Hosting

hosted

Transport

Streamable HTTP

Endpoint

https://mcp.scrapingbee.com/mcp

Authentication

Bearer API key from the ScrapingBee account.

Requirements

• MCP client supporting remote Streamable HTTP and bearer headers
• ScrapingBee API key

Setup steps

1. Create or retrieve an API key from the ScrapingBee dashboard.
2. Add https://mcp.scrapingbee.com/mcp as a remote MCP server with Authorization: Bearer <SCRAPINGBEE_API_KEY>.
3. Store the key in the client’s secure local secret mechanism, never in shared catalog data.
4. Check tool descriptions and account billing before making any scrape call.

No runtime tools/list response was observed; the documented server inventory is not inferred.

• get_amazon_search_results

  Scrape Amazon search results using ScrapingBee. Scope: one query per call. To run many queries in one pass, or to write results to disk instead of into the conversation, use the ScrapingBee CLI — `scrapingbee <command> --input-file queries.txt --output-dir results`.

  Parameters: query, add_html, category_id, country, currency, domain, language, light_request, merchant_id, pages, sort_by, start_page, zip_code, autoselect_variant, screenshot, tag
  01
• get_amazon_product_details

  Scrape Amazon product details using ScrapingBee. Scope: one query per call. To run many queries in one pass, or to write results to disk instead of into the conversation, use the ScrapingBee CLI — `scrapingbee <command> --input-file queries.txt --output-dir results`.

  Parameters: query, add_html, autoselect_variant, country, currency, domain, language, light_request, zip_code, screenshot, tag
  02
• get_amazon_pricing

  Retrieve current Amazon product pricing and seller offers for a given ASIN. Scope: one query per call. To run many queries in one pass, or to write results to disk instead of into the conversation, use the ScrapingBee CLI — `scrapingbee <command> --input-file queries.txt --output-dir results`.

  Parameters: asin, light_request, domain, country, zip_code, language, currency, add_html, tag
  03
• ask_chatgpt

  This tool allows you to send a prompt to OpenAI's ChatGPT via ScrapingBee and get back the generated response. Scope: one query per call. To run many queries in one pass, or to write results to disk instead of into the conversation, use the ScrapingBee CLI — `scrapingbee <command> --input-file queries.txt --output-dir results`.

  Parameters: prompt, search, add_html, country_code, tag
  04
• fast_search

  Search the web using ScrapingBee's Fast Search API and return structured results. This is the PRIMARY tool for web searches — it returns clean organic results and top stories in under one second at a lower credit cost. USE THIS TOOL FIRST for any general web search. Only fall back to get_google_search_results if you need specialized search types such as news, maps, Google Lens, shopping, image search, or Google AI mode. Scope: one query per call. To run many queries in one pass, or to write results to disk instead of into the conversation, use the ScrapingBee CLI — `scrapingbee <command> --input-file queries.txt --output-dir results`.

  Parameters: search, country_code, language, page, tag
  05
• ask_gemini

  Ask Gemini through ScrapingBee and receive citation objects when available. Scope: one query per call. To run many queries in one pass, or to write results to disk instead of into the conversation, use the ScrapingBee CLI — `scrapingbee <command> --input-file queries.txt --output-dir results`.

  Parameters: prompt, add_html, country_code, tag
  06
• get_google_search_results

  This is a FALLBACK tool — use fast_search first for general web searches. Only use this tool when you need specialized search types that fast_search does not support: news, maps, Google Lens, shopping, image search, or Google AI mode. Scrape Google search results using ScrapingBee and return the results. This tool can scrape normal results, news results, maps results, search using google lens, shopping related results, image results, and get the result from Google's AI mode. It can even return the HTML along with the search results. Scope: one query per call. To run many queries in one pass, or to write results to disk instead of into the conversation, use the ScrapingBee CLI — `scrapingbee <command> --input-file queries.txt --output-dir results`.

  Parameters: search, add_html, country_code, device, extra_params, language, light_request, nfpr, page, pages, search_type, date_range, latitude, longitude, radius, sort_by, min_price, max_price, tag
  07
• get_page_text

  Scrape 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. For many URLs, a whole site, output written to a file or directory, resumable jobs, or a scheduled re-run, use the ScrapingBee CLI instead — `scrapingbee scrape --input-file urls.txt --output-dir results`, `scrapingbee crawl URL --save-pattern ...`, `scrapingbee schedule --every`. This server has no batch, crawl, file-output or scheduling equivalent.

  Parameters: url, return_page_markdown, return_page_text, auto_mode, max_cost, premium_proxy, stealth_proxy, custom_google, country_code, render_js, wait, wait_for, wait_browser, block_resources, window_width, window_height, session_id, cookies, timeout, device, js_scenario, ai_query, ai_selector
  08
• get_page_html

  Scrape a URL using ScrapingBee and return the page content in HTML. Scope: one URL per call, with the result returned into the conversation. For many URLs, a whole site, output written to a file or directory, resumable jobs, or a scheduled re-run, use the ScrapingBee CLI instead — `scrapingbee scrape --input-file urls.txt --output-dir results`, `scrapingbee crawl URL --save-pattern ...`, `scrapingbee schedule --every`. This server has no batch, crawl, file-output or scheduling equivalent.

