Playwright Browser Automation MCP Server

Browser AutomationJavaScript

Automate browser interactions, take screenshots, and scrape web content

Available Tools

navigateTo

Navigate to a specified URL in the browser

click

Click on an element identified by a selector

fill

Fill a form field with text

screenshot

Take a screenshot of the current page

getPageContent

Get the HTML content of the current page

executeJavaScript

Execute JavaScript code in the browser context

generateTestCode

Generate test automation code for the current page

scrapeWebPage

Extract structured data from the current web page

Playwright MCP Server provides powerful browser automation capabilities using the Playwright framework. It enables AI assistants to interact with web pages, take screenshots, generate test code, scrape web content, and execute JavaScript in a real browser environment. This tool bridges the gap between AI language models and web browsing, allowing for dynamic web interactions and data extraction.

Overview

Playwright MCP Server enables AI assistants to control web browsers, allowing them to navigate websites, interact with elements, capture screenshots, and extract data. This powerful tool leverages Microsoft's Playwright framework to provide cross-browser automation capabilities.

Installation Options

You can install Playwright MCP Server using one of the following methods:

Using npm

npm install -g @executeautomation/playwright-mcp-server

Using mcp-get

npx @michaellatman/mcp-get@latest install @executeautomation/playwright-mcp-server

Using Smithery

For automatic installation with Claude Desktop:

npx @smithery/cli install @executeautomation/playwright-mcp-server --client claude

Installation in VS Code

For VS Code users, you can install the Playwright MCP Server through the Cursor extension or directly via npm.

Configuration

After installation, you'll need to configure your AI client to use the Playwright MCP Server. Add the following configuration to your client's settings:

"mcpServers": {
  "playwright-server": {
    "command": "playwright-mcp-server",
    "args": []
  }
}

Usage

Once installed and configured, your AI assistant can use Playwright to:

Navigate to websites: Open any URL in a browser
Interact with elements: Click buttons, fill forms, and more
Take screenshots: Capture visual evidence of web pages
Extract content: Scrape text, links, and other data from web pages
Execute JavaScript: Run custom scripts within the browser context
Generate test code: Create automation scripts for testing

Examples

Here are some example commands you can use:

"Navigate to example.com and take a screenshot"
"Fill out the login form on website.com with my credentials"
"Extract all product information from an e-commerce page"
"Click the submit button and tell me what happens"

Troubleshooting

If you encounter issues:

Ensure the server is properly installed and running
Check that your AI client is correctly configured to use the server
Verify that you have the necessary permissions for browser automation
For specific errors, refer to the official documentation