【AI】MCP代码实践纯享

使用MCPServer(天气预报与告警)、MCPClient(deepseek-chat)，实践基于MCP的AI对话开发

1.依赖安装

pip install --upgrade pip
pip install flask requests
pip install uv
pip install httpx
pip install FastMCP
pip install OpenAI

2.源码

.env

BASE_URL=https://api.deepseek.com
# 可以更换成你对应的支持MCP的模型
MODEL=deepseek-chat
OPENAI_API_KEY=sk-xxx

client.py

import asyncio
import os
import json
from typing import Optional
from contextlib import AsyncExitStack

from openai import OpenAI  
from dotenv import load_dotenv

from mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client

# 加载 .env 文件，确保 API Key 受到保护
load_dotenv()

class MCPClient:
    def __init__(self):
        """初始化 MCP 客户端"""
        self.exit_stack = AsyncExitStack()
        self.openai_api_key = os.getenv("OPENAI_API_KEY")  # 读取 OpenAI API Key
        self.base_url = os.getenv("BASE_URL")  # 读取 BASE YRL
        self.model = os.getenv("MODEL")  # 读取 model
        if not self.openai_api_key:
            raise ValueError("❌ 未找到 OpenAI API Key，请在 .env 文件中设置 OPENAI_API_KEY")
        self.client = OpenAI(api_key=self.openai_api_key, base_url=self.base_url) # 创建OpenAI client
        self.session: Optional[ClientSession] = None
        self.exit_stack = AsyncExitStack()        

    async def connect_to_server(self, server_script_path: str):
        """连接到 MCP 服务器并列出可用工具"""
        is_python = server_script_path.endswith('.py')
        is_js = server_script_path.endswith('.js')
        if not (is_python or is_js):
            raise ValueError("服务器脚本必须是 .py 或 .js 文件")

        command = "python" if is_python else "node"
        server_params = StdioServerParameters(
            command=command,
            args=[server_script_path],
            env=None
        )

        # 启动 MCP 服务器并建立通信
        stdio_transport = await self.exit_stack.enter_async_context(stdio_client(server_params))
        self.stdio, self.write = stdio_transport
        self.session = await self.exit_stack.enter_async_context(ClientSession(self.stdio, self.write))

        await self.session.initialize()

        # 列出 MCP 服务器上的工具
        response = await self.session.list_tools()
        tools = response.tools
        print("\n已连接到服务器，支持以下工具:", [tool.name for tool in tools])     
        
    async def process_query(self, query: str) -> str:
        """
        使用大模型处理查询并调用可用的 MCP 工具 (Function Calling)
        """
        messages = [{"role": "user", "content": query}]
        
        response = await self.session.list_tools()
        
        available_tools = [{
            "type": "function",
            "function": {
                "name": tool.name,
                "description": tool.description,
                "input_schema": tool.inputSchema
            }
        } for tool in response.tools]
        # print(available_tools)
        
        response = self.client.chat.completions.create(
            model=self.model,            
            messages=messages,
            tools=available_tools     
        )
        
        # 处理返回的内容
        content = response.choices[0]
        if content.finish_reason == "tool_calls":
            # 如何是需要使用工具，就解析工具
            tool_call = content.message.tool_calls[0]
            tool_name = tool_call.function.name
            tool_args = json.loads(tool_call.function.arguments)
            
            # 执行工具
            result = await self.session.call_tool(tool_name, tool_args)
            print(f"\n\n[Calling tool {tool_name} with args {tool_args}]\n\n")
            
            # 将模型返回的调用哪个工具数据和工具执行完成后的数据都存入messages中
            messages.append(content.message.model_dump())
            messages.append({
                "role": "tool",
                "content": result.content[0].text,
                "tool_call_id": tool_call.id,
            })
            
