Open Source MCP CLient Library

开源 MCP 客户端库

🌐 MCP-Use 是一种开源方式，可将任意大模型连接到 MCP 工具，并构建具备工具访问权限的自定义 Agent，无需使用闭源客户端或应用客户端。

💡 让开发者轻松将任意大模型连接到网页浏览、文件操作等工具。

功能

✨ 主要功能

功能	描述
🔄 易于使用	只需 6 行代码，即可创建你的第一个支持 MCP 的 Agent
🤖 大模型灵活性	兼容 LangChain 支持的、具备工具调用能力的任意大模型（OpenAI、Anthropic、Groq、LLama 等）
🌐 HTTP 支持	直接连接到运行在指定 HTTP 端口上的 MCP 服务
🧩 多服务支持	在单个 Agent 中同时使用多个 MCP 服务
🛡️ 工具限制	限制可能有危险的工具，例如文件系统或网络访问

快速开始

使用 pip：

pip install mcp-use

或从源代码安装：

git clone https://github.com/pietrozullo/mcp-use.git
cd mcp-use
pip install -e .

安装 LangChain 提供程序

mcp_use 可通过 LangChain 与各种大模型提供程序配合使用。你需要为所选的大模型安装相应的 LangChain 提供程序包。例如：

# For OpenAI
pip install langchain-openai

# For Anthropic
pip install langchain-anthropic

# For other providers, check the [LangChain chat models documentation](https://python.langchain.com/docs/integrations/chat/)

并将所需提供程序的 API 密钥添加到你的 .env 文件中。

OPENAI_API_KEY=
ANTHROPIC_API_KEY=

重要提示：只有具备工具调用能力的模型才能与 mcp_use 配合使用。请确保所选模型支持函数调用或工具使用。

启动你的 Agent：

import asyncio
import os
from dotenv import load_dotenv
from langchain_openai import ChatOpenAI
from mcp_use import MCPAgent, MCPClient

async def main():
    # Load environment variables
    load_dotenv()

    # Create configuration dictionary
    config = {
      "mcpServers": {
        "playwright": {
          "command": "npx",
          "args": ["@playwright/mcp@latest"],
          "env": {
            "DISPLAY": ":1"
          }
        }
      }
    }

    # Create MCPClient from configuration dictionary
    client = MCPClient.from_dict(config)

    # Create LLM
    llm = ChatOpenAI(model="gpt-4o")

    # Create agent with the client
    agent = MCPAgent(llm=llm, client=client, max_steps=30)

    # Run the query
    result = await agent.run(
        "Find the best restaurant in San Francisco",
    )
    print(f"\nResult: {result}")

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

你也可以像这样从配置文件添加服务配置：

client = MCPClient.from_config_file(
        os.path.join("browser_mcp.json")
    )

配置文件示例（browser_mcp.json）：

{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": ["@playwright/mcp@latest"],
      "env": {
        "DISPLAY": ":1"
      }
    }
  }
}

有关其他设置、模型等信息，请查阅文档。

使用场景示例

使用 Playwright 浏览网页

import asyncio
import os
from dotenv import load_dotenv
from langchain_openai import ChatOpenAI
from mcp_use import MCPAgent, MCPClient

async def main():
    # Load environment variables
    load_dotenv()

    # Create MCPClient from config file
    client = MCPClient.from_config_file(
        os.path.join(os.path.dirname(__file__), "browser_mcp.json")
    )

    # Create LLM
    llm = ChatOpenAI(model="gpt-4o")
    # Alternative models:
    # llm = ChatAnthropic(model="claude-3-5-sonnet-20240620")
    # llm = ChatGroq(model="llama3-8b-8192")

    # Create agent with the client
    agent = MCPAgent(llm=llm, client=client, max_steps=30)

    # Run the query
    result = await agent.run(
        "Find the best restaurant in San Francisco USING GOOGLE SEARCH",
        max_steps=30,
    )
    print(f"\nResult: {result}")

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

Airbnb 搜索

import asyncio
import os
from dotenv import load_dotenv
from langchain_anthropic import ChatAnthropic
from mcp_use import MCPAgent, MCPClient

async def run_airbnb_example():
    # Load environment variables
    load_dotenv()

    # Create MCPClient with Airbnb configuration
    client = MCPClient.from_config_file(
        os.path.join(os.path.dirname(__file__), "airbnb_mcp.json")
    )

    # Create LLM - you can choose between different models
    llm = ChatAnthropic(model="claude-3-5-sonnet-20240620")

    # Create agent with the client
    agent = MCPAgent(llm=llm, client=client, max_steps=30)

    try:
        # Run a query to search for accommodations
        result = await agent.run(
            "Find me a nice place to stay in Barcelona for 2 adults "
            "for a week in August. I prefer places with a pool and "
            "good reviews. Show me the top 3 options.",
            max_steps=30,
        )
        print(f"\nResult: {result}")
    finally:
        # Ensure we clean up resources properly
        if client.sessions:
            await client.close_all_sessions()

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

配置文件示例（airbnb_mcp.json）：

{
  "mcpServers": {
    "airbnb": {
      "command": "npx",
      "args": ["-y", "@openbnb/mcp-server-airbnb"]
    }
  }
}

