# ScrapingBee (remote · mcp.scrapingbee.com) Scrape any web page, search Google/Amazon/Walmart/YouTube and extract data via the ScrapingBee API. - Trust score: 66/100 (medium) - Change this week: +4 - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-10-18 ## Components - remote · `mcp.scrapingbee.com`: 66/100 (this document), [markdown](https://verifymcp.io/servers/com-scrapingbee-mcp/mcp.md), [page](https://verifymcp.io/servers/com-scrapingbee-mcp/mcp) ## Channel facts - Endpoint: `https://mcp.scrapingbee.com/mcp` - Transports: `streamable-http` - Auth: `none` - Version: `2.2.1` ## Trust breakdown How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-10-18. - **Endpoint Security**: 57/100 - The endpoint's TLS certificate is valid, in date, and uses a strong key. - Authorisation not fully verified: no authorisation is required to call this server, and 18 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. - HTTPS is enforced; there's no plaintext access path. - HSTS check failed: the Strict-Transport-Security header is absent. - DNSSEC check failed: this domain isn't protected by DNSSEC. - **Transport & Reachability**: 100/100 - Verified streamable-http transport via a live MCP handshake. - **Schema Quality & AI Usability**: 59/100 - AI-judged instruction clarity (excellent). - Context-footprint check failed: tool/resource definitions use about 6923 tokens (~384/item across 18 items; 18 tools + 0 resources), over budget; trim descriptions and params. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 30/100 - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses. - **Tool Coverage**: 100/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 100% of tool parameters carry a description. - Structured output schemas are declared (89% of tools); any adoption earns full credit. - **Tool Safety**: 100/100 - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured. - We read all 18 captured tool definition(s), and no name or description among them implies an irreversible operation. - An AI judge read all 18 captured unit(s) of tool text and found none that tries to manipulate the model reading it. - **Capabilities**: 100/100 - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28. ## Install ### How do I install the ScrapingBee MCP server? ScrapingBee is a hosted endpoint at https://mcp.scrapingbee.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation. ### Claude ```bash claude mcp add --transport http com-scrapingbee-mcp 'https://mcp.scrapingbee.com/mcp' ``` ### Cursor ```json { "mcpServers": { "com-scrapingbee-mcp": { "url": "https://mcp.scrapingbee.com/mcp" } } } ``` ### VS Code ```json { "servers": { "com-scrapingbee-mcp": { "type": "http", "url": "https://mcp.scrapingbee.com/mcp" } } } ``` ### Codex ```toml [mcp_servers.com-scrapingbee-mcp] url = "https://mcp.scrapingbee.com/mcp" ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "com-scrapingbee-mcp": { "type": "remote", "url": "https://mcp.scrapingbee.com/mcp", "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add com-scrapingbee-mcp --url 'https://mcp.scrapingbee.com/mcp' --transport streamable-http ``` ### Hermes ```yaml mcp_servers: com-scrapingbee-mcp: url: "https://mcp.scrapingbee.com/mcp" ``` ### Netclaw ```json { "McpServers": { "com-scrapingbee-mcp": { "Transport": "http", "Url": "https://mcp.scrapingbee.com/mcp" } } } ``` ### Vellum ```bash assistant mcp add com-scrapingbee-mcp -t streamable-http -u 'https://mcp.scrapingbee.com/mcp' ``` ### Other ```json { "mcpServers": { "com-scrapingbee-mcp": { "type": "http", "url": "https://mcp.scrapingbee.com/mcp" } } } ``` The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs. ## Changelog Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims. ### 2026-10-18 (score 66, +1) No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-10-16 (score 65, +1) No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-10-14 (score 64, +1) No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-10-13 (score 63, 0) - [functional] Server version: 2.2.0 → 2.2.1 ### 2026-10-12 (score 63, +1) No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-10-10 (score 62) First indexed and scored. ## MCP tools (18) ### `get_amazon_search_results` (~395 tokens) 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 --input-file queries.txt --output-dir results`. Input parameters: - `add_html` (boolean): Whether to return the HTML along with the search results. - `autoselect_variant` (boolean): Automatically select the default/most-popular variant. - `category_id` (string): The category ID to use for the search. - `country` (string): The country code for localization (e.g., us, uk, de). Do not combine with a matching domain (e.g., country=fr&domain=fr). - `currency` (string): The currency