How do I install MCP Server Playwright?
Run `npx @automatalabs/mcp-server-playwright install` or use Smithery with `npx -y @smithery/cli install @automatalabs/mcp-server-playwright --client claude`.
@aptcats
基本信息
MCP Server Playwright - A browser automation service for Claude Desktop
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-server-playwright": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@automatalabs/mcp-server-playwright",
"--client",
"claude"
]
}
}
}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,在临时沙箱中运行此服务器并实时获取工具列表。
MCP Server Playwright is a Model Context Protocol server that gives AI agents full browser automation capabilities via Playwright. It enables navigation, screenshot capture, form filling, clicking, JavaScript execution, and console log monitoring. It is designed for use with Claude and similar MCP clients.
Install the server using npx @automatalabs/mcp-server-playwright install or via Smithery (npx -y @smithery/cli install @automatalabs/mcp-server-playwright --client claude). The installer automatically updates your Claude desktop configuration. Once configured, invoke browser tools like browser_navigate, browser_screenshot, browser_click, browser_fill, and browser_evaluate from your MCP client.
Run `npx @automatalabs/mcp-server-playwright install` or use Smithery with `npx -y @smithery/cli install @automatalabs/mcp-server-playwright --client claude`.
The installer adds a `playwright` entry to your Claude desktop config with the command `npx -y @automatalabs/mcp-server-playwright`.
It provides `browser_navigate`, `browser_screenshot`, `browser_click`, `browser_click_text`, `browser_hover`, `browser_hover_text`, `browser_fill`, `browser_select`, `browser_select_text`, and `browser_evaluate`.
Screenshots are available as a resource at `screenshot://<name>`, where `<name>` is the name you provided during capture.
Console logs are exposed as a text resource at `console://logs` and include all console messages from the browser.
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.

An MCP server for generating images from HTML & CSS or screenshots of URLs using htmlcsstoimage.com.

Model Context Protocol Servers
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.
Browse the web, directly from Cursor etc.
评论