Python 从0到1构建MCP Server & Client
About
支持查询主流agent框架技术文档的MCP server（支持stdio和sse两种传输协议）, 支持 langchain、llama-index、autogen、agno、openai-agents-sdk、mcp-doc、camel-ai 和 crew-ai
Explore
- Implements both Stdio (local) and SSE (remote) transport protocols
- Provides a get_docs tool that searches and retrieves documentation for eight popular AI libraries
- Uses the Serper API for Google search and BeautifulSoup for web page parsing
- Includes ready-to-use client configurations for Cursor and Cline
- Ships a complete custom Python MCP client using the OpenAI SDK
- Requires only the mcp CLI package, httpx, and BeautifulSoup as dependencies
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Python 从0到1构建MCP Server & ClientCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install UV, create a project directory, install dependencies (mcp[cli], httpx), and write a main.py file that defines the MCP server with the get_docs tool. Run the server locally with uv run main.py for Stdio, or uv run main.py --host 0.0.0.0 --port 8020 for SSE. Configure clients (Cline, Cursor) by adding a JSON block pointing uv --directory <path> run main.py to the MCP server definition.
print("Initialized SSE client...")
print("Listing tools...")
response = await self.session.list_tools()
tools = response.tools
print("\nConnected to server with tools:", [tool.name for tool in tools])
async def cleanup(self):
"""Properly clean up the session and streams"""
if self._session_context:
await self._session_context.__aexit__(None, None, None)
if self._streams_context:
await self._streams_context.__aexit__(None, None, None)
async def process_query(self, query: str) -> str:
"""Process a query using OpenAI API and available tools"""
messages = [
{
"role": "user",
"content": query
}
]
response = await self.session.list_tools()
available_tools = [{
"type": "function",
"function": {
"name": tool.name,
"description": tool.description,
"parameters": tool.inputSchema
}
} for tool in response.tools]
tool_results = []
final_text = []
assistant_message = completion.choices[0].message
if assistant_message.tool_calls:
for tool_call in assistant_message.tool_calls:
tool_name = tool_call.function.name
tool_args = json.loads(tool_call.function.arguments)
result = await self.session.call_tool(tool_name, tool_args)
tool_results.append({"call": tool_name, "result": result})
final_text.append(f"[Calling tool {tool_name} with args {tool_args}]")
messages.extend([
{
"role": "assistant",
"content": None,
"tool_calls": [tool_call]
},
{
"role": "tool",
"tool_call_id": tool_call.id,
"content": result.content[0].text
}
])
print(f"Tool {tool_name} returned: {result.content[0].text}")
print("messages", messages)
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"python \u4ece0\u52301\u6784\u5efamcp server & client": {
"python-mcp-server-client": {
"command": "uv",
"args": [
"init",
"mcp-server"
]
}
}
}
}McpServers
{
"python-mcp-server-client": {
"command": "uv",
"args": [
"init",
"mcp-server"
]
}
}中文 | English
简介
MCP Server 是实现模型上下文协议（MCP）的服务器，旨在为 AI 模型提供一个标准化接口，连接外部数据源和工具，例如文件系统、数据库或 API。
MCP 的优势
在 MCP 出现前，AI 调用工具基本通过 Function Call 完成，存在以下问题：
1. 不同的大模型厂商 Function Call 格式不一致
2. 大量 API 工具的输入和输出格式不一致，封装管理繁琐
MCP 相当于一个统一的 USB-C，不仅统一了不同大模型厂商的 Function Call 格式，也对相关工具的封装进行了统一。
MCP 传输协议
目前 MCP 支持两种主要的传输协议：
1. Stdio 传输协议
- 针对本地使用
- 需要在用户本地安装命令行工具
- 对运行环境有特定要求
2. SSE（Server-Sent Events）传输协议
- 针对云服务部署
- 基于 HTTP 长连接实现
项目结构
MCP Server
- Stdio 传输协议（本地） - SSE 传输协议（远程）MCP Client（客户端）
- 自建客户端（Python） - Cursor - Cline环境配置
1. 安装 UV 包
MacOS/Linux:
curl -LsSf https://astral.sh/uv/install.sh | sh
Windows:
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
2. 初始化项目
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
