creating-your-first-mcp-server

creating-your-first-mcp-server

Enables to perform mathematical calculations, retrieve weather information, and manage files through a standardized MCP interface, showcasing best practices for building MCP servers.

Category
访问服务器

README

Creating Your First MCP Server

<p align="center"> <img src="hero.svg" alt="Creating Your First MCP Server" width="100%"> </p>

A production-ready TypeScript implementation of a Model Context Protocol (MCP) server with example tools demonstrating best practices for building MCP servers.

Quick Start

Installation

npm install

Build

npm run build

Run the Server

npm start

Run Example Client

npm run example

What is MCP?

The Model Context Protocol (MCP) is an open protocol that standardizes how applications provide context to Large Language Models (LLMs). It enables:

  • Standardized Communication: A unified way for LLMs to interact with external tools and data sources
  • Tool Integration: Expose custom functionality that AI models can discover and use
  • Resource Management: Provide structured access to files, databases, and APIs
  • Prompt Templates: Define reusable prompts for common tasks

Key MCP Concepts

  1. Server: Exposes tools, resources, and prompts that clients can use
  2. Client: Connects to MCP servers to access their capabilities
  3. Tools: Executable functions that perform specific tasks
  4. Resources: Data sources like files, database records, or API endpoints
  5. Prompts: Reusable prompt templates with parameters

Project Structure

creating-your-first-mcp-server/
├── src/
│   ├── index.ts              # Main MCP server implementation
│   └── tools/
│       ├── calculator.ts      # Mathematical operations tool
│       ├── weather.ts         # Weather information tool
│       └── file-ops.ts        # File operations tool
├── examples/
│   └── client.ts             # Example MCP client usage
├── documentation/
│   ├── MCP-CONCEPTS.md       # In-depth MCP concepts
│   ├── TOOL-DEVELOPMENT.md   # Guide to creating tools
│   └── INTEGRATION.md        # Integration guide
├── package.json
├── tsconfig.json
└── LICENSE

Available Tools

Calculator Tool

Performs mathematical operations (add, subtract, multiply, divide, power, sqrt).

// Example usage
{
  "operation": "add",
  "a": 5,
  "b": 3
}
// Returns: { "result": 8 }

Weather Tool

Retrieves weather information for a location (simulated data for demonstration).

// Example usage
{
  "location": "San Francisco"
}
// Returns weather data including temperature, conditions, humidity

File Operations Tool

Performs file system operations (read, write, list, delete).

// Example usage
{
  "operation": "read",
  "path": "/path/to/file.txt"
}
// Returns file contents or operation result

Development

Building

npm run build

Watch Mode

npm run dev

Clean Build Artifacts

npm run clean

Documentation

For more detailed information, see:

Error Handling

This server implements comprehensive error handling:

  • Input validation for all tool parameters
  • Graceful error messages for clients
  • Type-safe error responses
  • Logging for debugging

Security Considerations

  • File operations are restricted to safe directories
  • Input validation prevents injection attacks
  • Error messages don't expose sensitive system information
  • Rate limiting can be added for production use

License

MIT License - Copyright (c) 2026 ry-ops

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Resources

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