MCP Server
A lightweight and extensible Model Context Protocol server built with Node.js, exposing custom tools and resources for AI clients.
README
MCP Server 🚀
A lightweight and extensible Model Context Protocol (MCP) Server built with Node.js and the official MCP SDK. This project exposes custom tools and resources that can be used by MCP-compatible AI clients, enabling seamless integration with external services and AI models.
✨ Features
- 🔧 Custom MCP tools
- 🤖 AI model integration
- 📦 Modular project structure
- ⚡ Fast and lightweight
- 🔐 Environment variable support
- 🌐 JSON-RPC communication
- 📚 Easy to extend with new tools
- 📝 Resource support
- 🛠️ Developer-friendly architecture
🛠️ Tech Stack
- Node.js
- TypeScript
- Model Context Protocol (MCP) SDK
- Google Gemini API (Optional)
- dotenv
📂 Project Structure
mcp-server/
├── src/
│ ├── index.ts
│ ├── tools/
│ ├── resources/
│ ├── handlers/
│ └── utils/
├── package.json
├── tsconfig.json
├── .env.example
├── .gitignore
└── README.md
🚀 Installation
Clone the repository:
git clone https://github.com/NavanethaKrishnan-14/<repository-name>.git
Navigate to the project:
cd <repository-name>
Install dependencies:
npm install
⚙️ Environment Variables
Create a .env file in the project root.
Example:
GEMINI_API_KEY=your_api_key
Never commit your actual
.envfile to GitHub.
▶️ Running the Server
Development mode:
npm run dev
Production:
npm run build
npm start
🔧 Example MCP Tools
- Greeting Tool
- Calculator Tool
- AI Chat Tool (Gemini)
- Custom Resource Provider
These tools can be extended by adding new handlers in the tools directory.
📡 Compatible MCP Clients
This server can be integrated with MCP-compatible clients such as:
- Cursor
- Claude Desktop
- VS Code MCP extensions
- Custom MCP clients
📈 Future Enhancements
- Authentication support
- Streaming responses
- Database integration
- Logging and monitoring
- Additional AI providers
- File system tools
- Web search tools
🤝 Contributing
Contributions are welcome. Feel free to fork the repository, create a feature branch, and submit a pull request.
📄 License
This project is licensed under the MIT License.
👨💻 Author
Navanetha Krishnan
GitHub: https://github.com/NavanethaKrishnan-14
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。