GitHub MCP Server

GitHub MCP Server

joon1251ai

开发者工具
访问服务器

README

GitHub MCP Server

MCP Server for the GitHub API, enabling file operations, repository management, search functionality, and more.

Features

  • Automatic Branch Creation: When creating/updating files or pushing changes, branches are automatically created if they don't exist
  • Comprehensive Error Handling: Clear error messages for common issues
  • Git History Preservation: Operations maintain proper Git history without force pushing
  • Batch Operations: Support for both single-file and multi-file operations
  • Advanced Search: Support for searching code, issues/PRs, and users

Tools

  1. create_or_update_file

    • Create or update a single file in a repository
    • Inputs:
      • owner (string): Repository owner (username or organization)
      • repo (string): Repository name
      • path (string): Path where to create/update the file
      • content (string): Content of the file
      • message (string): Commit message
      • branch (string): Branch to create/update the file in
      • sha (optional string): SHA of file being replaced (for updates)
    • Returns: File content and commit details
  2. push_files

    • Push multiple files in a single commit
    • Inputs:
      • owner (string): Repository owner
      • repo (string): Repository name
      • branch (string): Branch to push to
      • files (array): Files to push, each with path and content
      • message (string): Commit message
    • Returns: Updated branch reference
  3. search_repositories

    • Search for GitHub repositories
    • Inputs:
      • query (string): Search query
      • page (optional number): Page number for pagination
      • perPage (optional number): Results per page (max 100)
    • Returns: Repository search results
  4. create_repository

    • Create a new GitHub repository
    • Inputs:
      • name (string): Repository name
      • description (optional string): Repository description
      • private (optional boolean): Whether repo should be private
      • autoInit (optional boolean): Initialize with README
    • Returns: Created repository details
  5. get_file_contents

    • Get contents of a file or directory
    • Inputs:
      • owner (string): Repository owner
      • repo (string): Repository name
      • path (string): Path to file/directory
      • branch (optional string): Branch to get contents from
    • Returns: File/directory contents
  6. create_issue

    • Create a new issue
    • Inputs:
      • owner (string): Repository owner
      • repo (string): Repository name
      • title (string): Issue title
      • body (optional string): Issue description
      • assignees (optional string[]): Usernames to assign
      • labels (optional string[]): Labels to add
      • milestone (optional number): Milestone number
    • Returns: Created issue details
  7. create_pull_request

    • Create a new pull request
    • Inputs:
      • owner (string): Repository owner
      • repo (string): Repository name
      • title (string): PR title
      • body (optional string): PR description
      • head (string): Branch containing changes
      • base (string): Branch to merge into
      • draft (optional boolean): Create as draft PR
      • maintainer_can_modify (optional boolean): Allow maintainer edits
    • Returns: Created pull request details
  8. fork_repository

    • Fork a repository
    • Inputs:
      • owner (string): Repository owner
      • repo (string): Repository name
      • organization (optional string): Organization to fork to
    • Returns: Forked repository details
  9. create_branch

    • Create a new branch
    • Inputs:
      • owner (string): Repository owner
      • repo (string): Repository name
      • branch (string): Name for new branch
      • from_branch (optional string): Source branch (defaults to repo default)
    • Returns: Created branch reference
  10. list_issues

    • List and filter repository issues
    • Inputs:
      • owner (string): Repository owner
      • repo (string): Repository name
      • state (optional string): Filter by state ('open', 'closed', 'all')
      • labels (optional string[]): Filter by labels
      • sort (optional string): Sort by ('created', 'updated', 'comments')
      • direction (optional string): Sort direction ('asc', 'desc')
      • since (optional string): Filter by date (ISO 8601 timestamp)
      • page (optional number): Page number
      • per_page (optional number): Results per page
    • Returns: Array of issue details
  11. update_issue

    • Update an existing issue
    • Inputs:
      • owner (string): Repository owner
      • repo (string): Repository name
      • issue_number (number): Issue number to update
      • title (optional string): New title
      • body (optional string): New description
      • state (optional string): New state ('open' or 'closed')
      • labels (optional string[]): New labels
      • assignees (optional string[]): New assignees
      • milestone (optional number): New milestone number
    • Returns: Updated issue details
  12. add_issue_comment

