MCP Servers · Official

GitHub MCP Server

Lets AI agents access GitHub repositories, issues, pull requests, and Actions through controlled tools.

32.3k StarsMITGoUpdated 3 days ago
01

Project overview

Lets AI agents access GitHub repositories, issues, pull requests, and Actions through controlled tools. Its core areas include Repository search, Issue management, Pull requests, Actions. Start with the repository documentation and the smallest practical scope before adopting it broadly.

02

Core capabilities

01

Repository search

Exposes Repository search to compatible clients through MCP tools.

02

Issue management

Exposes Issue management to compatible clients through MCP tools.

03

Pull requests

Exposes Pull requests to compatible clients through MCP tools.

04

Actions

Exposes Actions to compatible clients through MCP tools.

03

Setup and connection

This usage path is based on the current public documentation for GitHub MCP Server. Complete the steps in order before using it from your agent.

AI AGENT INSTALL

Let an AI Agent install it

Send this prompt to Codex, Claude Code, or another AI agent that can work with your local environment.

Help me install this MCP: GitHub MCP Server
Project URL: https://github.com/github/github-mcp-server

Read the README and installation files first, confirm the current environment and target directory, then follow the project's documented installation method. Run a minimal verification task afterward and report the install location, steps, and result. Ask before requesting credentials, additional permissions, overwriting files, or performing risky actions.
01Before you start
  • Prepare a compatible agent or runtime
  • Confirm access to the local files or services required by the project
02Copy the install command or configuration
{
  "servers": {
    "github": {
      "type": "http",
      "url": "https://api.githubcopilot.com/mcp/"
    }
  }
}
03Complete the setup steps
  1. 1
    Apply the configuration

    Use the command or configuration above to add the resource to the current agent environment.

  2. 2
    Complete required setup

    Complete path, permission, or connection settings for the current runtime.

  3. 3
    Run a minimal task

    Run a minimal task in the agent. If the resource is recognized and returns the documented type of result, the setup is active.

How to verify the setup

Run a minimal task in the agent. If the resource is recognized and returns the documented type of result, the setup is active.

04

Use cases

SCENARIO 01

You need to connect an AI agent to tools, browsers, code, or data through MCP

SCENARIO 02

Your current task needs Repository search or Issue management

05

Assessment

Why it may be useful

  • You need to connect an AI agent to tools, browsers, code, or data through MCP
  • Your current task needs Repository search or Issue management

What to know first

  • Your agent does not support MCP or you cannot provide the required environment
  • You want to use it in production without reading the repository documentation or reviewing permissions
06

README

GitHub MCP Server


Overview

Lets AI agents access GitHub repositories, issues, pull requests, and Actions through controlled tools. GitHub's official MCP Server.

Getting started

  • This usage path is based on the current public documentation for GitHub MCP Server. Complete the steps in order before using it from your agent.
  • Project focus: Lets AI agents access GitHub repositories, issues, pull requests, and Actions through controlled tools.
  • Published characteristics: Remote and local, OAuth or PAT, Optional read-only mode.
  • Run a minimal task in the agent. If the resource is recognized and returns the documented type of result, the setup is active.

Configuration

{
  "servers": {
    "github": {
      "type": "http",
      "url": "https://api.githubcopilot.com/mcp/"
    }
  }
}
Read the complete README on GitHub