            # 将上面的结果再返回给大模型用于生产最终的结果
            response = self.client.chat.completions.create(
                model=self.model,
                messages=messages,
            )
            return response.choices[0].message.content
            
        return content.message.content
    
    async def chat_loop(self):
        """运行交互式聊天循环"""
        print("\n🤖 MCP 客户端已启动！输入 'quit' 退出")

        while True:
            try:
                query = input("\n你: ").strip()
                if query.lower() == 'quit':
                    break
                
                response = await self.process_query(query)  # 发送用户输入到 OpenAI API
                print(f"\n🤖 AI {response}")

            except Exception as e:
                print(f"\n⚠️ 发生错误: {str(e)}")

    async def cleanup(self):
        """清理资源"""
        await self.exit_stack.aclose()

async def main():
    if len(sys.argv) < 2:
        print("Usage: python client.py <path_to_server_script>")
        sys.exit(1)

    client = MCPClient()
    try:
        await client.connect_to_server(sys.argv[1])
        await client.chat_loop()
    finally:
        await client.cleanup()

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

server.py

import json
import httpx
from typing import Any
from mcp.server.fastmcp import FastMCP

# 初始化 MCP 服务器
mcp = FastMCP("WeatherServer")

# 常量
NWS_API_BASE = "https://api.weather.gov"
USER_AGENT = "weather-app/1.0"

async def make_nws_request(url: str) -> dict[str, Any] | None:
    """向 NWS API 发送请求，并进行错误处理"""
    headers = {
        "User-Agent": USER_AGENT,
        "Accept": "application/geo+json"
    }
    async with httpx.AsyncClient() as client:
        try:
            response = await client.get(url, headers=headers, timeout=30.0)
            response.raise_for_status()
            return response.json()
        except Exception:
            return None
def format_alert(feature: dict) -> str:
    """将天气警报格式化为可读的字符串"""
    props = feature["properties"]
    return f"""
事件: {props.get('event', '未知')}
地区: {props.get('areaDesc', '未知')}
严重程度: {props.get('severity', '未知')}
描述: {props.get('description', '无描述')}
指引: {props.get('instruction', '无具体指引')}
"""

@mcp.tool()
async def get_alerts(state: str) -> str:
    """获取某个美国州的天气警报。
    参数:
        state: 两个字母的州代码（如 CA、NY）
    """
    url = f"{NWS_API_BASE}/alerts/active/area/{state}"
    data = await make_nws_request(url)
    if not data or "features" not in data:
        return "无法获取警报或未找到警报信息。"
    if not data["features"]:
        return "该州当前没有活跃的天气警报。"
    alerts = [format_alert(feature) for feature in data["features"]]
    return "\n---\n".join(alerts)

@mcp.tool()
async def get_forecast(latitude: float, longitude: float) -> str:
    """获取指定位置的天气预报。
    参数:
        latitude: 纬度
        longitude: 经度
    """
    # 获取天气预报的 API 端点
    points_url = f"{NWS_API_BASE}/points/{latitude},{longitude}"
    points_data = await make_nws_request(points_url)
    if not points_data:
        return "无法获取该位置的天气预报数据。"
    # 获取天气预报 URL
    forecast_url = points_data["properties"]["forecast"]
    forecast_data = await make_nws_request(forecast_url)
    if not forecast_data:
        return "无法获取详细的天气预报信息。"
    # 格式化天气预报
    periods = forecast_data["properties"]["periods"]
    forecasts = []
    for period in periods[:5]:  # 仅显示最近 5 个时段的预报
        forecast = f"""
{period['name']}:
温度: {period['temperature']}°{period['temperatureUnit']}
风速: {period['windSpeed']} {period['windDirection']}
天气: {period['detailedForecast']}
"""
        forecasts.append(forecast)
    print(forecasts)
    return "\n---\n".join(forecasts)
    
if __name__ == "__main__":
    # 以标准 I/O 方式运行 MCP 服务器
    mcp.run(transport='stdio')

3.原理简述

参考function-calling与mcp的对比图：

 4.效果