GitHub CLI MCP Server

GitHub CLI MCP Server

An MCP server that wraps the GitHub CLI to provide comprehensive access to repository management, pull requests, issues, and workflows. It enables users to perform complex GitHub operations and interact with the GitHub API through a standardized interface.

Category
访问服务器

README

GitHub CLI MCP Server

An MCP (Model Context Protocol) server that wraps the GitHub CLI (gh) tool, providing comprehensive access to GitHub functionality through a standardized interface.

Features

This server exposes the following GitHub CLI functionality:

Repository Management

  • gh_repo_list - List repositories for a user or organization
  • gh_repo_view - View information about a repository
  • gh_repo_create - Create a new repository

Pull Requests

  • gh_pr_list - List pull requests in a repository
  • gh_pr_view - View a pull request
  • gh_pr_create - Create a pull request
  • gh_pr_merge - Merge a pull request
  • gh_pr_checkout - Check out a pull request locally

Issues

  • gh_issue_list - List issues in a repository
  • gh_issue_view - View an issue
  • gh_issue_create - Create an issue
  • gh_issue_close - Close an issue

GitHub Actions

  • gh_workflow_list - List workflows in a repository
  • gh_workflow_view - View details about a workflow
  • gh_run_list - List recent workflow runs
  • gh_run_view - View details about a workflow run

Releases

  • gh_release_list - List releases in a repository
  • gh_release_view - View information about a release
  • gh_release_create - Create a new release

Search

  • gh_search_repos - Search for repositories
  • gh_search_issues - Search for issues and pull requests

Gists

  • gh_gist_list - List your gists
  • gh_gist_create - Create a new gist

Other

  • gh_api - Make authenticated GitHub API requests
  • gh_auth_status - View authentication status
  • gh_status - Print information about issues, PRs, and notifications

Prerequisites

  • Python 3.10 or higher
  • GitHub CLI (gh) installed and authenticated
    • Install: https://cli.github.com/
    • Authenticate: gh auth login

Installation

From GitHub

git clone https://github.com/munch-group/gh-mcp.git
cd gh-mcp
pip install -e .

Prerequisites

  • Python 3.10 or higher
  • GitHub CLI (gh) installed and authenticated
    • Install: https://cli.github.com/
    • Authenticate: gh auth login

Verify GitHub CLI is authenticated:

gh auth status

Usage

With Claude Desktop

# After installing with pip
claude mcp add gh gh-mcp-server

# Or run directly
claude mcp add gh python /path/to/gh-mcp/server.py

Or add manually to your Claude Desktop configuration:

{
  "mcpServers": {
    "gh": {
      "command": "python",
      "args": ["/path/to/gh-mcp/server.py"]
    }
  }
}

Standalone

Run the server directly:

python server.py

The server communicates via stdin/stdout using the MCP protocol.

Examples

Once configured, you can use the tools through your MCP client. For example, with Claude Code:

  • "List all open pull requests in my repository"
  • "Create a new issue titled 'Bug in login page'"
  • "Show me the status of workflow run #123"
  • "Search for Python repositories with more than 1000 stars"
  • "View release information for version v1.0.0"

Tool Parameters

Most tools accept optional parameters for filtering and customization. See the tool descriptions in the code for full parameter details.

Common parameters include:

  • repository: Specify repository in OWNER/REPO format (defaults to current repo)
  • limit: Maximum number of items to return
  • state: Filter by state (open, closed, all, etc.)
  • web: Open result in web browser instead of returning data

Error Handling

The server handles errors gracefully and returns informative error messages:

  • Command timeouts (60 seconds)
  • Invalid parameters
  • gh CLI errors
  • Authentication issues

Security

This server executes gh commands with the permissions of the authenticated GitHub CLI user. Ensure you trust any client using this server, as it can perform actions on your behalf such as:

  • Creating/modifying repositories
  • Creating/closing issues and pull requests
  • Triggering workflows
  • Creating releases

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选