Blender 3D 创作

import asyncio
from dotenv import load_dotenv
from langchain_anthropic import ChatAnthropic
from mcp_use import MCPAgent, MCPClient

async def run_blender_example():
    # Load environment variables
    load_dotenv()

    # Create MCPClient with Blender MCP configuration
    config = {"mcpServers": {"blender": {"command": "uvx", "args": ["blender-mcp"]}}}
    client = MCPClient.from_dict(config)

    # Create LLM
    llm = ChatAnthropic(model="claude-3-5-sonnet-20240620")

    # Create agent with the client
    agent = MCPAgent(llm=llm, client=client, max_steps=30)

    try:
        # Run the query
        result = await agent.run(
            "Create an inflatable cube with soft material and a plane as ground.",
            max_steps=30,
        )
        print(f"\nResult: {result}")
    finally:
        # Ensure we clean up resources properly
        if client.sessions:
            await client.close_all_sessions()

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

配置文件支持

MCP-Use 支持从配置文件初始化，便于管理和切换不同的 MCP 服务配置：

import asyncio
from mcp_use import create_session_from_config

async def main():
    # Create an MCP session from a config file
    session = create_session_from_config("mcp-config.json")

    # Initialize the session
    await session.initialize()

    # Use the session...

    # Disconnect when done
    await session.disconnect()

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

HTTP 连接示例

MCP-Use 现在支持 HTTP 连接，因此你可以连接到运行在指定 HTTP 端口上的 MCP 服务。此功能特别适用于与基于 Web 的 MCP 服务集成。

以下是 HTTP 连接功能的使用示例：

import asyncio
import os
from dotenv import load_dotenv
from langchain_openai import ChatOpenAI
from mcp_use import MCPAgent, MCPClient

async def main():
    """Run the example using a configuration file."""
    # Load environment variables
    load_dotenv()

    config = {
        "mcpServers": {
            "http": {
                "url": "http://localhost:8931/sse"
            }
        }
    }

    # Create MCPClient from config file
    client = MCPClient.from_dict(config)

    # Create LLM
    llm = ChatOpenAI(model="gpt-4o")

    # Create agent with the client
    agent = MCPAgent(llm=llm, client=client, max_steps=30)

    # Run the query
    result = await agent.run(
        "Find the best restaurant in San Francisco USING GOOGLE SEARCH",
        max_steps=30,
    )
    print(f"\nResult: {result}")

if __name__ == "__main__":
    # Run the appropriate example
    asyncio.run(main())

此示例演示如何连接到运行在指定 HTTP 端口上的 MCP 服务。请确保在运行此示例前启动 MCP 服务。

多服务支持

MCP-Use 支持同时使用多个 MCP 服务，让你可以在单个 Agent 中组合来自不同服务的工具。这适用于需要多种能力的复杂任务，例如将网页浏览与文件操作或 3D 建模结合起来。

配置

你可以在配置文件中配置多个服务：

{
  "mcpServers": {
    "airbnb": {
      "command": "npx",
      "args": ["-y", "@openbnb/mcp-server-airbnb", "--ignore-robots-txt"]
    },
    "playwright": {
      "command": "npx",
      "args": ["@playwright/mcp@latest"],
      "env": {
        "DISPLAY": ":1"
      }
    }
  }
}

使用

MCPClient 类提供了多种管理多个服务的方法：

import asyncio
from mcp_use import MCPClient, MCPAgent
from langchain_anthropic import ChatAnthropic

async def main():
    # Create client with multiple servers
    client = MCPClient.from_config_file("multi_server_config.json")

    # Create agent with the client
    agent = MCPAgent(
        llm=ChatAnthropic(model="claude-3-5-sonnet-20240620"),
        client=client
    )

    try:
        # Run a query that uses tools from multiple servers
        result = await agent.run(
            "Search for a nice place to stay in Barcelona on Airbnb, "
            "then use Google to find nearby restaurants and attractions."
        )
        print(result)
    finally:
        # Clean up all sessions
        await client.close_all_sessions()

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

工具访问控制

MCP-Use 支持限制 Agent 可用的工具，从而更好地保障安全并控制 Agent 的能力：

import asyncio
from mcp_use import MCPAgent, MCPClient
from langchain_openai import ChatOpenAI

async def main():
    # Create client
    client = MCPClient.from_config_file("config.json")

    # Create agent with restricted tools
    agent = MCPAgent(
        llm=ChatOpenAI(model="gpt-4"),
        client=client,
        disallowed_tools=["file_system", "network"]  # Restrict potentially dangerous tools
    )

    # Run a query with restricted tool access
    result = await agent.run(
        "Find the best restaurant in San Francisco"
    )
    print(result)

    # Clean up
    await client.close_all_sessions()

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

路线图

• [x] 同时连接多个服务
• [x] 测试远程连接器（http、ws）
• [ ] ...

贡献

我们欢迎贡献！如有 Bug 或功能需求，欢迎提交 issue。

要求

• Python 3.11+
• MCP 实现（例如 Playwright MCP）
• LangChain 和相应的模型库（OpenAI、Anthropic 等）

引用

如果您在研究或项目中使用 MCP-Use，请引用：

@software{mcp_use2025,
  author = {Zullo, Pietro},
  title = {MCP-Use: MCP Library for Python},
  year = {2025},
  publisher = {GitHub},
  url = {https://github.com/pietrozullo/mcp-use}
}

许可证

MIT