mcp playwright 简单试用

主要是一个演示集成，可以体验到mcp+ 大模型的方便之处

参考玩法

简单说明: 用户可以通过mcp client 或者集成的agent，然后client 配置playwright mcp 服务，对于 playwright mcp 服务可以使用remote cdp server 这样可以减少本地的资源占用（可以使用browserless后者资源占用比较少的lightpanda/browser）

参考示例

app.py

我使用了deepseek模型

import asyncio
from dotenv import load_dotenv
from mcp_use import MCPAgent, MCPClient
from langchain_openai import ChatOpenAI
async def main():
    load_dotenv(".env")
    config = {
      "mcpServers": {
        "playwright": {
          "command": "npx",
          "args": ["@playwright/mcp@latest","--user-agent","Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3","--cdp-endpoint","ws://xxxxxxx:3000"],
          "env": {
            "DISPLAY": ":1"
          }
        }
    }
    client = MCPClient.from_dict(config)
    llm = ChatOpenAI(model="deepseek-chat")
    agent = MCPAgent(llm=llm, client=client, max_steps=30)
    # Run the query
    agent.memory_enabled =False
    result = await agent.run(
        "打开https://www.cnblogs.com/rongfengliang/p/18975058,对于博客内容进行总结",
        external_history=None
    )
    print(f"\nResult: {result}")

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