MCP GitHub Navigator
MCP server for AI agents to securely access GitHub data, including listing repositories and user profile info via the GitHub API.
README
MCP GitHub Navigator
A Model Context Protocol (MCP) server that provides an AI agent with secure access to GitHub data, allowing it to list repositories, view issues, and read files via the GitHub API.
HLD (High-Level Design)
- Architecture: The server is built in Node.js/TypeScript and implements the standard MCP
@modelcontextprotocol/sdk. It uses a StdioServerTransport to communicate directly with any MCP-compatible AI client via standard input/output. - External Integration: Uses Axios to connect to the GitHub REST API (
https://api.github.com). - Authentication: Relies on a Personal Access Token provided via the
GITHUB_TOKENenvironment variable.
LLD (Low-Level Design)
- Entry Point:
src/index.tsis the main entry point which initializes theServerinstance and maps MCP capabilities. - Tools Registered:
get_user: UsesGET /userto return the authenticated GitHub profile.list_repos: UsesGET /user/repos?sort=updated&per_page=10to return recently active repositories.
- Data Flow: When an AI client sends a
CallToolRequestSchemaforlist_repos, the MCP server validates the tool name, invokes the corresponding GitHub API endpoint via Axios, formats the JSON response into a text block, and returns it to the client.
TDD (Test-Driven Development) Strategy
- Frameworks: We recommend using
Jestfor executing test suites. - Mocking: Testing relies on mocking the
axiosInstanceusing libraries likenockoraxios-mock-adapterto simulate GitHub API responses without requiring an active internet connection or hitting API rate limits. - Integration Tests: Creating a mock MCP Client using
@modelcontextprotocol/sdk/clientto test the end-to-end flow of standardCallToolrequests.
Setup Instructions
Prerequisites
- Node.js (v16 or higher)
- A GitHub Personal Access Token (PAT)
Installation
- Clone the repository:
git clone https://github.com/RachitJava/mcp-github.git cd mcp-github - Install dependencies:
npm install - Build the project:
npm run build
Running the Server
The server requires the GITHUB_TOKEN environment variable to be set. You can run it directly:
export GITHUB_TOKEN="your_personal_access_token_here"
npm start
Note: Since this is an MCP server, it is meant to be run by an MCP client (like Claude Desktop) rather than manually.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。