MCP Server Playwright

Name: MCP Server Playwright
Author: thesimsguy

@thesimsguy

代码仓库

关于 MCP Server Playwright

暂无概览

#browser-automation #playwright #mcp-server

基本信息

分类

浏览器自动化

许可证

MIT license

运行时

node

传输方式

stdio

发布者

thesimsguy

配置

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-thesimsguy": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "@automatalabs/mcp-server-playwright",
        "--client",
        "claude"
      ]
    }
  }
}

工具

未检测到工具

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 MCP Server Playwright?

MCP Server Playwright is a Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. It enables large language models (LLMs) to interact with web pages, take screenshots, and execute JavaScript in a real browser environment.

How to use MCP Server Playwright?

Install the server via Smithery (npx -y @smithery/cli install @automatalabs/mcp-server-playwright --client claude) or using npx (npx @automatalabs/mcp-server-playwright install) or mcp-get. The installation process checks OS compatibility and automatically creates or updates the Claude desktop configuration file at the appropriate path. The required configuration adds a playwright entry under mcpServers in the Claude config.

Key features of MCP Server Playwright

Full browser automation capabilities
Screenshot capture of entire pages or specific elements
Comprehensive web interaction (navigation, clicking, form filling)
Console log monitoring
JavaScript execution in browser context

Use cases of MCP Server Playwright

LLM-driven web page navigation and data extraction
Visual feedback through screenshot capture for LLM agents
Automated form filling and element interaction
Executing custom JavaScript in the browser console
Monitoring browser console logs for debugging

FAQ from MCP Server Playwright

What tools does MCP Server Playwright provide?

It provides tools for navigation (browser_navigate), screenshot capture (browser_screenshot), clicking elements (browser_click, browser_click_text), hovering (browser_hover, browser_hover_text), filling input fields (browser_fill), selecting options (browser_select, browser_select_text), and executing JavaScript (browser_evaluate).

How do I capture a screenshot?

Use the browser_screenshot tool with a required name parameter and optional selector and fullPage booleans (default false). The captured screenshot is then accessible via the screenshot://<n> resource.

Can I run JavaScript in the browser?

Yes, use the browser_evaluate tool with a script parameter (e.g., "document.title") to execute JavaScript in the browser console.

Where are screenshots and console logs stored?

Screenshots are available as PNG images at screenshot://<n>, referenced by the name given during capture. Console logs are available as text at console://logs, including all browser console messages.

How do I configure MCP Server Playwright with Claude?

After installation, the Claude config file is automatically updated with a playwright entry: "command": "npx", "args": ["-y", "@automatalabs/mcp-server-playwright"]. On Windows the config is at `%APPDATA%\Claude\claude_d