Bright Data

Integrates with Bright Data's web scraping platform to provide bot detection bypass, browser automation via Playwright, and access to 40+ pre-built datasets from major platforms like Amazon, LinkedIn, and Google Maps with structured data extraction and JSON conversion capabilities.

This MCP server provides integration with Bright Data's web scraping and data extraction platform, forked by dsouza-anush and adapted for Heroku deployment. It combines web unlocking capabilities that bypass bot detection and CAPTCHAs with browser automation tools powered by Playwright, plus access to 40+ pre-built datasets for major platforms like Amazon, LinkedIn, Instagram, TikTok, and Google Maps. The implementation includes both direct web scraping tools (markdown/HTML extraction, search engine results) and structured data retrieval from cached datasets, along with an AI-powered extraction tool that converts scraped content to JSON using sampling. Designed for automated data collection workflows, market research, and applications requiring reliable access to web data at scale.