MCP server · GitHub
GitHub GraphQL MCP server
by QuentinCody
Lets your AI ask GitHub questions about repos, issues and pull requests and get answers back.
This is a small helper that connects your AI assistant to GitHub, the site where code and projects live. Once it is set up, you can ask your AI things about GitHub in normal words, and it will go and fetch the details for you. It is handy if you work with developers or need to look up project information without clicking around GitHub yourself.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you. It cannot see your GitHub account or look anything up there. An MCP server is a small helper program that gives your AI a new skill, and this one gives it a connection to GitHub. So when you ask a question about a repository or a user, your AI passes the request to this helper, the helper asks GitHub, and the answer comes back to you in the chat.
What this MCP server does
You type a question about GitHub, like asking about a project or a person's profile. Your AI turns that into a GitHub request and hands it to this helper. The helper sends the request to GitHub using a special key you set up. GitHub sends back the details, and the helper passes them to your AI. Your AI then shows you the answer in plain words in the chat.
Click to zoomWhat you can do with it
- Look up details about any public repository, like its description and star count
- Search GitHub for repositories matching words or filters you give
- Get a user's profile, bio and their most popular projects
- Check information about issues and pull requests in a project
- Run a custom GitHub query when you know exactly what you want
Try asking your AI
- “Show me the details of the octocat Hello-World repository”
- “Search GitHub for popular Python projects about machine learning”
- “What is octocat's bio and what are their top repositories?”
- “Find open issues in the microsoft vscode repository”
What it gives back to you
You get back plain answers in the chat: names, descriptions, star counts, links, user bios and lists of repositories or issues. If you asked for a search, you get a short list of matching projects with their key details. If you asked about a person, you get their profile summary. Everything shows up as normal text you can read and copy.
Before you start
What you need
- Python 3.10 or newer installed on your computer
- A GitHub Personal Access Token (a kind of password you create in your GitHub settings)
- The Claude desktop app if you want to use it there
Good to know
It can run any GitHub query you give it, including ones that change or delete things, so be careful with what you ask it to do.
Install it with your AI
Add GitHub GraphQL 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 GitHub GraphQL 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
People who work with developers or manage projects on GitHub and want quick answers without clicking through the site.
