MCP server · Developer tools
AI Distiller MCP server
by janreges
Lets your AI read a tidy summary of your codebase so it writes code that fits your project.
AI Distiller is a helper that takes a big pile of code and boils it down to just the important parts: the names of functions, the types they use, and how they connect. It is made for people who use AI coding tools like Claude Code, Cursor, or Copilot on large projects and keep getting code that looks fine but does not fit. If your AI keeps guessing at how your code works, this gives it the real picture.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you. It cannot see your project files unless you paste them in, and big projects are far too large to paste. 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 AI Distiller, which reads your code folder and hands back a short, clear summary of how your code is built, so the AI can use your existing functions correctly instead of inventing its own.
What this MCP server does
You ask your AI a question about your project, like how a certain function is meant to be used. The AI passes that request to this helper. The helper scans your code folder, picks out the public parts of your classes and functions, and skips the long inner workings. It sends back a compact summary, usually only a small slice of the original size. Your AI then writes its answer using the real names, types, and structure from your project.
Click to zoomWhat you can do with it
- Get a short summary of your whole code folder
- Look up the exact names and inputs of functions in your project
- See how different files and functions call each other
- Focus on one file or one module instead of the whole project
- Include or leave out comments, private parts, and function bodies
- Prepare a ready-made prompt for a deeper code review
- Check how much smaller the summary is compared to the original code
Try asking your AI
- “Summarize the public functions in my src folder so I can see what is available”
- “What arguments does the createUser function take, and what does it return?”
- “Show me how the files in my project depend on each other, starting from main.py”
- “Distill just the api module and tell me which functions I can reuse”
What it gives back to you
You get back a short, readable summary of your code in the chat. It lists function names, their inputs and outputs, and the types involved, without the long inner code. Sometimes it also shows a small note about how much was trimmed, like the original size versus the summary size. Your AI then uses that summary to answer your question or write new code.
Before you start
What you need
- The Claude desktop app or another AI tool that supports MCP servers
- Node.js installed on your computer (the free program that runs this helper)
- A code project folder on your computer that you want the AI to understand
Good to know
It reads your project files, so only point it at code you are comfortable having an AI look at.
Install it with your AI
Add AI Distiller 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 AI Distiller 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 technical teams who use AI coding assistants on large projects and want the AI to stop guessing at how their code works.
