writing old code.
stalemap is a helper for people who use AI coding assistants like Claude Code or Cursor on JavaScript and TypeScript projects. AI models learn about libraries from old data, so they often write code for versions that no longer exist. stalemap finds the packages in your project that changed since your AI's learning cutoff and quietly tells it what is different.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you and write code from what it already knows. 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 stalemap, which looks at your project's npm packages and the changes they went through. When you ask your AI to write or fix code, it can quietly check with stalemap first and use the right, current version of the library.
What this MCP server does
You ask your AI to write or edit code in your project. The AI asks stalemap about the packages involved, and stalemap looks up what changed in each one since the AI's training cutoff. It compares the old and new versions of the package's type files, reads release notes and upgrade guides, and ranks what matters for the code you actually use. The AI then writes code that matches the version you have pinned, and if it slips up, the guard catches the type error and explains the fix. You get working code and fewer confusing errors about APIs that no longer exist.
What you can do with it
- Find out which of your npm packages changed after your AI's training cutoff
- Write a short ranked notes block into AGENTS.md or CLAUDE.md so your AI reads it first
- Catch type errors caused by changed library APIs right after each edit
- Search type changes, release notes and upgrade guides in plain words
- Set up the notes, MCP server and guard for Claude Code, Cursor, Codex or OpenCode in one command
- Run a check in CI that fails when the notes are missing or out of date
- Comment on pull requests that change dependencies, showing what changed
Try asking your AI
- “Set up stalemap for my project so my AI knows which packages changed”
- “Search stalemap for how to resolve an alias in next.config”
- “Why is my AI writing maxSteps when the AI SDK no longer accepts it”
- “Run the stalemap guard on my TypeScript files and explain the errors”
What it gives back to you
You get a short ranked list of changes, written into a notes block in AGENTS.md or CLAUDE.md, with the package name, old and new version, and the specific APIs that changed. In the chat, your AI gets the same notes plus matching sections from release notes or upgrade guides when it hits an error. Search results come back as a ranked list of changes with their sources. The guard reports compile errors and points at the note that explains each one.
Before you start
What you need
- Node.js installed on your computer (the tool runs with npx)
- A JavaScript or TypeScript project with a package.json file
- An AI coding assistant that supports MCP, such as Claude Code, Cursor, Codex or OpenCode
Good to know
It reads your project files and sends package names, versions and type diffs to services like the npm registry, GitHub and, with some options, Claude, though your source code is never uploaded.
Install it with your AI
Add stalemap 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 stalemap 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
Developers and technical teams using AI coding assistants on JavaScript or TypeScript projects who keep hitting errors from outdated library knowledge.




