mcp-builder

MCP 服务构建技能

现在，你已具备构建 MCP（Model Context Protocol）服务的专业知识。MCP 使 Claude 能够通过标准化协议与外部服务交互。

什么是 MCP？

MCP 服务提供：

• 工具：Claude 可以调用的函数（如 API 端点）
• 资源：Claude 可以读取的数据（如文件或数据库记录）
• 提示词：预先构建的提示词模板

快速入门：Python MCP 服务

1. 项目设置

# Create project
mkdir my-mcp-server && cd my-mcp-server
python3 -m venv venv && source venv/bin/activate

# Install MCP SDK
pip install mcp

2. 基本服务模板

#!/usr/bin/env python3
"""my_server.py - A simple MCP server"""

from mcp.server import Server
from mcp.server.stdio import stdio_server
from mcp.types import Tool, TextContent

# Create server instance
server = Server("my-server")

# Define a tool
@server.tool()
async def hello(name: str) -> str:
    """Say hello to someone.

    Args:
        name: The name to greet
    """
    return f"Hello, {name}!"

@server.tool()
async def add_numbers(a: int, b: int) -> str:
    """Add two numbers together.

    Args:
        a: First number
        b: Second number
    """
    return str(a + b)

# Run server
async def main():
    async with stdio_server() as (read, write):
        await server.run(read, write)

if __name__ == "__main__":
    import asyncio
    asyncio.run(main())

3. 注册到 Claude

添加到 ~/.claude/mcp.json：

{
  "mcpServers": {
    "my-server": {
      "command": "python3",
      "args": ["/path/to/my_server.py"]
    }
  }
}

TypeScript MCP 服务

1. 设置

mkdir my-mcp-server && cd my-mcp-server
npm init -y
npm install @modelcontextprotocol/sdk

2. 模板

// src/index.ts
import { Server } from "@modelcontextprotocol/sdk/server/index.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";

const server = new Server({
  name: "my-server",
  version: "1.0.0",
});

// Define tools
server.setRequestHandler("tools/list", async () => ({
  tools: [
    {
      name: "hello",
      description: "Say hello to someone",
      inputSchema: {
        type: "object",
        properties: {
          name: { type: "string", description: "Name to greet" },
        },
        required: ["name"],
      },
    },
  ],
}));

server.setRequestHandler("tools/call", async (request) => {
  if (request.params.name === "hello") {
    const name = request.params.arguments.name;
    return { content: [{ type: "text", text: `Hello, ${name}!` }] };
  }
  throw new Error("Unknown tool");
});

// Start server
const transport = new StdioServerTransport();
server.connect(transport);

高级模式

外部 API 集成

import httpx
from mcp.server import Server

server = Server("weather-server")

@server.tool()
async def get_weather(city: str) -> str:
    """Get current weather for a city."""
    async with httpx.AsyncClient() as client:
        resp = await client.get(
            f"https://api.weatherapi.com/v1/current.json",
            params={"key": "YOUR_API_KEY", "q": city}
        )
        data = resp.json()
        return f"{city}: {data['current']['temp_c']}C, {data['current']['condition']['text']}"

数据库访问

import sqlite3
from mcp.server import Server

server = Server("db-server")

@server.tool()
async def query_db(sql: str) -> str:
    """Execute a read-only SQL query."""
    if not sql.strip().upper().startswith("SELECT"):
        return "Error: Only SELECT queries allowed"

    conn = sqlite3.connect("data.db")
    cursor = conn.execute(sql)
    rows = cursor.fetchall()
    conn.close()
    return str(rows)

资源（只读数据）

@server.resource("config://settings")
async def get_settings() -> str:
    """Application settings."""
    return open("settings.json").read()

@server.resource("file://{path}")
async def read_file(path: str) -> str:
    """Read a file from the workspace."""
    return open(path).read()

测试

# Test with MCP Inspector
npx @anthropics/mcp-inspector python3 my_server.py

# Or send test messages directly
echo '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' | python3 my_server.py

最佳实践

1. 清晰的工具描述：Claude 会根据这些描述判断何时调用工具
2. 输入验证：始终验证并清理输入
3. 错误处理：返回有意义的错误消息
4. 默认使用异步：对 I/O 操作使用 async/await
5. 安全性：未经身份验证，切勿公开敏感操作
6. 幂等性：工具应支持安全重试