Agents Index

ScrapingBee

OnlineOfficial

Scrape any web page, search Google/Amazon/Walmart/YouTube and extract data via the ScrapingBee API.

Visit publisherConnectJSON

What it can do: 18 tools

  • get_amazon_search_results read-onlyScrape Amazon search results using ScrapingBee. Scope: one query per call, with the result returned into the conversation.
  • get_amazon_product_details read-onlyScrape Amazon product details using ScrapingBee. Scope: one query per call, with the result returned into the conversation.
  • get_amazon_pricing read-onlyRetrieve current Amazon product pricing and seller offers for a given ASIN. Scope: one query per call, with the result returned into the conversation.
  • ask_chatgpt read-onlyThis tool allows you to send a prompt to OpenAI's ChatGPT via ScrapingBee and get back the generated response. Scope: one query per call, with the result returned into the conversation.
  • fast_search read-onlySearch the web using ScrapingBee's Fast Search API and return organic results and top stories as JSON, typically in under one second and at a lower credit cost than get_google_search_results. For news, maps, Google Lens
  • ask_gemini read-onlyAsk Gemini through ScrapingBee and receive citation objects when available. Scope: one query per call, with the result returned into the conversation.
  • get_google_search_results read-onlySupports specialized Google search types that fast_search does not: news, maps, Google Lens, shopping, image search and Google AI mode. For plain organic results, fast_search is faster and uses fewer credits. Scrape Goo
  • get_page_text read-onlyScrape a URL using ScrapingBee and return the page content in Markdown or Text format. Scope: one URL per call, with the result returned into the conversation. This server has no batch, crawl, file-output or scheduling
  • get_page_html read-onlyScrape a URL using ScrapingBee and return the page content in HTML. Scope: one URL per call, with the result returned into the conversation. This server has no batch, crawl, file-output or scheduling mode. Docs: https:
  • extract_page_data read-onlyScrape a URL using ScrapingBee and extract specific data using CSS or XPath selectors. Scope: one URL per call, with the result returned into the conversation. This server has no batch, crawl, file-output or scheduling
  • get_screenshot read-onlyCapture a PNG screenshot of a web page through ScrapingBee: the viewport, the full page, or one element selected with CSS. Scope: one URL per call, with the result returned into the conversation. This server has no batc
  • get_file read-onlyDownload a file (PDF, image, CSV, …) from a URL through ScrapingBee and return it as an embedded resource. Scope: one URL per call, with the result returned into the conversation. This server has no batch, crawl, file-o
  • get_scrapingbee_usage read-onlyRead real-time credit and concurrency usage for the authenticated ScrapingBee account. Note: This endpoint is rate-limited to 6 calls per minute and does not count against the account's concurrency limit. Returns:
  • get_walmart_search_results read-onlyScrape Walmart search results using ScrapingBee. Scope: one query per call, with the result returned into the conversation.
  • get_walmart_product_details read-onlyScrape Walmart product details using ScrapingBee. Scope: one query per call, with the result returned into the conversation.
  • get_youtube_search_results read-onlySearch YouTube and return structured results. Scope: one query per call, with the result returned into the conversation.
  • get_youtube_video_metadata read-onlyFetch structured metadata for a YouTube video including title, description, views, likes, channel info, and technical details. Scope: one query per call, with the result returned into the conversation.
  • get_youtube_video_subtitles read-onlyRetrieve subtitles for one YouTube video. Scope: one query per call, with the result returned into the conversation.

Connect it

Claude Code
claude mcp add --transport http scrapingbee https://mcp.scrapingbee.com/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://mcp.scrapingbee.com/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "scrapingbee": {
      "url": "https://mcp.scrapingbee.com/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "scrapingbee": {
      "type": "http",
      "url": "https://mcp.scrapingbee.com/mcp"
    }
  }
}

Questions

What does ScrapingBee do?

Scrape any web page, search Google/Amazon/Walmart/YouTube and extract data via the ScrapingBee API. It exposes 18 tools to AI assistants.

What tools does ScrapingBee provide?

18 tools, including get_amazon_search_results, get_amazon_product_details, get_amazon_pricing, ask_chatgpt, fast_search, ask_gemini, get_google_search_results, get_page_text, get_page_html, extract_page_data, get_screenshot, get_file….

How do I connect ScrapingBee to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://mcp.scrapingbee.com/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does ScrapingBee require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is ScrapingBee online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes ScrapingBee?

scrapingbee.com. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in Web Search & Scraping