展示 HN：Polymcp – 将任何 Python 函数转换为 AI 代理的 MCP 工具
我构建了 Polymcp，这是一个框架，可以将任何 Python 函数转换为可供 AI 代理使用的 MCP（模型上下文协议）工具。无需重写，无需复杂的集成。
<p>示例</p>
<p>简单函数：</p>
```python
from polymcp.polymcp_toolkit import expose_tools_http
def add(a: int, b: int) -> int:
"""添加两个数字"""
return a + b
app = expose_tools_http([add], title="数学工具")
```
<p>运行命令：</p>
```
uvicorn server_mcp:app --reload
```
<p>现在，add 函数通过 MCP 暴露，可以被 AI 代理直接调用。</p>
<p>API 函数：</p>
```python
import requests
from polymcp.polymcp_toolkit import expose_tools_http
def get_weather(city: str):
"""返回某个城市的当前天气数据"""
response = requests.get(f"https://api.weatherapi.com/v1/current.json?q={city}")
return response.json()
app = expose_tools_http([get_weather], title="天气工具")
```
<p>AI 代理可以调用 get_weather("London") 来即时获取实时天气数据。</p>
<p>业务工作流函数：</p>
```python
import pandas as pd
from polymcp.polymcp_toolkit import expose_tools_http
def calculate_commissions(sales_data: list[dict]):
"""根据销售数据计算销售佣金"""
df = pd.DataFrame(sales_data)
df["commission"] = df["sales_amount"] * 0.05
return df.to_dict(orient="records")
app = expose_tools_http([calculate_commissions], title="业务工具")
```
<p>AI 代理现在可以自动生成佣金报告。</p>
<p>对企业的重要性：</p>
- 立即重用现有代码：遗留脚本、内部库、API。
- 自动化复杂工作流：AI 可以可靠地协调多个工具。
- 即插即用：多个 Python 函数可以在同一 MCP 服务器上暴露。
- 减少开发时间：无需自定义包装器或中间件。
- 内置可靠性：包含输入/输出验证和错误处理。
<p>Polymcp 使 Python 函数能够被 AI 代理立即使用，标准化了企业软件的集成。</p>
<p>代码库：<a href="https://github.com/poly-mcp/Polymcp" rel="nofollow">https://github.com/poly-mcp/Polymcp</a></p>
查看原文
I built Polymcp, a framework that allows you to transform any Python function into an MCP (Model Context Protocol) tool ready to be used by AI agents. No rewriting, no complex integrations.<p>Examples<p>Simple function:<p>from polymcp.polymcp_toolkit import expose_tools_http<p>def add(a: int, b: int) -> int:
"""Add two numbers"""
return a + b<p>app = expose_tools_http([add], title="Math Tools")<p>Run with:<p>uvicorn server_mcp:app --reload<p>Now add is exposed via MCP and can be called directly by AI agents.<p>API function:<p>import requests
from polymcp.polymcp_toolkit import expose_tools_http<p>def get_weather(city: str):
"""Return current weather data for a city"""
response = requests.get(f"<a href="https://api.weatherapi.com/v1/current.json?q={city}" rel="nofollow">https://api.weatherapi.com/v1/current.json?q={city}</a>")
return response.json()<p>app = expose_tools_http([get_weather], title="Weather Tools")<p>AI agents can call get_weather("London") to get real-time weather data instantly.<p>Business workflow function:<p>import pandas as pd
from polymcp.polymcp_toolkit import expose_tools_http<p>def calculate_commissions(sales_data: list[dict]):
"""Calculate sales commissions from sales data"""
df = pd.DataFrame(sales_data)
df["commission"] = df["sales_amount"] * 0.05
return df.to_dict(orient="records")<p>app = expose_tools_http([calculate_commissions], title="Business Tools")<p>AI agents can now generate commission reports automatically.<p>Why it matters for companies
• Reuse existing code immediately: legacy scripts, internal libraries, APIs.
• Automate complex workflows: AI can orchestrate multiple tools reliably.
• Plug-and-play: multiple Python functions exposed on the same MCP server.
• Reduce development time: no custom wrappers or middleware needed.
• Built-in reliability: input/output validation and error handling included.<p>Polymcp makes Python functions immediately usable by AI agents, standardizing integration across enterprise software.<p>Repo: <a href="https://github.com/poly-mcp/Polymcp" rel="nofollow">https://github.com/poly-mcp/Polymcp</a>