Browser Automation Server

🚀 Browser Automation MCP Server

A Model Context Protocol (MCP) server that provides browser automation capabilities for Claude and other MCP-compatible AI assistants.

🚀 Quick Start

This server offers browser automation functions for Claude and other MCP-compatible AI assistants. You can quickly set up and use it by following the steps below.

✨ Features

• Web Automation: Programmatically control web browsers.
• Screenshot Capture: Take screenshots of web pages.
• Element Interaction: Click, input, and interact with web elements.
• Navigation: Navigate between pages and manage browser state.
• Form Filling: Automatically fill out and submit forms.
• Data Extraction: Extract data from web pages.

📦 Installation

# Clone the repository
git clone https://github.com/samihalawa/browser-automation-server.git
cd browser-automation-server

# Install dependencies
npm install

# Build the server
npm run build

💻 Usage Examples

Starting the Server

npm start

Configuration

Add the server to your MCP 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"
      }
    }
  }
}

Available Tools

navigate

Navigate to the specified URL.

• url (string, required): The URL to navigate to.
• waitUntil (string, optional): Navigation wait condition. Options: 'load', 'domcontentloaded', 'networkidle'. Default: 'load'.

screenshot

Take a screenshot of the current page.

• fullPage (boolean, optional): Whether to capture the entire page or just the viewport. Default: false.
• path (string, optional): The path to save the screenshot. If not provided, a Base64-encoded image will be returned.

click

Click on the specified element.

• selector (string, required): The CSS selector of the element to click.
• waitForSelector (boolean, optional): Whether to wait for the selector to appear. Default: true.

type

Enter text in an input field.

• selector (string, required): The CSS selector of the input element.
• text (string, required): The text to enter.
• delay (number, optional): The delay between keystrokes in milliseconds. Default: 0.

extract

Extract data from the page.

• selector (string, required): The CSS selector of the element to extract.
• attribute (string, optional): The attribute to extract. If not provided, the text content will be extracted.

evaluate

Evaluate JavaScript in the browser context.

• script (string, required): The JavaScript code to evaluate.
• args (array, optional): The parameters passed to the script.

Basic Usage

Here are some basic usage examples:

1. Navigate to a website:

   navigate(url: "https://example.com")
   

2. Take a screenshot:

   screenshot(fullPage: true)
   

3. Click a button:

   click(selector: "#submit-button")
   

4. Fill out a form:

   type(selector: "#username", text: "user123")
   type(selector: "#password", text: "password123")
   click(selector: "#login-button")
   

5. Extract data:

   extract(selector: ".product-title", attribute: "innerText")
   

📚 Documentation

Requirements

• Node.js 14+
• Playwright for browser automation

📄 License

MIT