code (ISO 4217) to display results (e.g., USD, GBP, EUR). - `domain` (string): The Amazon domain to use for the search (e.g., com, co.uk, de). - `language` (string): The language code to display results (e.g., en, fr, de). - `light_request` (boolean): Whether to use a light request or not. - `merchant_id` (string): The merchant ID to use for the search. - `pages` (integer): The number of pages to scrape. - `query` (string, required): The search query to perform. - `screenshot` (boolean): Force a browser screenshot (returns base64 image). - `sort_by` (string): The sort order to use for the search (most_recent, price_low_to_high, price_high_to_low, featured, average_review, bestsellers). - `start_page` (integer): The page number to start scraping from. - `tag` (string): Response-header label only. - `zip_code` (string): The ZIP code to use for delivery localization. ### `get_amazon_product_details` (~305 tokens) 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 --input-file queries.txt --output-dir results`. Input parameters: - `add_html` (boolean): Whether to return the HTML along with the product details. - `autoselect_variant` (boolean): Whether to automatically select product variant if applicable. - `country` (string): The country code for localization (e.g., us, uk, de). Do not combine with a matching domain (e.g., country=fr&domain=fr). - `currency` (string): The currency code (ISO 4217) to display results (e.g., USD, GBP, EUR). - `domain` (string): The Amazon domain to use for the search (e.g., com, co.uk, de). - `language` (string): The language code to display results (e.g., en, fr, de). - `light_request` (boolean): Whether to use a light request or not. - `query` (string, required): Search term (must be a valid 10-character ASIN code) - `screenshot` (boolean): Force a browser screenshot (returns base64 image). - `tag` (string): Response-header label only. - `zip_code` (string): The zip code to use for delivery localization. ### `get_amazon_pricing` (~221 tokens) 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 --input-file queries.txt --output-dir results`. Input parameters: - `add_html` (boolean): Include page HTML in the response. - `asin` (string, required): Required 10-character ASIN from an Amazon product URL. - `country` (string): ISO country code for localization. Do not combine with a matching domain (e.g., country=fr&domain=fr). - `currency` (string): ISO 4217 display currency. - `domain` (string): Amazon domain (default com). - `language` (string): ISO language code. - `light_request` (boolean): Use a light request (default True) or browser-rendered (False). - `tag` (string): Response-header label only. - `zip_code` (string): ZIP code for delivery localization. ### `ask_chatgpt` (~175 tokens) 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 --input-file queries.txt --output-dir results`. Input parameters: - `add_html` (boolean): Whether to include the full HTML of the page in the results. - `country_code` (string): ISO country code the request should originate from (affects web results when search is enabled). - `prompt` (string, required): The prompt to send to ChatGPT. - `search` (boolean): Whether to enable web search capability for the prompt. - `tag` (string): Response-header label only. ### `fast_search` (~278 tokens) 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 --input-file queries.txt --output-dir results`. Input parameters: - `country_code` (string): ISO 3166-1 alpha-2 country code to localize results (Example: us, fr, de, in, gb, br, etc.). - `language` (string): Language of the search results (Example: en, fr, de, etc.). - `page` (integer): The page number to return. Default is 1, use page=2 for the second page, etc. - `search` (string, required): The search query to use. Make sure to URL-encode special characters such as :, & or +. - `tag` (string): Response-header label only. ### `ask_gemini` (~132 tokens) 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 --input-file queries.txt --output-dir results`. Input parameters: - `add_html` (boolean): Whether to return the full HTML of searched pages. - `country_code` (string): ISO country code to set request geolocation. - `prompt` (string, required): The prompt to send to Gemini. - `tag` (string): Response-header label only. ### `get_google_search_results` (~571 tokens) 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 --input-file queries.txt --output-dir results`. Input parameters: - `add_html` (boolean): Whether to return the HTML along with the search results. - `country_code` (string): The country code to use for the search (Example: us, fr, de, etc.). - `date_range` (string): Filter by date range: past_hour, past_day, past_week, past_month, past_year. Only for classic, news, and