Server profile

GitHub MCP Server

GitHub MCP Server connects AI tools to repository content, issues, pull requests, and platform workflows. Developers can use GitHub-hosted access or run a local server for conversational project management and code analysis.

Server facts

GitHub MCP Server

Project

Author
github
License
MIT
Category
Version Control

Tech

Runtime / language
goGo
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
33,663
Last commit
Data as of

Tags

  • Github
  • Github Actions
  • Issues
  • Pull Requests
  • Repositories

Overview

GitHub MCP Server brings GitHub context and operations into compatible AI tools. The README describes repository browsing, file searches, commit analysis, issue management, and pull request work as core uses. It also covers GitHub Actions monitoring, release management, security findings, Dependabot alerts, discussions, notifications, and team activity. Developers can therefore ask an assistant to investigate project state or coordinate several related platform tasks without treating repository files as the only available context. Individual tool identifiers are not enumerated in the supplied README excerpt, so its capabilities are described here at the workflow level.

GitHub offers a hosted remote server and a local alternative. Remote setup requires a compatible host and applicable policies, with OAuth support depending on the host application's integration; personal access tokens are another option. Local execution can use Docker and supports either a token or a documented OAuth login flow. The README stresses granting only permissions appropriate to the intended agent tasks and keeping credentials out of version control. Enterprise configuration differs by deployment: Enterprise Cloud with data residency has a remote option, while Enterprise Server requires the local route. Toolset selection and an insiders mode offer additional configuration choices. This is a suitable integration for teams wanting GitHub-native context and actions, provided authentication and host support are configured deliberately.

Install & configure

Requirements

  • Docker installed and running for local container execution
  • An MCP-compatible host
  • GitHub authentication and appropriate account permissions
Documented launch / install command
docker run -i --rm -e GITHUB_PERSONAL_ACCESS_TOKEN ghcr.io/github/github-mcp-server

The command uses the README's local PAT-based Docker example. The remote URL uses HTTP and supports OAuth where the host implements it, or PAT authentication. Grant only the permissions required for your tasks.

Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Desktop configuration
{
  "mcpServers": {
    "github-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "GITHUB_PERSONAL_ACCESS_TOKEN",
        "ghcr.io/github/github-mcp-server"
      ],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "<your GitHub personal access token with appropriate permissions>"
      }
    }
  }
}

Read the Claude Desktop setup guide

Config file · Project: .cursor/mcp.json

User: ~/.cursor/mcp.json

The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.

Cursor configuration
{
  "mcpServers": {
    "github-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "GITHUB_PERSONAL_ACCESS_TOKEN",
        "ghcr.io/github/github-mcp-server"
      ],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "<your GitHub personal access token with appropriate permissions>"
      }
    }
  }
}

Read the Cursor setup guide

Config file · Workspace: .vscode/mcp.json

For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.

VS Code configuration
{
  "servers": {
    "github-mcp-server": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "GITHUB_PERSONAL_ACCESS_TOKEN",
        "ghcr.io/github/github-mcp-server"
      ],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "<your GitHub personal access token with appropriate permissions>"
      }
    }
  }
}

Read the VS Code setup guide

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.

Windsurf configuration
{
  "mcpServers": {
    "github-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "GITHUB_PERSONAL_ACCESS_TOKEN",
        "ghcr.io/github/github-mcp-server"
      ],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "<your GitHub personal access token with appropriate permissions>"
      }
    }
  }
}

Read the Windsurf setup guide

Config file · Project scope: .mcp.json at the repository root

The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Code configuration
{
  "mcpServers": {
    "github-mcp-server": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "GITHUB_PERSONAL_ACCESS_TOKEN",
        "ghcr.io/github/github-mcp-server"
      ],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "<your GitHub personal access token with appropriate permissions>"
      }
    }
  }
}

Read the Claude Code setup guide

Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.

Tools

No individual tool names were confirmed in the source material. Check the repository for its current tool list.

Names, permissions, and defaults can change. Check the current upstream documentation before granting access.

Use cases

  • Explore repositories, files, and commit history through an assistant.
  • Triage issues and manage pull request workflows.
  • Investigate failed GitHub Actions runs and development pipeline activity.
  • Review security findings and Dependabot alerts.
  • Coordinate discussions, notifications, and team project work.

Strengths

  • Connects agents to multiple GitHub workflows beyond source files.
  • Provides both GitHub-hosted and local deployment options.
  • Documents OAuth, personal access tokens, and enterprise configuration.

Limitations

  • OAuth support and configuration vary by MCP host.
  • GitHub Enterprise Server cannot use the hosted remote service.
  • Individual tool names are not stated in the supplied README excerpt.

Frequently asked questions

No. GitHub also provides a hosted remote endpoint for MCP hosts that support remote connections.

Yes. The README documents local OAuth login and Docker callback-port configuration. A PAT remains an alternative and takes precedence when configured.

No. The README directs Enterprise Server users to local server configuration.

Use the minimum permissions needed for your intended operations and keep the token out of version control.

Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.

Related MCP servers

GitHub MCP Server

Version Control

Expose GitHub repository, issue, and pull-request operations to an assistant. The supplied tool catalog covers file changes, code search, branching, reviews, and merges, but its README lacks setup details.

Playwright MCP

Browser Automation

Playwright MCP lets AI assistants operate browsers using structured accessibility data. It suits agents that need persistent page context, interactive exploration, and browser inspection without a vision model.

Firecrawl MCP Server

Search & Web Data

Firecrawl MCP connects AI agents to web search, scraping, crawling, and live browser interaction. It offers hosted access or a local server for collecting structured web context and running research tasks.

Framelink MCP for Figma

Design & Creative

Framelink supplies coding agents with selected Figma metadata and image assets. Developers can bring a design link into an editor conversation and use its underlying layout details while implementing an interface.

21st.dev Magic AI Agent

Design & Creative

21st.dev Magic AI Agent turns natural-language requests into customizable UI components inside supported coding tools. It combines component-library inspiration, previews, TypeScript support, and brand assets for interface development.

Browserbase MCP Server

Browser Automation

Browserbase MCP Server lets assistants operate cloud browser sessions through Browserbase and Stagehand. Six tools handle sessions, navigation, page actions, observation, and extraction, with hosted and self-hosted connection options.

MiniMax MCP

AI Models & Agents

MiniMax MCP exposes MiniMax media APIs to compatible AI clients for speech, voice work, images, video, and music. It supports local stdio use and SSE deployment, with region-specific API credentials and configurable resource output.

BlenderMCP

Games & 3D

BlenderMCP links AI assistants to Blender for scene inspection, object and material changes, and Python execution. Optional asset integrations add Poly Haven downloads, Sketchfab models, and generated 3D assets.