brightdata-mcp-adk-hackathon

Overview

This is a full-ledged web scraping platform that combines BrightData's MCP server with Google's Agent Development Kit. It provides a complete solution with React frontend, FastAPI backend, and enterprise-grade scraping capabilities through BrightData's proxy network. The system supports various data extraction scenarios including e-commerce, social media, and business data, powered by Google Gemini 2.0 Flash for intelligent tool selection.

Try asking AI

After installing, here are 7 things you can ask your AI assistant:

• search_engine

  Multi-engine search results from Google, Bing, Yandex

  Try:Search for the latest trends in artificial intelligenceTry:Find information about sustainable energy solutions
• scrape_as_markdown

  Clean webpage extraction to markdown format

  Try:Extract the content from this webpage as markdownTry:Summarize the main points from this article
• scraping_browser_amazon

  Extract product information from Amazon

  Try:Find the top 10 selling laptops on AmazonTry:Get reviews and ratings for this product
• scraping_browser_walmart

  Extract product information from Walmart

  Try:Find the best deals on home appliances at WalmartTry:Check prices for this product across different categories
• scraping_browser_ebay

  Extract product information from eBay

  Try:Find vintage electronics on eBayTry:Get average selling price for this item
• scraping_linkedin

  Extract professional data from LinkedIn

  Try:Find tech companies in San Francisco on LinkedInTry:Get information about job postings for software engineers
• scraping_instagram

  Extract social media data from Instagram

  Try:Find trending hashtags related to travelTry:Get information about this influencer's profile
• scraping_youtube

  Extract video data from YouTube

  Try:Find tutorials on machine learningTry:Get statistics for this popular video
• scraping_crunchbase

  Extract business data from Crunchbase

  Try:Find venture-backed startups in fintechTry:Get funding information for this company
• scraping_yahoo_finance

  Extract financial data from Yahoo Finance

  Try:Get stock market performance for tech companiesTry:Find information about this company's earnings report
• scraping_google_maps

  Extract location data from Google Maps

  Try:Find restaurants near Times Square with high ratingsTry:Get information about businesses in this area
• scraping_zillow

  Extract real estate data from Zillow

  Try:Find houses for sale in Seattle under $500,000Try:Get rental prices for apartments in downtown Chicago

Comparable tools

Installation

git clone https://github.com/arjunprabhulal/brightdata-mcp-adk-hackathon.git
cd brightdata-mcp-adk-hackathon

cp backend/config/.env.example backend/config/.env
# Edit .env with your API credentials

docker compose up -d

{
  "mcpServers": {
    "brightdata-mcp": {
      "command": "python",
      "args": ["path/to/brightdata/mcp/server.py"],
      "env": {
        "BRIGHTDATA_API_TOKEN": "your_token_here"
      }
    }
  }
}

FAQ

What types of websites can this platform scrape?

The platform supports scraping various websites including e-commerce platforms (Amazon, Walmart), social media (LinkedIn, Instagram), news sources, business data platforms, and custom websites with anti-bot protection through BrightData's proxy network.

How is this different from other web scraping tools?

This platform integrates BrightData's MCP server with Google's Agent Development Kit and Gemini 2.0 Flash AI, enabling intelligent tool selection for optimal scraping. It provides a complete solution with UI, API, and enterprise infrastructure rather than just a scraping library.

What are the rate limits and pricing?

Pricing and rate limits depend on your BrightData subscription plan and API usage. The platform includes environment variable configuration for managing API tokens and authentication credentials.

Compare brightdata-mcp-adk-hackathon with