关于如何构建MCP Server请参考：https://blog.csdn.net/jimmyleeee/article/details/154799040

1、环境的构建：

本文使用的是ollama的llama3.2:latest模型，所以，需要首先下载并且安装ollama。

关于如何安装ollama，可以参考如下：

安装之后，执行命令: ollama pull llama3.2:latest ，下载需要的模型。也可以从https://ollama.com/search 查询想要使用的模型，例如：deepseek-r1, 

搜索到模型之后，就可以使用  ollama pull 模型名，把模型下载到本地。

参考：https://blog.csdn.net/jimmyleeee/article/details/154799040 安装相关的依赖，这里建议使用uv而不是pip，安装uv的方法如下：

uv和pip的比较如下：

2、 构建一个MCP Server

这里参考使用https://blog.csdn.net/jimmyleeee/article/details/154799040的MCP Server，文件名字weather_server.py,代码现实如下：

# file name weather_server.py
import httpx
from fastmcp import FastMCP

# Create FastMCP server
mcp = FastMCP("Weather")

@mcp.tool()
async def get_weather(location: str) -> str:
    """Get current weather for a location"""
    async with httpx.AsyncClient() as client:
        response = await client.get(f"https://wttr.in/{location}?format=j1")
        data = response.json()
        
        current = data["current_condition"][0]
        area = data["nearest_area"][0]["areaName"][0]["value"]
        
        return f"Weather in {area}: {current['temp_C']}°C, {current['weatherDesc'][0]['value']}"


@mcp.tool()
async def get_forecast(location: str) -> str:
    """Get 3-day weather forecast"""
    async with httpx.AsyncClient() as client:
        response = await client.get(f"https://wttr.in/{location}?format=j1")
        data = response.json()
        
        result = f"3-day forecast for {location}:\n"
        for day in data["weather"][:3]:
            result += f"{day['date']}: {day['mintempC']}-{day['maxtempC']}°C\n"
        return result


if __name__ == "__main__":
    mcp.run(transport="stdio")
    #mcp.run(transport="streamable-http", port=8001)

3、 构建一个Agent

Agent是使用之前下载的 llama3.2:latest， 通过Agent识别query的内容，然后自动去调用weather_server.py的MCP server去查询某个城市的天气。示例代码如下：

# filename  agent_client.py

import asyncio
from langchain_ollama import ChatOllama
from mcp_use import MCPAgent, MCPClient

async def main():

    # Create configuration dictionary
    config = {
      "mcpServers": {
          "weather": {
              "command": "uv",
              "args": ["run",
                       "--directory",
                       "D:\\AI_Test_Code\\FirstMcpServer\\ollama",
                       "weather_server.py"],
          }
      }
    }

    # Create MCPClient from configuration dictionary
    client = MCPClient.from_dict(config)

    # Create LLM
    llm = ChatOllama(base_url="http://localhost:11434", model="llama3.2:latest")

    # Create agent with the client
    agent = MCPAgent(llm=llm, client=client, max_steps=30)

    # Run the query
    result = await agent.run(
        "What's the weather in Shanghai and the 3-day forecast?",
    )
    print(f"\nResult: {result}")

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

4、运行

在VS Code的terminal里，执行 uv run agent_client.py，或者直接使用VS Code的运行程序按钮也可以。

运行Agent的结果如下：

可以看到已经根据城市名称查询到未来3天的天气情况。