8种主流Agent框架与MCP的集成，让你一文搞懂Agent框架！

import asyncio, os
from agents import Agent, Runner, AsyncOpenAI, OpenAIChatCompletionsModel, RunConfig
from agents.mcp import MCPServerStdio

asyncdefmain():
    # 1. 创建MCP Server实例
    search_server = MCPServerStdio(
        params={
            "command": "npx",
            "args": ["-y", "@mcptools/mcp-tavily"],
            "env": {**os.environ}
        }
    )
    await search_server.connect()

    # 2. 创建Agent并集成MCP Server
    agent = Agent(
        name="助手Agent",
        instructions="你是一个具有网页搜索能力的助手，必要时使用搜索工具获取信息。",
        mcp_servers=[search_server], # 将MCP Server列表传入Agent
    )

    # 3. 运行Agent，让其自动决定何时调用搜索工具
    result = await Runner.run(agent, "Llama4.0发布了吗？",run_config=RunConfig(tracing_disabled=True))
    print(result.final_output)

    await search_server.cleanup()

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

import asyncio, os
from langchain_mcp_adapters.client import MultiServerMCPClient

from langchain_core.messages import SystemMessage, HumanMessage
from langchain_openai import ChatOpenAI
from dotenv import load_dotenv
from langgraph.prebuilt import create_react_agent

# 加载环境变量
load_dotenv()

# 定义大语言模型
model = ChatOpenAI(model="gpt-4o-mini")

# 定义并运行agent
asyncdefrun_agent():
    # 定义MCP服务器，用于访问Tavily搜索工具
    asyncwith MultiServerMCPClient(
        {
            "tavily": {
            "command": "npx",
            "args": ["-y", "@mcptools/mcp-tavily"],
            "env": {**os.environ} # 传递环境变量给MCP工具
            }
        }
    ) as client:

        # 创建ReAct风格的agent
        agent = create_react_agent(model, client.get_tools())

        # 定义系统消息，指导如何使用工具
        system_message = SystemMessage(content=(
                "你是一个具有网页搜索能力的助手，必要时使用搜索工具获取信息。"
        ))

        # 处理查询
        agent_response = await agent.ainvoke({"messages": [system_message, HumanMessage(content="Llama4.0发布了吗？")]})

        # 返回agent的回答
        return agent_response["messages"][-1].content

# 运行agent
if __name__ == "__main__":
    response = asyncio.run(run_agent())
    print("\n最终回答:", response)

from llama_index.tools.mcp import McpToolSpec,BasicMCPClient
import asyncio
from llama_index.llms.openai import OpenAI
from llama_index.core.agent import ReActAgent
import os

llm = OpenAI(model="gpt-4o-mini")

asyncdefmain():

    mcp_client = BasicMCPClient("npx", ["-y", "@mcptools/mcp-tavily"], env={**os.environ})
    mcp_tool = McpToolSpec(client=mcp_client)
    tools = await mcp_tool.to_tool_list_async()

    agent = ReActAgent.from_tools(
        tools,
        llm=llm,
        verbose=True,
        system_prompt="你是一个具有网页搜索能力的助手，必要时使用搜索工具获取信息。"
    )

    response = await agent.aquery("Llama4.0发布了吗？")
    print(response) 

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

from autogen_ext.tools.mcp import StdioServerParams, mcp_server_tools
...

async def get_mcp_tools():
    server_params = StdioServerParams(
        command="npx", 
        args = [
        "-y",
        "@mcptools/mcp-tavily",
      ],env={**os.environ}
    )
    tools = await mcp_server_tools(server_params)
    return tools
...


classToolUseAgent(RoutedAgent):
...


async defmain():
    """主函数，设置并运行agent系统"""
    # 创建单线程agent运行时
    runtime = SingleThreadedAgentRuntime()

    mcp_tools = await get_mcp_tools()
    tools = [*mcp_tools]

    # 注册agent类型
    await ToolUseAgent.register(runtime, "my_agent", lambda: ToolUseAgent(tools))
...

    message = Message('Llama4.0发布了吗？)
    response = await runtime.send_message(message, AgentId("my_agent", "default"))

from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStdio
import os

server = MCPServerStdio( 
    'npx',
    ["-y", "@mcptools/mcp-tavily"],
    env={**os.environ} 
)

agent = Agent(
        name="助手Agent",
        system_prompt="你是一个具有网页搜索能力的助手，必要时使用搜索工具获取信息。",
        model='openai:gpt-4o-mini', 
        mcp_servers=[server])

async def main():
    asyncwith agent.run_mcp_servers():
        result = await agent.run('"Llama4.0发布了吗?')
    print(result.data)

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

from smolagents import ToolCollection, CodeAgent
from smolagents.agents import ToolCallingAgent
from smolagents import tool, LiteLLMModel
from mcp import StdioServerParameters
import os

model = LiteLLMModel(model_id="gpt-4o-mini")

server_parameters = StdioServerParameters(
    command="npx",
    args=["-y", "@mcptools/mcp-tavily"],
    env={**os.environ},
)

with ToolCollection.from_mcp(server_parameters, trust_remote_code=True) as tool_collection:
    agent = ToolCallingAgent(tools=[*tool_collection.tools], model=model)
    response = agent.run("llama4.0发布了吗？")
    print(response)