    • Add a comment to an issue
    • Inputs:
      • owner (string): Repository owner
      • repo (string): Repository name
      • issue_number (number): Issue number to comment on
      • body (string): Comment text
    • Returns: Created comment details
  13. search_code

    • Search for code across GitHub repositories
    • Inputs:
      • q (string): Search query using GitHub code search syntax
      • sort (optional string): Sort field ('indexed' only)
      • order (optional string): Sort order ('asc' or 'desc')
      • per_page (optional number): Results per page (max 100)
      • page (optional number): Page number
    • Returns: Code search results with repository context
  14. search_issues

    • Search for issues and pull requests
    • Inputs:
      • q (string): Search query using GitHub issues search syntax
      • sort (optional string): Sort field (comments, reactions, created, etc.)
      • order (optional string): Sort order ('asc' or 'desc')
      • per_page (optional number): Results per page (max 100)
      • page (optional number): Page number
    • Returns: Issue and pull request search results
  15. search_users

    • Search for GitHub users
    • Inputs:
      • q (string): Search query using GitHub users search syntax
      • sort (optional string): Sort field (followers, repositories, joined)
      • order (optional string): Sort order ('asc' or 'desc')
      • per_page (optional number): Results per page (max 100)
      • page (optional number): Page number
    • Returns: User search results
  16. list_commits

  • Gets commits of a branch in a repository
  • Inputs:
    • owner (string): Repository owner
    • repo (string): Repository name
    • page (optional string): page number
    • per_page (optional string): number of record per page
    • sha (optional string): branch name
  • Returns: List of commits
  1. get_issue
  • Gets the contents of an issue within a repository
  • Inputs:
    • owner (string): Repository owner
    • repo (string): Repository name
    • issue_number (number): Issue number to retrieve
  • Returns: Github Issue object & details
  1. get_pull_request
  • Get details of a specific pull request
  • Inputs:
    • owner (string): Repository owner
    • repo (string): Repository name
    • pull_number (number): Pull request number
  • Returns: Pull request details including diff and review status
  1. list_pull_requests
  • List and filter repository pull requests
  • Inputs:
    • owner (string): Repository owner
    • repo (string): Repository name
    • state (optional string): Filter by state ('open', 'closed', 'all')
    • head (optional string): Filter by head user/org and branch
    • base (optional string): Filter by base branch
    • sort (optional string): Sort by ('created', 'updated', 'popularity', 'long-running')
    • direction (optional string): Sort direction ('asc', 'desc')
    • per_page (optional number): Results per page (max 100)
    • page (optional number): Page number
  • Returns: Array of pull request details
  1. create_pull_request_review
  • Create a review on a pull request
  • Inputs:
    • owner (string): Repository owner
    • repo (string): Repository name
    • pull_number (number): Pull request number
    • body (string): Review comment text
    • event (string): Review action ('APPROVE', 'REQUEST_CHANGES', 'COMMENT')
    • commit_id (optional string): SHA of commit to review
    • comments (optional array): Line-specific comments, each with:
      • path (string): File path
      • position (number): Line position in diff
      • body (string): Comment text
  • Returns: Created review details
  1. merge_pull_request
  • Merge a pull request
  • Inputs:
    • owner (string): Repository owner
    • repo (string): Repository name
    • pull_number (number): Pull request number
    • commit_title (optional string): Title for merge commit
    • commit_message (optional string): Extra detail for merge commit
    • merge_method (optional string): Merge method ('merge', 'squash', 'rebase')
  • Returns: Merge result details
  1. get_pull_request_files
  • Get the list of files changed in a pull request
  • Inputs:
    • owner (string): Repository owner
    • repo (string): Repository name
    • pull_number (number): Pull request number
  • Returns: Array of changed files with patch and status details
  1. get_pull_request_status
  • Get the combined status of all status checks for a pull request
  • Inputs:
    • owner (string): Repository owner
    • repo (string): Repository name
    • pull_number (number): Pull request number
  • Returns: Combined status check results and individual check details
  1. update_pull_request_branch
  • Update a pull request branch with the latest changes from the base branch (equivalent to GitHub's "Update branch" button)
  • Inputs:
    • owner (string): Repository owner
    • repo (string): Repository name
    • pull_number (number): Pull request number
    • expected_head_sha (optional string): The expected SHA of the pull request's HEAD ref
  • Returns: Success message when branch is updated
  1. get_pull_request_comments
  • Get the review comments on a pull request
  • Inputs:
    • owner (string): Repository owner
    • repo (string): Repository name
    • pull_number (number): Pull request number
  • Returns: Array of pull request review comments with details like the comment text, author, and location in the diff
  1. get_pull_request_reviews
  • Get the reviews on a pull request
  • Inputs:
    • owner (string): Repository owner
    • repo (string): Repository name
    • pull_number (number): Pull request number
  • Returns: Array of pull request reviews with details like the review state (APPROVED, CHANGES_REQUESTED, etc.), reviewer, and review body

