Navigate to any URL in the browser
Capture screenshots of the entire page or specific elements
Click elements on the page using CSS selector
Click elements on the page by their text content
Hover over elements on the page
Type text into input fields
Extract text content from elements
Get the HTML content of the page or specific elements
Execute JavaScript code in the browser context
Retrieve console logs from the browser
Playwright Browser Automation is a powerful Model Context Protocol server that enables LLMs to interact with web pages in a real browser environment. It provides comprehensive browser automation capabilities including navigation, element interaction, screenshot capture, and JavaScript execution, allowing AI assistants to perform complex web tasks and gather visual information from websites.
Playwright Browser Automation provides a complete set of browser automation capabilities for AI assistants. This MCP server allows language models to navigate websites, interact with web elements, capture screenshots, and execute JavaScript in a real browser environment.
The easiest way to install Playwright Browser Automation is via Smithery:
npx -y @smithery/cli install @automatalabs/mcp-server-playwright --client claude
This command will automatically:
You can also install the package manually using npx:
npx @automatalabs/mcp-server-playwright install
Or using mcp-get:
npx @michaellatman/mcp-get@latest install @automatalabs/mcp-server-playwright
The installation process will automatically add the necessary configuration to your Claude config file, which is located at:
%APPDATA%\Claude\claude_desktop_config.json
~/Library/Application Support/Claude/claude_desktop_config.json
The installation process will automatically add the following configuration to your Claude config file:
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": ["-y", "@automatalabs/mcp-server-playwright"]
}
}
}
Once installed, the AI assistant can use the Playwright Browser Automation tools to perform various web-based tasks. The assistant can navigate to websites, interact with elements, take screenshots, and execute JavaScript code.
For example, to navigate to a website and take a screenshot:
browser_navigate
tool to go to a specific URLbrowser_screenshot
tool to capture the pageFor advanced users, the repository includes a Dockerfile for containerized deployment.
If you encounter issues with the installation:
For additional help, refer to the GitHub repository or open an issue there.