MCP.so
登录

playwright-server MCP server

@blackwhite084

代码仓库

关于 playwright-server MCP server

暂无概览

基本信息

分类

浏览器自动化

许可证

Apache-2.0

运行时

python

传输方式

stdio

发布者

blackwhite084

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-plus-python-mcp": {
      "command": "uv",
      "args": [
        "sync"
      ]
    }
  }
}

工具

8

Navigates to a specified URL. This operation will automatically create a new session if there is no active session.

Takes a screenshot of the current page or a specific element.

Clicks an element on the page using a CSS selector.

Fills out an input field.

Executes JavaScript code in the browser console.

Clicks an element on the page by its text content.

Get the text content of all visiable elements.

Get the HTML content of the page.

概览

What is playwright-server?

A Model Context Protocol (MCP) server that provides Playwright-based browser automation tools for navigation, screenshots, clicking, form filling, JavaScript execution, and content extraction. It also includes a simple note storage system with a summarization prompt.

How to use playwright-server?

Configure the server in your MCP client (e.g., Claude Desktop) by adding the playwright-server entry to the mcpServers configuration. Use the published package with uvx playwright-server or for development use uv --directory <path> run playwright-server. The server exposes tools that can be invoked via the MCP tools interface.

Key features of playwright-server

  • Navigate to URLs with automatic session creation.
  • Take full-page or element-specific screenshots.
  • Click elements by CSS selector or text content.
  • Fill input fields with specified values.
  • Execute JavaScript in the browser console.
  • Retrieve visible text or HTML content of a page.
  • Store and access notes via custom note:// URI scheme.
  • Generate note summaries with adjustable detail level.

Use cases of playwright-server

—

FAQ from playwright

评论

浏览器自动化 分类下的更多 MCP 服务器

Fastcrw

us

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

browser-use-mcp-server

co-browser

Browse the web, directly from Cursor etc.

827

@mendableai/firecrawl Mcp Server

mendableai

The API to search, scrape, and interact with the web at scale. 🔥

148.0K

fetch-mcp

egoist

An MCP server for fetching URLs / Youtube video transcript.

156

Scrapling Fetch MCP

cyberchitta

Helps AI assistants access text content from bot-protected websites. MCP server that fetches HTML/markdown from sites with anti-automation measures using Scrapling.

101