开源 MCP 客户端仓库（MCP-Use）

山行AI

发布于 2026-03-13 21:03:22

1850

开源 MCP 客户端库（MCP-Use）

🌐 MCP-Use 是一种开源工具，可将**任意大语言模型（LLM）**连接到任何 MCP 服务器，帮助开发人员构建自定义的智能代理，访问诸如网页浏览、文件操作等工具，无需使用封闭源或专用客户端。

💡 让开发者轻松连接任意 LLM 到浏览网页、文件操作等各种工具。

主要功能

功能	描述
🔄 易于使用	只需6行代码即可创建一个支持MCP的代理
🤖 LLM灵活性	支持任何LangChain兼容、支持工具调用的LLM（如OpenAI、Anthropic、Groq、LLama等）
🌐 HTTP支持	直接连接到运行在特定HTTP端口的MCP服务器
🧩 多服务器支持	单个代理可同时使用多个MCP服务器
🛡️ 工具访问限制	可限制具有潜在危险性的工具，如文件系统或网络访问

快速开始

安装：

pip install mcp-use

从源代码安装：

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

安装 LangChain 提供者

根据使用的LLM安装对应的LangChain提供者。例如：

# 对于OpenAI
pip install langchain-openai

# 对于Anthropic
pip install langchain-anthropic

在.env文件中添加API密钥：

OPENAI_API_KEY=
ANTHROPIC_API_KEY=

注意: 仅支持具备工具调用功能的模型。

启动代理

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

async def main():
    load_dotenv()
    config = {
        "mcpServers": {
            "playwright": {
                "command": "npx",
                "args": ["@playwright/mcp@latest"],
                "env": {"DISPLAY": ":1"}
            }
        }
    }
    client = MCPClient.from_dict(config)
    llm = ChatOpenAI(model="gpt-4o")
    agent = MCPAgent(llm=llm, client=client, max_steps=30)
    result = await agent.run("查找旧金山最好的餐厅")
    print(f"\n结果: {result}")

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

也可使用配置文件创建客户端：

client = MCPClient.from_config_file("browser_mcp.json")

配置文件示例 (browser_mcp.json)：

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

使用场景示例

网页浏览（使用Playwright）

# 同快速启动代码示例
import asyncio
import os
from dotenv import load_dotenv
from langchain_openai import ChatOpenAI
from mcp_use import MCPAgent, MCPClient

async def main():
    # 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

# Airbnb搜索代码示例
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创建

# Blender 3D创建代码示例
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

# 从配置文件初始化MCP会话
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

支持连接到HTTP端口运行的MCP服务器：

# HTTP连接示例代码
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())

多服务器支持

支持同时使用多个MCP服务器：

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

工具访问控制

限制代理可访问的工具，提高安全性：

agent = MCPAgent(
    llm=ChatOpenAI(model="gpt-4"),
    client=client,
    disallowed_tools=["file_system", "network"]
)

路线图

• 支持多服务器• 远程连接测试（HTTP、WS）• 更多功能持续开发中

贡献

欢迎提交问题和功能请求。

系统要求

•Python 3.11+•MCP实现（如Playwright MCP）•LangChain和相应模型库

引用方式

若在研究或项目中使用，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}
}

MIT许可。

声明：本文由山行AI翻译整理自：https://github.com/mcp-use/mcp-use，如果对您有帮助，请帮忙点赞、关注、收藏，谢谢～

本文参与腾讯云自媒体同步曝光计划，分享自微信公众号。

原始发表：2025-04-18，如有侵权请联系 cloudcommunity@tencent.com 删除

客户端