MCP Server

Integrating with Bright Data MCP Server

Bright Data Model Context Protocol (MCP) empowers your AI models and agents with real-time, reliable access to public web data. With Bright Data MCP, your applications can effortlessly retrieve both static and dynamic content from across the web, eliminating the need to build or maintain complex data scraping and unlocking infrastructure.

GitHub

Visit Bright Data GitHub repository

npm

Visit Bright Data npm repository

Configuration

Before you begin, ensure you have the below completed:

• Node.js package is installed and updated
• Make sure you have an account on Bright Data (new users get free credit for testing, and pay as you go options are available)
• Get your API key from the user settings page
• Create a Web Unlocker zone named mcp_unlocker in your control panel
• For browser automation capabilities create a Scraping Browser zone in your control panel (any zone name is allowed)

If you prefer to use a different zone name, you can specify it with the WEB_UNLOCKER_ZONE environment variable in your configuration

Step 1:

Install Bright Data MCP package:
https://www.npmjs.com/package/@brightdata/mcp

Step 2:

Choose your client configuration:

Claude

// Paste the below code onto your MCP configuration.json file

{
  "mcpServers": {
    "Bright Data": {
      "command": "npx",
      "args": ["@brightdata/mcp"],
      "env": {
        "API_TOKEN": "<insert-your-api-token-here>",
        "WEB_UNLOCKER_ZONE": "<optional if you want to override the default mcp_unlocker zone name>",
        "BROWSER_AUTH": "<optional if you want to enable remote browser control tools>"
      }
    }
  }
}

Examples

Extract real-time data from Google

“Extract all flight times depart from JFK airport to Heathrow in the next 24 hours”

Extract data from Linkedin

“Extract Bright Data overview section content from Linkedin”

Extract dynamic data from ebay.com

“Go to ebay.com, click the “shop by category” button on the navigation bar, extract all categories”