MCP server · Developer tools
ontomics MCP server
Lets your AI read your codebase's concepts, naming rules, and similar functions in one quick step.
ontomics is a helper that builds a map of what your code is really about: the main ideas, the names your team uses, and which functions do similar things. It is made for people who work with a codebase and want their AI assistant to understand it without reading hundreds of files. If you use ChatGPT or Claude to ask questions about code, this makes those answers faster and more accurate.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you. It does not know your project unless you paste files into the conversation. An MCP server is a small helper program that gives your AI a new skill or a connection to something outside the chat. Here, ontomics is that helper: it reads your code folder, builds an index of the ideas inside, and hands your AI the right pieces when you ask a question.
What this MCP server does
You ask your AI something like what does this word mean in our code. Your AI sends that question to ontomics. ontomics looks at its pre-built index of your project, finds the matching concepts, naming patterns, and similar functions, and sends back a short, focused answer. Your AI then explains it to you in plain words. All of this happens on your own computer, so your code never leaves your machine.
Click to zoomWhat you can do with it
- Find every place a term is used and what it means in your project
- List the main ideas and naming rules your codebase follows
- Check whether a new name fits your project's style
- Suggest a name that matches how your team already names things
- Find functions that behave similarly even if they are named differently
- See what new or changed concepts appeared since a past version
- Export your project's vocabulary to share with another repo
Try asking your AI
- “What does 'transform' mean in this codebase?”
- “What are the main domain concepts in this project?”
- “Is 'process_data' a good name here, or should I rename it?”
- “Which functions behave like spatial_transform?”
What it gives back to you
You get short, focused answers in the chat: lists of concepts, naming suggestions, function names with file locations, or a summary of what changed. The answers are compact, so you do not have to scroll through walls of code. If you ask for a comparison, you may see a small ranked list of similar functions. Everything is written in plain language your AI can explain back to you.
Before you start
What you need
- A git repository (a project folder with a .git folder inside)
- Node.js 18 or newer if you install with npm
- Rust and Cargo if you build from source
- The Claude desktop app or another tool that supports MCP servers
Good to know
It reads your source code and builds an index on your machine, so make sure you are comfortable with that; it does not change your code.
Install it with your AI
Add ontomics 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 ontomics 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, tech leads, and anyone who asks an AI assistant questions about an existing codebase and wants fast, accurate answers.
