GitHub MCP Server

Official

GitHub's official MCP server for managing repos, issues, PRs, and workflows via natural language

How to install ↓ Compare GitHub source repository ↗

Category: Dev Tools #4 of 438
Stars: ★ 33.7k Very popular
Transport: stdio (local process) · Streamable HTTP
Runtime: Docker · Go · Hosted (no local runtime)
Credentials: Optional API key
License: MIT
Last commit: 7 days ago
Tools: 15

76FMRS · B

Maintained by the official GitHub team; toolsets cover the full repository lifecycle. Both local Docker and remote HTTP paths are clearly documented. This review is based on the README and server.json, not an actual handshake test — verify with a read-only toolset before enabling write access.

Strongest · Maintenance 18/20 Weakest · Reliability 13/20

Reliability

13/20

Security and permissions

14/20

Maintenance

18/20

Documentation

17/20

Setup experience

14/20

Test out of dateListed 2026-07-24

Read the FMRS scoring method →

Fit and risk

What it can accessUses the networkChanges third-party account data

Best for

Teams that want an AI assistant to directly operate on GitHub repos and collaboration workflows
Users already in the GitHub Copilot ecosystem who want a zero-deployment remote option

Not for

Scenarios where you don't want the assistant to have write access to repos (enable only read-only toolsets)
Environments with strict network isolation for private repos that can't reach the official remote endpoint

Required permissions

A personal access token (PAT) or OAuth App token; effective scope depends on the token's own permissions
Enabling toolsets like actions/issues/pull_requests grants write access — request tokens on a least-privilege basis

Risks and side effects

Write toolsets (creating/merging PRs, triggering workflows) can cause accidental changes if the token is overscoped — try a read-only toolset first
In hosted mode, credentials travel via the Authorization header — make sure the client-to-api.githubcopilot.com connection is trusted

Setup

Before you start

Runtime：Docker · Go · Hosted (no local runtime)

GITHUB_PERSONAL_ACCESS_TOKEN optionalsecret GitHub Personal Access Token created at github.com/settings/personal-access-tokens; takes precedence over OAuth login when set.

Other optional settings (5)

GITHUB_OAUTH_CALLBACK_PORT optional Fixed OAuth callback port (default 8085); must match the port published with -p when running in Docker.

GITHUB_TOOLSETS optional Comma-separated toolset allow-list such as repos,issues; use all to enable every toolset.

GITHUB_TOOLS optional Comma-separated list of individual tool names; can be combined additively with toolsets.

GITHUB_HOST optional Hostname for GitHub Enterprise Server or ghe.com, prefixed with https://.

GITHUB_INSIDERS optional Set to true to enable the insiders version with early-access experimental tools.

1) Local: docker pull ghcr.io/github/github-mcp-server, then start it with the config above — first run triggers an OAuth login, or supply a GITHUB_PERSONAL_ACCESS_TOKEN env var to skip it.
2) Remote: point your client's URL at https://api.githubcopilot.com/mcp/ with a PAT or App Token in the Authorization header — no local install needed.
3) Optionally restrict enabled toolsets with --toolsets; only the context toolset is enabled by default.

claude_desktop_config.json

{
  "mcpServers": {
    "github": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "-p", "127.0.0.1:8085:8085", "-e", "GITHUB_OAUTH_CALLBACK_PORT=8085", "-e", "GITHUB_PERSONAL_ACCESS_TOKEN", "ghcr.io/github/github-mcp-server"],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "<YOUR_GITHUB_TOKEN>"
      }
    }
  }
}

Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.

.vscode/mcp.json

{
  "servers": {
    "github": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-p",
        "127.0.0.1:8085:8085",
        "-e",
        "GITHUB_OAUTH_CALLBACK_PORT=8085",
        "-e",
        "GITHUB_PERSONAL_ACCESS_TOKEN",
        "ghcr.io/github/github-mcp-server"
      ],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "<YOUR_GITHUB_TOKEN>"
      }
    }
  }
}

Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).

Terminal

claude mcp add github -e 'GITHUB_PERSONAL_ACCESS_TOKEN=<YOUR_GITHUB_TOKEN>' -- docker run -i --rm -p 127.0.0.1:8085:8085 -e GITHUB_OAUTH_CALLBACK_PORT=8085 -e GITHUB_PERSONAL_ACCESS_TOKEN ghcr.io/github/github-mcp-server

Run it in a terminal; replace any <…> placeholders with your own values first.

Generate and validate client config

Check that it works

After connecting, call the get_me tool from the context toolset; if it returns your GitHub user profile, the server is running and authenticated.

Troubleshooting

OAuth callback fails: check whether local port 8085 is in use or blocked by a firewall
A toolset isn't active: verify the `--toolsets` flag or corresponding env var is spelled correctly
401 on the remote endpoint: confirm the PAT/App Token in the Authorization header is valid and not expired

Things to try

Once connected, you can ask your AI assistant things like:

List all open issues in octocorp/api and summarize them grouped by label.
Check why the latest GitHub Actions run on the main branch failed and summarize the failed job logs.
Create a red label named bug in the my-app repo, then apply it to issue #42.
List the high-severity Dependabot alerts in the web repo and explain which dependency each one affects.

Tools 15

context read-only

Tools that provide context about the current user and GitHub context (strongly recommended)

actions writes

GitHub Actions workflows and CI/CD operations

code_quality read-only

GitHub Code Quality related tools

code_security read-only

Code security related tools, such as GitHub Code Scanning

discussions writes

GitHub Discussions related tools

gists writes

GitHub Gist related tools

git read-only

GitHub Git API related tools for low-level Git operations

issues writes

GitHub Issues related tools

Show 7 more tools

labels writes

GitHub Labels related tools

notifications writes

GitHub Notifications related tools

orgs read-only

GitHub Organization related tools

projects writes

GitHub Projects related tools

pull_requests writes

Create, review, and manage pull requests

repos read-only

Repository management tools

users read-only

User lookup tools

Use cases

Create, comment on, and merge pull requests via natural language

Have an AI assistant diagnose GitHub Actions CI failures

Bulk-manage issue labels and notifications

Query code security scanning results directly from your IDE

Supported clients

Claude Desktop

Claude Code

VS Code

Cursor

Windsurf

JetBrains IDEs

Zed

Amp

Listed from the project's documentation, not tested by this site.

Overview

The official GitHub-maintained MCP server, exposing GitHub's core capabilities (repositories, issues, pull requests, Actions, code security scanning, Discussions, orgs and projects) through grouped toolsets. Runs locally via Docker, or connects directly to GitHub's hosted remote Streamable HTTP endpoint (api.githubcopilot.com/mcp/) with no local install required.

Similar servers

Context7 80 · B

Upstash's official server providing up-to-date third-party library docs for AI coding assistants

★ 63.3k · Tools 2 Compare with this →

NPM Sentinel MCP Server 79 · B

AI-powered NPM package analysis MCP server

★ 18 · Tools 19 Compare with this →

MartinLoop MCP Server 79 · B

An independent control layer that gives AI coding agents budgets, brakes, and receipts

★ 413 Compare with this →

FastMCP 75 · B

A TypeScript framework for building MCP servers

★ 3.3k Compare with this →

Compare with other MCP servers

Source revision e3809fe91c75 Data synced 2026-10-19 Read the FMRS scoring method