当前位置：首页 > news >正文

多路由隔离：构建模块化Agent工具服务器

news 2025/10/22 7:59:30

在构建多Agent系统时，工具隔离是一个关键需求。通过Starlette和FastMCP，我们可以创建一个支持多路由隔离的工具服务器，让不同Agent调用各自专属的工具集。

核心思路：路由隔离工具集

from starlette.applications import Starlette
from starlette.routing import Mount
from mcp.server.fastmcp import FastMCP# 创建多个独立的MCP实例
github_mcp = FastMCP("GitHub API")
browser_mcp = FastMCP("Browser")
curl_mcp = FastMCP("Curl")
search_mcp = FastMCP("Search")# 应用配置
app = Starlette(routes=[Mount("/github", app=github_mcp.sse_app()),Mount("/browser", app=browser_mcp.sse_app()),Mount("/curl", app=curl_mcp.sse_app()),Mount("/search", app=search_mcp.sse_app()),]
)

这种架构的关键优势在于：

工具隔离：每个路由下的工具相互独立
模块化设计：按功能划分工具组
独立扩展：不同工具集可以单独扩展和部署
权限控制：为不同Agent分配不同路由权限

工具定义示例

GitHub工具集（/github路由）

@github_mcp.tool()
async def search_github_repos(query: str, limit: int = 10) -> Dict[str, Any]:"""搜索GitHub仓库"""url = f"https://api.github.com/search/repositories?q={query}&per_page={limit}"response = requests.get(url)return response.json()

浏览器工具集（/browser路由）

@browser_mcp.tool()
async def get_webpage_title(url: str) -> Dict[str, Any]:"""获取网页标题"""try:response = requests.get(url, timeout=5)# 简单提取标题import retitle_match = re.search(r'<title>(.*?)</title>', response.text, re.IGNORECASE | re.DOTALL)title = title_match.group(1) if title_match else "未找到标题"return {"url": url, "title": title}except Exception as e:return {"url": url, "error": str(e)}

客户端调用示例

不同Agent可以访问各自的路由：

# GitHub Agent
github_client = Client("http://localhost:8000/github/sse")
await github_client.call_tool("search_github_repos", {"query": "AI"})# 浏览器Agent
browser_client = Client("http://localhost:8000/browser/sse")
await browser_client.call_tool("get_webpage_title", {"url": "https://example.com"})

架构优势分析

职责分离：每个工具组专注于特定领域
安全隔离：敏感工具（如curl）可单独保护
性能优化：高负载工具可独立扩展
版本管理：不同工具组可独立升级

实际应用场景

多Agent协作系统：不同Agent使用不同工具集
微服务架构：每个路由作为独立微服务
权限分级系统：根据用户角色分配路由访问权限
A/B测试环境：不同路由部署不同版本工具

总结

通过Starlette的路由挂载功能和FastMCP的工具管理能力，我们可以构建高度模块化的Agent工具服务器。这种架构不仅实现了工具隔离，还为系统的可扩展性和安全性提供了坚实基础。

if __name__ == "__main__":import uvicornuvicorn.run(app, host="0.0.0.0", port=8000)

启动服务器后，不同Agent就可以通过各自的路由访问专属工具集，实现安全、高效的协作。

mcp 服务

from starlette.applications import Starlette
from starlette.routing import Mount
from mcp.server.fastmcp import FastMCPimport requestsfrom typing import Dict, Any# Create multiple MCP servers
github_mcp = FastMCP("GitHub API")
browser_mcp = FastMCP("Browser")
curl_mcp = FastMCP("Curl")
search_mcp = FastMCP("Search")@github_mcp.tool()
async def search_github_repos(query: str, limit: int = 10) -> Dict[str, Any]:"""搜索GitHub仓库Args:query: 搜索关键词limit: 返回结果数量限制，默认10个Returns:包含仓库信息的字典"""url = f"https://api.github.com/search/repositories?q={query}&per_page={limit}"response = requests.get(url)return response.json()@browser_mcp.tool()
async def get_webpage_title(url: str) -> Dict[str, Any]:"""获取网页标题Args:url: 网页地址Returns:包含网页标题的字典"""try:response = requests.get(url, timeout=5)# 简单提取标题import retitle_match = re.search(r'<title>(.*?)</title>', response.text, re.IGNORECASE | re.DOTALL)title = title_match.group(1) if title_match else "未找到标题"return {"url": url, "title": title}except Exception as e:return {"url": url, "error": str(e)}@curl_mcp.tool()
async def make_http_request(url: str, method: str = "GET", headers: Dict[str, str] = None) -> Dict[str, Any]:"""发起HTTP请求Args:url: 请求地址method: HTTP方法，默认GETheaders: 请求头Returns:HTTP响应结果"""try:if headers is None:headers = {}response = requests.request(method, url, headers=headers)return {"status_code": response.status_code,"headers": dict(response.headers),"content": response.text[:1000]  # 限制返回内容长度}except Exception as e:return {"error": str(e)}@search_mcp.tool()
async def search_text(query: str, texts: list) -> Dict[str, Any]:"""在文本列表中搜索关键词Args:query: 搜索关键词texts: 要搜索的文本列表Returns:包含匹配文本的列表"""results = []for i, text in enumerate(texts):if query.lower() in text.lower():results.append({"index": i, "text": text})return {"query": query, "results": results}app = Starlette(routes=[# Using settings-based configurationMount("/github", app=github_mcp.sse_app()),Mount("/browser", app=browser_mcp.sse_app()),Mount("/curl", app=curl_mcp.sse_app()),Mount("/search", app=search_mcp.sse_app()),]
)if __name__ == "__main__":import uvicornuvicorn.run(app, host="0.0.0.0", port=8000)

客户请求

import asyncio
from fastmcp import Clientclient = Client("http://localhost:8000/search/sse")async def call_tool(name: str):async with client:result = await client.list_tools()print(result)result = await client.call_tool("search_text", {"query": name,"texts":["dfdsf","sdfsdfsf"]})print(result)asyncio.run(call_tool("Ford"))client = Client("http://localhost:8000/curl/sse")async def call_tool(name: str):async with client:result = await client.list_tools()print(result)asyncio.run(call_tool("Ford"))client = Client("http://localhost:8000/browser/sse")async def call_tool(name: str):async with client:result = await client.list_tools()print(result)asyncio.run(call_tool("Ford"))client = Client("http://localhost:8000/github/sse")async def call_tool(name: str):async with client:result = await client.list_tools()print(result)asyncio.run(call_tool("Ford"))