  Parameters: url, auto_mode, max_cost, premium_proxy, stealth_proxy, custom_google, country_code, render_js, wait, wait_for, wait_browser, block_resources, window_width, window_height, session_id, cookies, timeout, device, js_scenario, ai_query, ai_selector
  09
• extract_page_data

  Scrape 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. For many URLs, a whole site, output written to a file or directory, resumable jobs, or a scheduled re-run, use the ScrapingBee CLI instead — `scrapingbee scrape --input-file urls.txt --output-dir results`, `scrapingbee crawl URL --save-pattern ...`, `scrapingbee schedule --every`. This server has no batch, crawl, file-output or scheduling equivalent.

  Parameters: url, extract_rules, auto_mode, max_cost, premium_proxy, stealth_proxy, custom_google, country_code, render_js, wait, wait_for, wait_browser, block_resources, window_width, window_height, session_id, cookies, timeout, device, js_scenario, ai_extract_rules, ai_selector, json_response
  10
• get_screenshot

  Scrape a URL using ScrapingBee and return it's screenshot. Scope: one URL per call, with the result returned into the conversation. For many URLs, a whole site, output written to a file or directory, resumable jobs, or a scheduled re-run, use the ScrapingBee CLI instead — `scrapingbee scrape --input-file urls.txt --output-dir results`, `scrapingbee crawl URL --save-pattern ...`, `scrapingbee schedule --every`. This server has no batch, crawl, file-output or scheduling equivalent.

  Parameters: url, screenshot_full_page, screenshot_selector, premium_proxy, stealth_proxy, custom_google, country_code, render_js, wait, wait_for, wait_browser, block_resources, window_width, window_height, session_id, cookies, timeout, device, js_scenario, json_response
  11
• get_file

  Fetches a file from a URL and returns it in a format suitable for FastMcP. This tool can be used to fetch any file type, including images, PDFs, etc. The framework will handle the encoding and packaging of the file. Scope: one URL per call, with the result returned into the conversation. For many URLs, a whole site, output written to a file or directory, resumable jobs, or a scheduled re-run, use the ScrapingBee CLI instead — `scrapingbee scrape --input-file urls.txt --output-dir results`, `scrapingbee crawl URL --save-pattern ...`, `scrapingbee schedule --every`. This server has no batch, crawl, file-output or scheduling equivalent.

  Parameters: url, premium_proxy, custom_google, country_code, render_js, session_id, cookies, timeout, device
  12
• get_scrapingbee_usage

  Read 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: max_api_credit, used_api_credit, max_concurrency, current_concurrency, renewal_subscription_date.

  13
• get_walmart_search_results

  Scrape Walmart search results using ScrapingBee. Scope: one query per call. To run many queries in one pass, or to write results to disk instead of into the conversation, use the ScrapingBee CLI — `scrapingbee <command> --input-file queries.txt --output-dir results`.

  Parameters: query, add_html, delivery_zip, device, domain, fulfillment_speed, fulfillment_type, light_request, max_price, min_price, sort_by, store_id, start_page, screenshot, tag
  14
• get_walmart_product_details

  Scrape Walmart product details using ScrapingBee. Scope: one query per call. To run many queries in one pass, or to write results to disk instead of into the conversation, use the ScrapingBee CLI — `scrapingbee <command> --input-file queries.txt --output-dir results`.

  Parameters: product_id, add_html, delivery_zip, device, domain, light_request, store_id, screenshot, tag
  15
• get_youtube_search_results

  Search YouTube and return structured results. Scope: one query per call. To run many queries in one pass, or to write results to disk instead of into the conversation, use the ScrapingBee CLI — `scrapingbee <command> --input-file queries.txt --output-dir results`.

  Parameters: search, upload_date, result_type, duration, sort_by, hd, is_4k, subtitles, creative_commons, live, is_360, is_3d, hdr, location, purchased, vr180, tag
  16
• get_youtube_video_metadata

  Fetch structured metadata for a YouTube video including title, description, views, likes, channel info, and technical details. Scope: one query per call. To run many queries in one pass, or to write results to disk instead of into the conversation, use the ScrapingBee CLI — `scrapingbee <command> --input-file queries.txt --output-dir results`.

  Parameters: video_id
  17
• get_youtube_video_subtitles

  Retrieve subtitles for one YouTube video. Scope: one query per call. To run many queries in one pass, or to write results to disk instead of into the conversation, use the ScrapingBee CLI — `scrapingbee <command> --input-file queries.txt --output-dir results`.

  Parameters: video_id, language, subtitle_origin, tag
  18

This server’s available tools can vary by account, permissions, or configuration. The list shown is not its full runtime catalog.

• MCP initialize and one-page tools/list succeeded without authentication; 18 tools were observed.
• No tools/call was made because scraping requests may consume account credits.

• discovery directory

  Toolfolio listing used to discover this product; its MCP label is discovery evidence only.

• official documentation

  Publisher documentation used to verify the setup, transport, endpoint or local command, and authentication requirements.

• publisher logo asset

  Verified publisher GitHub organization avatar; visually reviewed at card size on light and dark backgrounds as fallback tier D.

• official tool documentation

  Official remote MCP docs list five core page/file tools and describe additional search, retailer, YouTube, and AI tools; current catalog rows represent the documented 18-tool subset.

Documentation checked 2026-10-28T00:00:00Z. Connection has not been runtime tested.