Playwright MCP
About
Control a browser for automation and web scraping tasks using Playwright.
Details
- Author
- misanthropic-ai
- Categories
- Web Scraping, Automation, Developer Tools, Other
Jump to
Setup
Install Playwright MCP in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/misanthropic-ai/playwrite-mcp
Follow the installation instructions in the repository README, then restart your MCP client.
Playwright wrapper for MCP (Model Context Protocol). This server enables LLM-powered clients to control a browser for automation tasks.
The server exposes resources for accessing browser screenshots:
- Screenshot resource URI:screenshot://{page_id}
- Screenshot resources are automatically available for all open pages
The server provides a prompt to help clients interpret web pages:
- interpret-page: Analyzes the current web page content and structure
- Optionalpage_idargument to select which page to interpret
- Optionalfocusargument to focus on specific aspects (full, forms, navigation, text)
- Returns both text analysis and a screenshot of the page
The server implements a comprehensive set of browser automation tools:
- navigate: Go to a specific URL
- new_page: Create a new browser page with a specific ID
- switch_page: Switch to a different browser page
- get_pages: List all available browser pages
- click: Click on an element using CSS selector
- type: Type text into an input element
- wait_for_selector: Wait for an element to appear on the page
- get_text: Get text content from an element
- get_page_content: Get the entire page HTML
- take_screenshot: Capture visual state of the page or element
uv add playwright playwright install chromium
On MacOS:~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows:%APPDATA%/Claude/claude_desktop_config.json
"mcpServers": { "playwright-mcp": { "command": "uv", "args": [ "--directory", "/Users/shannon/Workspace/artivus/playwright-mcp", "run", "playwright-mcp" ] } }
"mcpServers": { "playwright-mcp": { "command": "uvx", "args": [ "playwright-mcp" ] } }
To prepare the package for distribution:
This will create source and wheel distributions in thedist/directory.
Note: You'll need to set PyPI credentials via environment variables or command flags:
- Token:--tokenorUV_PUBLISH_TOKEN
- Or username/password:--username/UV_PUBLISH_USERNAMEand--password/UV_PUBLISH_PASSWORD
Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using theMCP Inspector.
You can launch the MCP Inspector vianpmwith this command:
npx @modelcontextprotocol/inspector uv --directory /Users/shannon/Workspace/artivus/playwright-mcp run playwright-mcp
Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
Take screenshots and read console logs from web pages using Playwright.
Official Playwright MCP server for browser automation, page inspection, screenshots, and web interaction from Claude, Cursor, and other AI agents.
Render website screenshots with ScreenshotOne
Attaches to existing browser sessions using the Chrome DevTools Protocol for automation and interaction.
A browser screenshot tool to capture scrolling screenshots of webpages using Playwright, with support for intelligent section identification and multiple output formats.
Help your AI agent finish more browser tasks.
Automate remote browsers using the BrowserCat API.
Remote browser automation using the BrowserCat API.
Automate browser tasks using the Browser Use API.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.


