Browser Automation MCP Server by samihalawa - MCP Server

The Browser Automation MCP Server is designed to facilitate seamless browser automation for AI assistants like Claude. It allows programmatic control over web browsers, enabling tasks such as web navigation, form filling, and data extraction. The server is built using Node.js and leverages Playwright for robust browser automation. It supports a variety of features that make it a versatile tool for automating web interactions, capturing screenshots, and evaluating JavaScript in the browser context. This server is particularly useful for developers and AI researchers looking to integrate web automation capabilities into their AI models.

Features

Web Automation: Control web browsers programmatically
Screenshot Capture: Take screenshots of web pages
Element Interaction: Click, type, and interact with web elements
Navigation: Navigate between pages and manage browser state
Data Extraction: Extract data from web pages

MCP Tools

{'navigate': 'Navigate to a URL.'}
{'screenshot': 'Take a screenshot of the current page.'}
{'click': 'Click on an element.'}
{'type': 'Type text into an input field.'}
{'extract': 'Extract data from the page.'}
{'evaluate': 'Evaluate JavaScript in the browser context.'}

Usage with Different Platforms

Starting the Server

bash
npm start

Configuration


{
  "servers": {
    "browser-automation": {
      "command": "/path/to/node",
      "args": ["/path/to/browser-automation-server/build/index.js"],
      "enabled": true,
      "port": 3008,
      "environment": {
        "NODE_PATH": "/path/to/node_modules",
        "PATH": "/usr/local/bin:/usr/bin:/bin"
      }
    }
  }
}