What are the prerequisites?
Docker and Docker Compose must be installed on the host system.
@iuill
基本信息
This project provides a Docker Compose environment to run the '@playwright/mcp' server.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"playwright_sse": {
"type": "http",
"url": "http://localhost:8931/sse"
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,直接连接服务器端点实时获取工具列表。
It is a Docker Compose environment that runs the @playwright/mcp server, enabling easy setup and management of the Playwright MCP server for use with clients like Cline or Cursor.
Clone the repository, copy .env.sample to .env, configure settings (port, headless mode, etc.), then build and start the container with docker-compose up --build -d. Configure your MCP client to use SSE with the URL http://localhost:<MCP_HOST_PORT>/sse. Stop the server with docker-compose down.
MCP_HOST_PORT environment variableDocker and Docker Compose must be installed on the host system.
Set `HEADLESS=true` or `HEADLESS=false` in the `.env` file and restart the container with `docker-compose up -d`.
Yes, default settings in `.env.sample` and `docker-compose.yml` are configured for WSLg. Adjust the WSL distribution name in paths if it is not `Ubuntu`.
The MCP server uses SSE (Server-Sent Events) on the configured host port.
Run `docker-compose down` from the project directory.
Give your AI agent the live web. One MCP server for Search, Fetch, Browser, and Agent: browse real sites, extract structured data, fill forms, and run multi-step workflows. Search and Fetch are free.
MCP server for fetch web page content using Playwright headless browser.
Helps AI assistants access text content from bot-protected websites. MCP server that fetches HTML/markdown from sites with anti-automation measures using Scrapling.
Allow LLMs to control a browser with Browserbase and Stagehand

Model Context Protocol Servers
评论