MCP server · Developer tools

CodeHealth MCP server

Ask your AI to scan a codebase for dead code, circular imports, coupling, and architecture drift.

Developer tools Coding For it and development Developer Tools

CodeHealth MCP is a small helper that lets your AI look at a codebase and report on its health. It finds things like unused code, loops in imports, and messy connections between parts of a project. It is handy for developers and anyone who reviews code and wants a quick second opinion.

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 a service. This one connects your AI to a code analysis engine, so when you ask about a project, the AI can actually run checks on it and bring back findings instead of guessing.

What this MCP server does

You ask your AI something like "run a full health scan on this repo." The AI passes that request to this helper. The helper reads the code, runs several checks (dead code, circular imports, coupling, and layer violations), and hands the results back. The AI then shows you a list of findings with file and line numbers, plus a health score from 0 to 100 and suggested fixes.

Flow diagram: you ask your AI “Run a full health scan on my repo”, on your own computer the CodeHealth MCP server works with your code on your computer, and you get back findings and a health score.

Click to zoom

What you can do with it

Find unused functions, classes, and modules in a project
Spot circular import loops between files
Measure how tightly connected modules are and where refactoring might help
Check whether code breaks layer boundaries like UI reaching into data
Run one combined scan that returns a 0 to 100 health score
Ask for a plain-language explanation of any single finding
Check whether a remote MCP endpoint is actually healthy, not just returning HTTP 200

Try asking your AI

“Run a full health scan on /path/to/my/repo”
“Find circular dependencies in the frontend folder”
“Check coupling metrics in src/services”
“Explain this finding about the unused module in utils”

What it gives back to you

You get back a list of findings, each with a type, a severity (critical, warning, or info), the file and line, and a suggested fix. A full scan also returns a health score from 0 to 100 and a short list of prioritized actions. The AI shows this in the chat, usually as a readable summary or table you can scroll through.

Before you start

What you need

Node.js installed on your computer
The project files you want to analyze, either on your machine or a GitHub link
An LLM API key (a kind of password for AI services) if you want the AI-written explanations
A GitHub token only if you want to scan private repositories

Good to know

It reads your project files, so only point it at code you are allowed to share, and be aware that a full scan can send file contents to the AI provider you configured.

Install it with your AI

Add CodeHealth 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 CodeHealth 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.