MCP server · Developer tools
XRAY MCP server
Lets your AI read your code's structure, find functions and classes, and see what would break if you change something.
XRAY is a small helper that lets your AI assistant understand the shape of a code project. It works with Python, JavaScript, TypeScript and Go files. It is handy if you work with code and want your AI to answer questions like where a function lives or what uses it.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you. It cannot see the files on your computer or know how your project is put together. An MCP server is a small helper program that gives your AI a new skill. XRAY is that helper here: it reads your code folder and tells your AI what is inside, so the AI can answer questions about your project when you ask.
What this MCP server does
You point your AI at a folder on your computer and ask a question about the code. Your AI passes that request to XRAY. XRAY uses a tool called ast-grep to look at the actual code structure, not just plain text, so it can tell the difference between a function name and the same word in a comment. It sends back a clean list of files, functions, classes and where they are used. Your AI then explains the answer to you in the chat.
Click to zoomWhat you can do with it
- See the folder and file layout of a project
- Find a function or class by typing part of its name
- See the full signature and short description of each function
- Check which other places in the code use a function or class
- Estimate what would break if you change something
- Zoom into just one folder to keep results short
- Limit how deep the folder tree goes on big projects
Try asking your AI
- “Show me the structure of my project folder. use XRAY tools”
- “Find all functions with 'authenticate' in the name. use XRAY tools”
- “What would break if I change the authenticate method in UserService? use XRAY tools”
- “Which files call validate_user? use XRAY tools”
What it gives back to you
You get back plain answers in the chat: a folder tree, a list of matching functions or classes with their file and line number, or a list of places that use a symbol. Each result also shows the function signature and any short description written above it. Nothing is changed in your files. XRAY only reads and reports.
Before you start
What you need
- Python 3.10 or newer on your computer
- The uv tool installed (a small helper for running Python programs)
- Your AI assistant set up to use MCP servers, like Claude Desktop or Cursor
- A code project folder on your computer in Python, JavaScript, TypeScript or Go
Good to know
It only reads your code, so it will not change or delete anything, but it does look through the folder you point it at, so avoid pointing it at folders with private or secret files.
Install it with your AI
Add XRAY 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 XRAY 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, data scientists and anyone who reads or edits code and wants their AI to help them understand a project.