Search Query Syntax

Code Search

  • language:javascript: Search by programming language
  • repo:owner/name: Search in specific repository
  • path:app/src: Search in specific path
  • extension:js: Search by file extension
  • Example: q: "import express" language:typescript path:src/

Issues Search

  • is:issue or is:pr: Filter by type
  • is:open or is:closed: Filter by state
  • label:bug: Search by label
  • author:username: Search by author
  • Example: q: "memory leak" is:issue is:open label:bug

Users Search

  • type:user or type:org: Filter by account type
  • followers:>1000: Filter by followers
  • location:London: Search by location
  • Example: q: "fullstack developer" location:London followers:>100

For detailed search syntax, see GitHub's searching documentation.

Setup

Personal Access Token

Create a GitHub Personal Access Token with appropriate permissions:

  • Go to Personal access tokens (in GitHub Settings > Developer settings)
  • Select which repositories you'd like this token to have access to (Public, All, or Select)
  • Create a token with the repo scope ("Full control of private repositories")
    • Alternatively, if working only with public repositories, select only the public_repo scope
  • Copy the generated token

Usage with Claude Desktop

To use this with Claude Desktop, add the following to your claude_desktop_config.json:

Docker

{
  "mcpServers": {
    "github": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "GITHUB_PERSONAL_ACCESS_TOKEN",
        "mcp/github"
      ],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "<YOUR_TOKEN>"
      }
    }
  }
}

NPX

{
  "mcpServers": {
    "github": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-github"
      ],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "<YOUR_TOKEN>"
      }
    }
  }
}

Build

Docker build:

docker build -t mcp/github -f src/github/Dockerfile .

License

This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.

推荐服务器

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
MCP Package Docs Server

MCP Package Docs Server

促进大型语言模型高效访问和获取 Go、Python 和 NPM 包的结构化文档,通过多语言支持和性能优化来增强软件开发。

精选
本地
TypeScript
Claude Code MCP

Claude Code MCP

一个实现了 Claude Code 作为模型上下文协议(Model Context Protocol, MCP)服务器的方案,它可以通过标准化的 MCP 接口来使用 Claude 的软件工程能力(代码生成、编辑、审查和文件操作)。

精选
本地
JavaScript
@kazuph/mcp-taskmanager

@kazuph/mcp-taskmanager

用于任务管理的模型上下文协议服务器。它允许 Claude Desktop(或任何 MCP 客户端)在基于队列的系统中管理和执行任务。

精选
本地
JavaScript
mermaid-mcp-server

mermaid-mcp-server

一个模型上下文协议 (MCP) 服务器,用于将 Mermaid 图表转换为 PNG 图像。

精选
JavaScript
Jira-Context-MCP

Jira-Context-MCP

MCP 服务器向 AI 编码助手(如 Cursor)提供 Jira 工单信息。

精选
TypeScript
Linear MCP Server

Linear MCP Server

一个模型上下文协议(Model Context Protocol)服务器,它与 Linear 的问题跟踪系统集成,允许大型语言模型(LLM)通过自然语言交互来创建、更新、搜索和评论 Linear 问题。

精选
JavaScript
Sequential Thinking MCP Server

Sequential Thinking MCP Server

这个服务器通过将复杂问题分解为顺序步骤来促进结构化的问题解决,支持修订,并通过完整的 MCP 集成来实现多条解决方案路径。

精选
Python
Curri MCP Server

Curri MCP Server

通过管理文本笔记、提供笔记创建工具以及使用结构化提示生成摘要,从而实现与 Curri API 的交互。

官方
本地
JavaScript