MCP server · GitHub
PR Genius MCP server
by zsxh1990
Ask your AI whether a pull request to a big open source project is likely to be accepted before you send it.
PR Genius is a helper that gives your AI advice about pull requests you want to send to other people's open source projects. It is built from real cases: 1355 patterns collected from 61 repositories, showing what got merged and what got closed. It is handy if you contribute to projects like React, Kubernetes, or httpx and want to avoid wasting your time on a PR that will be rejected.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you using what it already learned. 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 a library of real pull request cases and repository rules. So when you ask about a PR, the AI can look up patterns and policies from that library and answer with evidence instead of guessing.
What this MCP server does
You describe the pull request you are thinking about, with a title and the repository name. Your AI sends that to the PR Genius helper running on your computer. The helper checks it against its stored patterns, case studies, and repository profiles. It then tells you things like the chance of merging, what might go wrong, and what to change first. You get the answer right in the chat, in plain words.
Click to zoomWhat you can do with it
- Check the merge probability of a PR before you open it
- Get a simple go or no-go decision on a PR idea
- See which repository rules your PR might break
- Look up a repository profile with its policies and preferences
- Search past cases and patterns for a topic like connection timeout
- Track the status of PRs you already sent to other projects
- Get suggestions for updating your contributor profile
Try asking your AI
- “Should I open this PR to encode/httpx? Title: fix: timeout in connection pool”
- “Give me a go or no-go on this PR to kubernetes: docs: clarify pod lifecycle”
- “What are the rules for contributing to pydantic?”
- “Search the patterns for PRs that were closed because they were too large”
What it gives back to you
You get a written answer in the chat: a merge probability, a risk level, and a list of things to fix or watch out for. For status checks, you get a list of your open PRs with labels like needs rebase or stale review. For pattern searches, you get matching cases with short explanations. Nothing is changed on GitHub unless you run the GitHub Action yourself.
Before you start
What you need
- Python installed on your computer
- The prgenius-core package installed with pip
- An MCP client like Claude Desktop or another app that supports MCP servers
Good to know
The advice comes from past cases and may not match what a maintainer decides today, so treat it as a second opinion, not a guarantee.
Install it with your AI
Add PR Genius 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 PR Genius 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
Open source contributors and developers who send pull requests to large projects and want to know in advance whether they will be accepted.
