Playwright Universal MCP Server

Name: Playwright Universal MCP Server
Author: xkiranj

@xkiranj

代码仓库

基本信息

分类

浏览器自动化

许可证

MIT

传输方式

stdio

作者

xkiranj

关于 Playwright Universal MCP Server

A universal Playwright MCP server for browser automation in containerized environments

#playwright #browser-automation#containerized-environments

Playwright Universal MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "playwright-universal-mcp": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        "playwright-mcp-venv"
      ]
    }
  }
}

Playwright Universal MCP Server 工具

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。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Playwright Universal MCP?

Playwright Universal MCP is a Model Context Protocol (MCP) server for browser automation, designed to work reliably in containerized environments with limited privileges. It provides browser control capabilities to AI assistants such as Claude and GPT-4.

How to use Playwright Universal MCP?

Install via pipx, pip, or from source, then install browsers with playwright install chromium. Run the server with the command playwright-universal-mcp using options like --browser, --headless, --headful, --debug, or --browser-arg. Configure it as an MCP server in Claude Desktop by adding the command and arguments to claude_desktop_config.json.

Key features of Playwright Universal MCP?

Multi-browser support (Chromium, Firefox, WebKit, Edge, Chrome)
Works in containerized environments with limited privileges
Headless and headful modes for server or debugging
Extensive browser control:

浏览器自动化分类下的更多 MCP 服务器

Fastcrw

Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary.

286