MCP server · Developer tools

ContribOS MCP server

Lets your AI check a repo's rules, draft issue briefs, and coach you before you open a pull request.

Developer tools GitHub Productivity For it and development Workplace & Productivity

ContribOS is a helper for people who want to contribute to open source projects on GitHub but keep getting their pull requests ignored or closed. It reads a project's rules, finds issues worth your time, and helps you write a clear proposal and explanation. It is handy for first-time or occasional contributors who want their work to actually get merged.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to another service. This one connects your AI to ContribOS, which looks at GitHub projects and their rules. So when you ask your AI to check a repo or help you prepare a pull request, it can use ContribOS to look things up and give you real answers instead of guesses.

What this MCP server does

You ask your AI something like whether a project welcomes outside contributors, or what its rules say about tests and AI use. Your AI passes that request to ContribOS through this MCP server. ContribOS then reads the project's files and history, and sends back what it found, with quotes from the actual files. Your AI shows you the result in the chat, and you decide what to do next. ContribOS never opens pull requests, posts comments, or claims issues for you.

What you can do with it

Check a project's contribution rules, AI policy, and testing expectations
Find open issues sorted into good bets, possible ones, and ones to skip
Draft a short proposal to post before you start coding
Get a brief on which files to read and what reviewers might ask
Run pre-submit checks on your explanation and test
Review and classify comments you got on your pull request
Check your writing for machine-sounding phrases before you post

Try asking your AI

“What are the contribution rules for pallets/flask?”
“Find me some good first issues in Python web projects”
“Help me write a proposal for this issue before I start coding”
“Check my explanation and test before I open a pull request”

What it gives back to you

You get back plain text answers in the chat: lists of issues with reasons, quoted rules from the project's own files, draft proposals, briefs on which files matter, and check results. Some answers include file names and line numbers so you can verify them yourself. It may also draft a pull request description or a reply to a reviewer. Nothing is posted anywhere unless you copy it and do it yourself.

Before you start

What you need

Python 3.10 or newer and git installed on your computer
A GitHub token (a kind of password for apps) for some features like finding issues or reviewing pull requests
An MCP-capable AI app like Claude Code, Cursor, or Codex

Good to know

It reads public project files and your GitHub activity, and it needs a GitHub token for some features, so treat that token like a password and keep it private.

Install it with your AI

Add ContribOS 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 ContribOS 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.