Model Context Protocol是 为大模型提供上下文和工具的全新标准化方法，FastMCP 使构建 MCP 服务器和客户端变得简单直观。

MCP这个标准是anthropic公司搞的，如果大家不了解的话，anthropic就是那个Claud Code产品的母公司。

https://www.anthropic.com/news/model-context-protocol

更进一步的 这个公司就是那个禁止中国公司和个人使用AI产品的那个。

https://www.anthropic.com/news/updating-restrictions-of-sales-to-unsupported-regions

抛开这些，mcp是他们搞的一个事实标准。用于LLM与外界进行交互。

fastmcp是python版本的SDK。

此SDK目前已经升级到v2.0，并且更新特别快。

所以网上的文档很多更新的不是特别及时。

很多人对于如何使用fastmcp搞不清楚。

这里我就给个demo，让大家搞清大概的用法。

有两个部分 server 和 client。

fastmcp需要python3.10以上版本。

如果没有的话，可以使用pyenv安装高版本的python

pyenv

# 安装依赖
sudo apt install -y build-essential libssl-dev zlib1g-dev \
libbz2-dev libreadline-dev libsqlite3-dev curl libncursesw5-dev \
xz-utils tk-dev libxml2-dev libxmlsec1-dev libffi-dev liblzma-dev

## 安装脚本会提示你将 pyenv 所需的环境变量添加到.bashrc文件中。
## 按照提示操作，并重启终端或运行source ~/.bashrc 使其生效。
curl https://pyenv.run | bash


pyenv install 3.12

#安装完成后，你可以通过以下命令来管理版本：
#查看已安装的所有版本
pyenv versions

#将全局默认版本设置为 Python 3.12
pyenv global 3.12

#在当前目录设置本地 Python 版本
pyenv local 3.12

mcp协议中有三种组件

Tools 工具

Resources 资源

Prompts 提示

下面的代码示例三种组件如何使用。

server.py

from fastmcp import FastMCP

mcp = FastMCP("My MCP Server")

@mcp.tool
def greet(name: str) -> str:
    '''Send hello to my friend.'''
    return f"Hello, {name}!"

@mcp.tool
def add(a: int, b: int) -> int:
    '''Add two integer numbers together.'''
    return a + b



# Basic dynamic resource returning a string
@mcp.resource("resource://greeting")
def get_greeting() -> str:
    """Provides a simple greeting message."""
    return "Hello from FastMCP Resources!"


# Resource returning JSON data (dict is auto-serialized)
@mcp.resource("data://config")
def get_config() -> dict:
    """Provides application configuration as JSON."""
    return {
        "theme": "dark",
        "version": "1.2.0",
        "features": ["tools", "resources"],
    }





# Basic prompt returning a string (converted to user message automatically)
@mcp.prompt
def ask_about_topic(topic: str) -> str:
    """Generates a user message asking for an explanation of a topic."""
    return f"Can you please explain the concept of '{topic}'?"




if __name__ == "__main__":
    mcp.run(transport="http", port=8000)

运行：

python  server.py

client.py

import asyncio


from fastmcp import Client
from fastmcp.client.logging import LogMessage

async def log_handler(message: LogMessage):
    print(f"Server log: {message.data}")

async def progress_handler(progress: float, total: float | None, message: str | None):
    print(f"Progress: {progress}/{total} - {message}")

async def sampling_handler(messages, params, context):
    # Integrate with your LLM service here
    return "Generated response"


client = Client("http://localhost:8000/mcp")
client.log_handler = log_handler
client.progress_handler = progress_handler
client.sampling_handler = sampling_handler


#client = Client( "server.py")
async def main():
    async with client:
        # Basic server interaction
        await client.ping()
        
        # List available operations
        tools = await client.list_tools()
        resources = await client.list_resources()
        prompts = await client.list_prompts()
        
        # Execute operations
        result = await client.call_tool("greet", {"name": "BaBa"})
        print(result)
        print("-------------------------");

        # Execute operations
        result = await client.call_tool("add", {"a": 3, "b": 5})
        print(result)
        print("-------------------------");


        print("Tools:", tools)
        print("-------------------------");
        print("Resources:", resources)
        print("-------------------------");
        print("Prompts:", prompts)
        print("-------------------------");

        # Read a resource
        content = await client.read_resource("resource://greeting")
        print(content[0].text)
        print("-------------------------");

        # Get a rendered prompt
        messages = await client.get_prompt("ask_about_topic", {"topic": "Python"})
        print(messages.messages)

asyncio.run(main())

运行

python3 client.py

运行结果：

pp@dell:~/fastmcp$ python3 client1.py 
CallToolResult(content=[TextContent(type='text', text='Hello, BaBa!', annotations=None, meta=None)], structured_content={'result': 'Hello, BaBa!'}, data='Hello, BaBa!', is_error=False)
-------------------------
CallToolResult(content=[TextContent(type='text', text='8', annotations=None, meta=None)], structured_content={'result': 8}, data=8, is_error=False)
-------------------------
Tools: [Tool(name='greet', title=None, description='Send hello to my friend.', inputSchema={'properties': {'name': {'title': 'Name', 'type': 'string'}}, 'required': ['name'], 'type': 'object'}, outputSchema={'properties': {'result': {'title': 'Result', 'type': 'string'}}, 'required': ['result'], 'title': '_WrappedResult', 'type': 'object', 'x-fastmcp-wrap-result': True}, annotations=None, meta={'_fastmcp': {'tags': []}}), Tool(name='add', title=None, description='Add two integer numbers together.', inputSchema={'properties': {'a': {'title': 'A', 'type': 'integer'}, 'b': {'title': 'B', 'type': 'integer'}}, 'required': ['a', 'b'], 'type': 'object'}, outputSchema={'properties': {'result': {'title': 'Result', 'type': 'integer'}}, 'required': ['result'], 'title': '_WrappedResult', 'type': 'object', 'x-fastmcp-wrap-result': True}, annotations=None, meta={'_fastmcp': {'tags': []}})]
-------------------------
Resources: [Resource(name='get_greeting', title=None, uri=AnyUrl('resource://greeting'), description='Provides a simple greeting message.', mimeType='text/plain', size=None, annotations=None, meta={'_fastmcp': {'tags': []}}), Resource(name='get_config', title=None, uri=AnyUrl('data://config'), description='Provides application configuration as JSON.', mimeType='text/plain', size=None, annotations=None, meta={'_fastmcp': {'tags': []}})]
-------------------------
Prompts: [Prompt(name='ask_about_topic', title=None, description='Generates a user message asking for an explanation of a topic.', arguments=[PromptArgument(name='topic', description=None, required=True)], meta={'_fastmcp': {'tags': []}})]
-------------------------
Hello from FastMCP Resources!
-------------------------
[PromptMessage(role='user', content=TextContent(type='text', text="Can you please explain the concept of 'Python'?", annotations=None, meta=None))]

可以看出调用的结果。

大家都说CSDN不好，里面的文章骗人。

可是技术类文章不在CSDN上发，还能到哪里发呢？

Looking in my eyes! 

Tell me where!

参考：

https://gofastmcp.com/getting-started/welcome