Smithery's MCP Proxy and managed identity shut down on October 31. See what's changing

SmitherySign up for Arcade

Bright Data

Arcade toolkit · docs.arcade.dev

Bright Data is a web data platform; this toolkit enables Arcade tools to scrape, search, and extract structured data from any public website at scale without getting blocked.

Capabilities

  • Web scraping: Fetch any webpage and return its content as clean Markdown, suitable for LLM consumption or downstream processing.
  • Multi-engine search: Run queries against Google, Bing, or Yandex with control over result count, search type (web/images), and country targeting.
  • Structured data extraction: Pull typed, schema-aligned records from major platforms — Amazon products and reviews, LinkedIn person and company profiles, Instagram profiles/posts/reels/comments, Facebook posts/marketplace/reviews, X posts, Zillow listings, Booking.com hotels, YouTube videos, and ZoomInfo company profiles.

Secrets

This toolkit requires no OAuth flow; all authentication is handled via secrets injected at runtime.

  • BRIGHTDATA_API_KEY — Your Bright Data account API key. Obtain it from the Bright Data control panel under Account Settings → API Tokens. A paid or trial Bright Data account is required; the key authenticates all API requests.

  • BRIGHTDATA_ZONE — The name of the Bright Data proxy/scraping zone to use for requests. Zones are created and managed in the Bright Data control panel under Proxies & Scraping Infrastructure. Each zone corresponds to a specific product (e.g., Web Unlocker, Scraping Browser, Residential Proxies); select or create the zone appropriate for your use case and copy its exact zone name.

For instructions on storing secrets in Arcade, see the Arcade secrets guide. You can also manage secrets directly at https://api.arcade.dev/dashboard/auth/secrets.

Tools3

  • Brightdata_ScrapeAsMarkdown

    Scrape a webpage and return content in Markdown format using Bright Data. Examples: scrape_as_markdown("https://example.com") - " Example Page Content..." scrape_as_markdown("https://news.ycombinator.com") - " Hacker News ..."

  • Brightdata_SearchEngine

    Search using Google, Bing, or Yandex with advanced parameters using Bright Data. Examples: search_engine("climate change") - " Search Results Climate Change - Wikipedia ..." search_engine("Python tutorials", engine="bing", num_results=5) - " Bing Results ..." search_engine("cats", search_type="images", country_code="us") - " Image Results ..."

  • Brightdata_WebDataFeed

    Extract structured data from various websites like LinkedIn, Amazon, Instagram, etc. NEVER MAKE UP LINKS. IF LINKS ARE NEEDED, FIND THEM WITH A WEB SEARCH FIRST. Supported source types: - amazon_product, amazon_product_reviews - linkedin_person_profile, linkedin_company_profile - zoominfo_company_profile - instagram_profiles, instagram_posts, instagram_reels, instagram_comments - facebook_posts, facebook_marketplace_listings, facebook_company_reviews - x_posts - zillow_properties_listing - booking_hotel_listings - youtube_videos Examples: web_data_feed("amazon_product", "https://amazon.com/dp/B08N5WRWNW") - "{"title": "Product Name", ...}" web_data_feed("linkedin_person_profile", "https://linkedin.com/in/johndoe") - "{"name": "John Doe", ...}" web_data_feed( "facebook_company_reviews", "https://facebook.com/company", num_of_reviews=50 ) - "[{"review": "...", ...}]"