Demo MCP Server

Demo MCP Server

A comprehensive TypeScript boilerplate MCP server featuring domain-driven design and dynamic component loading. Provides example tools for calculations and text processing, system resources, and writing assistance prompts.

Category
访问服务器

README

Demo MCP Server

A comprehensive boilerplate Model Context Protocol (MCP) server built with TypeScript using Domain-Driven Design patterns and dynamic component loading.

🚀 Features

  • Domain-Driven Design: Clean architecture with separated concerns
  • Dynamic Component Loading: File-based automatic loading of MCP components
  • TypeScript: Full type safety and modern JavaScript features
  • Dependency Injection: Modular and testable architecture
  • Example Components: Ready-to-use tools, resources, and prompts
  • Comprehensive Logging: Detailed startup and operation logging
  • Graceful Shutdown: Proper cleanup and resource management

📁 Project Structure

src/
├── index.ts                 # Main entry point
├── types/                   # Type definitions
│   └── index.ts            # MCP interfaces and types
├── services/                # Business logic services
│   ├── index.ts            # Services barrel export
│   └── module-loader-service.ts  # Dynamic module loading
├── server/                  # MCP server wrapper
│   ├── index.ts            # Server barrel export
│   └── my-mcp-server.ts    # Main server implementation
├── tools/                   # MCP tools directory
│   ├── index.ts            # Auto-loading tools
│   ├── calculator-tools.ts # Example arithmetic tools
│   └── text-processing-tools.ts # Example text tools
├── resources/               # MCP resources directory
│   ├── index.ts            # Auto-loading resources
│   ├── system-info-resources.ts # System information
│   └── config-resources.ts # Configuration data
└── prompts/                 # MCP prompts directory
    ├── index.ts            # Auto-loading prompts
    ├── code-review-prompts.ts # Code analysis prompts
    └── writing-assistance-prompts.ts # Writing help prompts

🛠️ Installation

  1. Clone the repository:

    git clone <repository-url>
    cd demo-mcp-dev-1
    
  2. Install dependencies:

    npm install
    
  3. Build the project:

    npm run build
    

🎯 Usage

Development Mode

Run the server in development mode with hot reloading:

npm run dev

Production Mode

Build and run the server in production:

npm run build
npm start

Direct Execution

Run the compiled server directly:

node dist/index.js

🔧 Available Tools

Calculator Tools

  • add - Add two numbers
  • subtract - Subtract two numbers
  • multiply - Multiply two numbers
  • divide - Divide two numbers (with zero-division protection)

Text Processing Tools

  • transform-text - Transform text (uppercase, lowercase, capitalize, reverse, word-count)
  • analyze-text - Analyze text and provide detailed statistics

📚 Available Resources

System Information

  • system://info - System and environment information
  • env://{varName} - Access environment variables
  • process://info - Node.js process information

Configuration

  • config://app - Application configuration
  • settings://{category}/{key} - Dynamic configuration settings
  • health://status - Health and status information

📝 Available Prompts

Code Review Prompts

  • review-code - Comprehensive code review with focus areas
  • refactor-code - Code refactoring suggestions
  • document-code - Generate code documentation

Writing Assistance

  • write-email - Professional email generation
  • write-technical-doc - Technical documentation creation
  • summarize-meeting - Meeting summary generation

🏗️ Architecture

Domain-Driven Design

The project follows DDD principles with clear separation of concerns:

  • Types: Domain interfaces and contracts
  • Services: Business logic and operations
  • Server: Infrastructure and MCP integration
  • Components: MCP-specific implementations (tools, resources, prompts)

Dynamic Component Loading

The ModuleLoaderService automatically discovers and loads MCP components:

  1. Scans component directories for TypeScript/JavaScript files
  2. Dynamically imports modules using file URLs
  3. Validates module contracts
  4. Registers components with the MCP server

Dependency Injection

The MyMCPServer class uses dependency injection patterns:

  • Abstract base classes for extensibility
  • Interface-based dependencies
  • Configurable service injection
  • Clean separation between SDK and business logic

🔌 Adding New Components

Adding a New Tool

  1. Create a new file in src/tools/ (e.g., my-new-tool.ts)
  2. Export an MCP module with the required structure:
import { z } from "zod";
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import type { MCPModule } from "../types/index.js";

async function register(server: McpServer): Promise<void> {
  server.registerTool(
    "my-tool",
    {
      title: "My Tool",
      description: "Description of what my tool does",
      inputSchema: {
        param1: z.string().describe("First parameter"),
        param2: z.number().describe("Second parameter")
      }
    },
    async ({ param1, param2 }) => ({
      content: [
        {
          type: "text",
          text: `Tool result: ${param1} - ${param2}`
        }
      ]
    })
  );
}

export const myNewTool: MCPModule = {
  register,
  metadata: {
    name: "my-new-tool",
    description: "My new tool implementation",
    version: "1.0.0",
    author: "Your Name"
  }
};

export default myNewTool;
  1. The tool will be automatically loaded on server startup!

Adding a New Resource

  1. Create a new file in src/resources/ (e.g., my-resource.ts)
  2. Export an MCP module following the same pattern as tools
  3. Use server.registerResource() in the register function

Adding a New Prompt

  1. Create a new file in src/prompts/ (e.g., my-prompt.ts)
  2. Export an MCP module following the same pattern
  3. Use server.registerPrompt() in the register function

🧪 Testing

Run the test suite:

npm test

Run linting:

npm run lint

Type checking:

npm run type-check

🔍 Debugging

The server provides comprehensive logging during startup and operation:

  • Component discovery and loading
  • Registration success/failure
  • Server status and configuration
  • Error details and stack traces

📊 Configuration

The server is configured in src/index.ts:

const serverConfig: MCPServerConfig = {
  name: "demo-mcp-server",
  version: "1.0.0",
  capabilities: {
    tools: true,
    resources: true,
    prompts: true,
    logging: true
  }
};

🤝 Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Add tests if applicable
  5. Submit a pull request

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

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