MCP Playwright Server

Automate web testing and tasks by connecting Claude Desktop with Playwright.

🚀 AI-Powered Browser Automation for Claude Desktop

Bridge the gap between AI and web automation with this revolutionary MCP server

A Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. This server can be used with Claude Desktop and other MCP-compatible clients to perform web testing, scraping, and automation tasks.

- 🤖 AI-First Design: Built specifically for AI agents and natural language automation
- 🎭 Multi-Browser Support: Chromium, Firefox, and WebKit out of the box
- 🐳 Production Ready: Docker support for consistent, scalable deployments
- ⚡ Lightning Fast: Optimized for enterprise-grade testing workflows
- 🔧 Developer Friendly: Comprehensive tooling and extensive documentation

- Multi-browser support: Chromium, Firefox, and WebKit
- Comprehensive automation: Navigate, click, type, screenshot, and more
- Docker support: Run in containers for consistent environments
- Testing framework: Built-in Playwright test configuration
- MCP integration: Compatible with Claude Desktop and other MCP clients

- launch_browser- Launch a new browser instance
- new_page- Create a new page in an existing browser
- navigate- Navigate to a URL
- click- Click on an element
- type_text- Type text into input fields
- get_text- Extract text content from elements
- screenshot- Take screenshots of pages
- wait_for_selector- Wait for elements to appear
- close_page- Close a page
- close_browser- Close a browser and all its pages

npm install -g mcp-playwright && mcp-playwright start

To use this MCP server with Claude Desktop, add the following to your Claude Desktop configuration file:

Edit~/Library/Application Support/Claude/claude_desktop_config.json:

{ "mcpServers": { "playwright": { "command": "node", "args": ["/path/to/your/mcpplaywright/src/index.js"], "env": { "PLAYWRIGHT_HEADLESS": "true" } } } }

{ "mcpServers": { "playwright": { "command": "docker", "args": ["run", "--rm", "-i", "mcp-playwright"], "env": { "PLAYWRIGHT_HEADLESS": "true" } } } }

// Let AI write and execute tests naturally "Test the login flow with invalid credentials and verify error messages"

// Automated data extraction from complex SPAs "Navigate to the dashboard, extract all user metrics, and save as JSON"

// Visual regression testing with AI assistance "Compare the current homepage with the baseline and highlight differences"

// Launch a browser const browser = await launchBrowser({ browserType: 'chromium', headless: true }); // Create a new page const page = await newPage({ browserId: browser.id, url: 'https://example.com' }); // Take a screenshot await screenshot({ pageId: page.id, path: 'example.png' }); // Click on an element await click({ pageId: page.id, selector: 'button#submit' }); // Type text await typeText({ pageId: page.id, selector: 'input[name="email"]', text: 'test@example.com' }); // Get text content const text = await getText({ pageId: page.id, selector: 'h1' });

# Run all tests npm test # Run tests in headed mode (visible browser) npm run test:headed # Debug tests npm run test:debug

For development with automatic restarts:

To add new MCP tools, editsrc/index.jsand:
- Add the tool definition to thetoolsarray inListToolsRequestSchemahandler
- Add a case in theCallToolRequestSchemahandler
- Implement the tool method in thePlaywrightMCPServerclass

- PLAYWRIGHT_HEADLESS: Set tofalseto run browsers in headed mode
- PLAYWRIGHT_SLOWMO: Add delay between operations (milliseconds)

- Node.js 18
- All Playwright browsers pre-installed
- System dependencies for browser operation
- Optimized for headless operation

# Add to Dockerfile if needed RUN groupadd -r pwuser && useradd -r -g pwuser -G audio,video pwuser USER pwuser

For large-scale testing, increase Docker memory limits:

docker run --memory=2g --cpus=2 mcp-playwright

- 📺 Getting Started Video- 5-minute setup guide
- 📖 Complete Tutorial Series- From basics to advanced
- 🎮 Interactive Playground- Try it live

We love contributions! See ourContributing Guidefor details.

⭐ GitHub Stars: 150+ (and growing!) 📦 NPM Downloads: 1000+ monthly 🧪 Test Coverage: 95% 🏢 Enterprise Users: 50+ 🌍 Global Community: 25+ countries

- ⭐Starringthis repository
- 🐦Sharingon social media
- 💬JoiningourDiscord community
- ☕Sponsoringdevelopment

Create and manage end-to-end tests using the Octomind platform.