MCP server · Developer tools
LayerMap MCP server
Your AI can trace what calls a function and which web routes a code change affects.
LayerMap is a helper for coding agents. It answers questions like "what calls this function?" and "if I change this, which web pages or endpoints break?" It is handy if you work on a codebase with other people and want your AI to understand how the pieces connect before it edits anything.
What is an MCP server? The 30-second version
On its own, your AI can only chat. An MCP server is a small helper program that gives your AI a new skill or a connection to something. LayerMap is that helper, and its skill is reading your codebase and drawing a map of how functions call each other. Once it is connected, your AI can look things up in that map for you when you ask.
What this MCP server does
You ask your AI a question about your code, like what calls a certain function. Your AI sends that question to LayerMap, which has already read your project and built a map of it. LayerMap follows the calls through your code, using each language's own compiler, and finds the web routes, jobs or commands that reach that function. Then your AI gets the answer back and explains it to you in the chat.
What you can do with it
- Find every place that calls a function, up to eight levels deep
- See which web routes or handlers a function is reached from
- List what a function itself calls
- Search your code for declarations by name, path or documentation
- Find every usage of a piece of code
- Check what your uncommitted edits affect, including related tests
Try asking your AI
- “What calls the createUser function and which routes reach it?”
- “If I change calculateTax, which endpoints are affected?”
- “Find every place that uses the Invoice type”
- “What did my uncommitted changes affect, and which tests should I run?”
What it gives back to you
You get back a list of callers or callees, each with its file, line numbers and the route it is registered under, like PUT /v1/feeds/{feedID}/mark-all-as-read. For a change check, you get the routes, jobs and commands your edit reaches, plus the tests related to it. Your AI then explains this in the chat in plain words. It never writes or runs tests for you.
Before you start
What you need
- Node.js 22.22 or later
- A Git repository (the project you want to map)
- macOS or Linux (Windows is experimental)
- For Java projects, a JDK 21 or later
Good to know
It only reads your code and sends nothing anywhere, but it cannot see calls the compiler cannot work out, like dependency injection or reflection, so a missing link does not always mean nothing is there.
Install it with your AI
Add LayerMap 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 LayerMap 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 4,361 MCP servers here for you.
Who it's for
Developers and anyone who works on a shared codebase and wants their AI to understand how the code connects before making changes.
