Greeting MCP Server
A simple MCP server built with Next.js that provides a greet_user tool to return friendly greetings, either general or personalized.
README
Greeting MCP Server
A simple Model Context Protocol (MCP) server built with Next.js that provides a greeting tool. This project serves as a clean foundation for building custom MCP servers.
Features
- Simple Greeting Tool: Provides a
greet_usertool that responds with friendly greetings - MCP Server Integration: Built using the Vercel MCP adapter for seamless integration
- No Authentication Required: Simple setup without API keys or user management
- TypeScript Support: Fully typed with TypeScript for better development experience
Getting Started
-
Install dependencies:
npm install -
Run the development server:
npm run dev -
Open your browser: Visit http://localhost:3000 to see the server info page
-
Configure your MCP Client: Add this server to your MCP client configuration:
{ "mcpServers": { "greeting-server": { "url": "http://localhost:3000/api/llm/mcp" } } } -
Test the greeting tool: In your MCP client, you can now use the
greet_usertool:greet_user()- Get a general greetinggreet_user(name: "Alice")- Get a personalized greeting
MCP Tool Reference
greet_user
Greets the user with a friendly message.
Parameters:
name(optional): The name of the user to greet
Examples:
- Without name: Returns "Hello! How are you doing today?"
- With name: Returns "Hello, [name]! Nice to meet you!"
Project Structure
src/
├── app/
│ ├── api/llm/[transport]/route.ts # MCP server endpoint
│ ├── layout.tsx # App layout
│ └── page.tsx # Info page
├── components/ui/ # Basic UI components
└── lib/utils.ts # Utility functions
Customization
This project is designed to be a clean starting point for your own MCP server. To customize:
- Modify the greeting tool in
src/app/api/llm/[transport]/route.ts - Add new tools by adding more
server.tool()calls - Add authentication if needed using the
experimental_withMcpAuthwrapper - Update the UI in
src/app/page.tsxto reflect your server's purpose
Learn More
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。