Playwright MCP
Automate web interactions and perform web scraping tasks using the Playwright framework.
Playwright MCP Configuration
This repository contains everything needed to launch and connect to a working Playwright MCP (Model Context Protocol) server.
✅ Overview
This setup allows you to automate and inspect web pages using structured data instead of screenshots — ideal for LLM-powered tools like Claude, Cursor, and VS Code AI agents.
🛠️ Prerequisites
-
Node.js v18 or newer
-
One of the following MCP-compatible clients:
- VS Code or VS Code Insiders
- Cursor
- Claude Desktop
📁 Repository Contents
.vscode/settings.json— VS Code configuration to launch Playwright MCPpackage.json— Includes required MCP dependenciesREADME.md— This file.gitignore— Basic Node project ignore rules
🚀 Getting Started
1. Clone the Repository
git clone https://github.com/faruklmu17/playwright_mcp.git
cd playwright-mcp-config
2. Install Dependencies
npm install
This installs all required packages, including @playwright/mcp.
3. Start the MCP Server
npx playwright-mcp --port 3550
You should see output like:
MCP Server started
Web server started
You can change the port if needed, e.g.
--port=4000
4. VS Code MCP Client Configuration
Add this to your .vscode/settings.json:
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": [
"@playwright/mcp@latest",
"--port=3550"
]
}
}
}
This tells VS Code (or Cursor) how to launch and connect to the MCP server.
5. Optional: Use Persistent or Isolated Sessions
Persistent (default)
The browser state is preserved across sessions.
Isolated Example
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": [
"@playwright/mcp@latest",
"--isolated",
"--storage-state=storage/state.json"
]
}
}
}
6. Additional Flags
You can enhance your MCP server using optional flags:
| Flag | Description |
|---|---|
--port <port> | Custom port (default is random/OS-assigned) |
--headless | Run without browser UI |
--device | Emulate a device (e.g., "iPhone 15") |
--vision | Enable screenshot-based vision (if supported) |
Check available flags with:
npx playwright-mcp --help
📅 Note About Browsers
You do not need to install playwright or run npx playwright install separately. The MCP package handles everything required for browser automation.
📄 .gitignore
node_modules/
.DS_Store
🤝 Contributing
Pull requests and suggestions are welcome!
📄 License
相關伺服器
Bright Data
贊助Discover, extract, and interact with the web - one interface powering automated access across the public internet.
Web-curl
Fetch, extract, and process web and API content. Supports resource blocking, authentication, and Google Custom Search.
MCP Web Research Server
A server for web research that brings real-time information into AI models like Claude.
MCP Go Colly Crawler
A web crawling framework that integrates the Model Context Protocol (MCP) with the Colly web scraping library.
MCP Chrome Integration
Control the Chrome browser for web automation using an AI model. Requires the MCP Chrome extension.
Website to Markdown MCP Server
Fetches and converts website content to Markdown with AI-powered cleanup, OpenAPI support, and stealth browsing.
Scrapfly
Scrapfly MCP Server gives AI agents a simple, unified way to scrape live web data with built-in anti-bot handling.
Context Scraper MCP Server
A server for web crawling and content extraction using the Crawl4AI library.
Feed
A server for fetching and parsing RSS, Atom, and JSON feeds.
Yahoo Finance
Provides comprehensive financial data from Yahoo Finance, including historical prices, company info, financial statements, and market news.
transcriptor-mcp
An MCP server (stdio + HTTP/SSE) that fetches video transcripts/subtitles via yt-dlp, with pagination for large responses. Supports YouTube, Twitter/X, Instagram, TikTok, Twitch, Vimeo, Facebook, Bilibili, VK, Dailymotion. Whisper fallback — transcribes audio when subtitles are unavailable (local or OpenAI API). Works with Cursor and other MCP host