images. - `device` (string): The device to use for the search (desktop, mobile). - `extra_params` (string): Extra parameters to pass to the search (Example: tbs=qdr:d&udm=7). - `language` (string): The language to use for the search (Example: en, fr, de, etc.). - `latitude`: Latitude in decimal degrees for geographic searches. - `light_request` (boolean): Whether to use a light request or not. - `longitude`: Longitude in decimal degrees for geographic searches. - `max_price`: Shopping maximum price filter. - `min_price`: Shopping minimum price filter. - `nfpr` (boolean): Whether to disable Google's autocorrection feature or not. - `page` (integer): The page number to return. - `pages` (integer): Number of pages to aggregate (max 10, default 1). - `radius`: Radius in meters (requires latitude and longitude). - `search` (string, required): The search query to use. - `search_type` (string): The search type to use (classic: normal results, news: news results [not available if device is mobile], maps: maps results, lens: search using google lens [requires image url as search parameter], s… - `sort_by` (string): Shopping sort order: relevance, reviews, price_asc, price_desc. - `tag` (string): Response-header label only. ### `get_page_text` (~776 tokens) 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. Input parameters: - `ai_query` (string): Natural-language question for AI extraction. - `ai_selector` (string): CSS selector to focus AI extraction on part of the page. - `auto_mode` (boolean): On by default — ScrapingBee automatically picks the cheapest configuration that successfully fetches the page, escalating proxy strength only as needed (you are charged only for the winning config).… - `block_resources` (boolean): Block images/CSS to speed up rendering. - `cookies` (string): Semicolon-separated cookies to send to the target. - `country_code` (string): ISO 3166-1 alpha-2 country code (e.g. "fr", "us") to route the request through an IP in that country. Only takes effect when premium_proxy or stealth_proxy is True. - `custom_google` (boolean): Set to True if the url is a google domain in the following format: .google. (Example: translate.google.com, mail.google.com, www.google.co.in etc) - `device` (string): desktop (default) or mobile. - `js_scenario` (string): Stringified JSON object of browser interaction instructions. - `max_cost` (integer): Optional credit ceiling for auto_mode (integer >= 1). The request will not escalate to a configuration costing more than this many credits. 0 means no ceiling. Ignored unless auto_mode is True. - `premium_proxy` (boolean): Manual option: use a premium proxy (middle tier of classic/premium/stealth). Setting this disables auto_mode. - `render_js`: Whether to use headless-browser rendering. Omit to use the API default (true). Setting this explicitly switches the request to manual configuration (disables auto_mode). - `return_page_markdown` (boolean): Whether to return the page content in Markdown format. - `return_page_text` (boolean): Whether to return the page content in Text format. - `session_id`: Integer 0–10000000 to reuse an IP for up to 5 minutes. - `stealth_proxy` (boolean): Manual option: use a stealth proxy (strongest tier of classic/premium/stealth). Setting this disables auto_mode. - `timeout` (integer): Request timeout in milliseconds (1000–140000, default 140000). - `url` (string, required): The URL of the page to scrape. - `wait` (integer): Milliseconds to wait after page load (0–35000). - `wait_browser` (string): domcontentloaded (default), load, networkidle0, networkidle2. - `wait_for` (string): CSS or XPath selector to wait for before returning. - `window_height` (integer): Viewport height (default 1080). - `window_width` (integer): Viewport width (default 1920). Output parameters: - `result` ### `get_page_html` (~735 tokens) 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. Input parameters: - `ai_query` (string): Natural-language question for AI extraction. - `ai_selector` (string): CSS selector to focus AI extraction on part of the page. - `auto_mode` (boolean): On by default — ScrapingBee automatically picks the cheapest configuration that successfully fetches the page, escalating proxy strength only as needed (you are charged only for the winning config).… - `block_resources` (boolean): Block images/CSS to speed up rendering. - `cookies` (string): Semicolon-separated cookies to send to the target. - `country_code` (string): ISO 3166-1 alpha-2 country code (e.g. "fr", "us") to route the request through an IP in that country. Only takes effect when premium_proxy or stealth_proxy is True. - `custom_google` (boolean): Set to True if the url is a google domain in the following format: .google. (Example: translate.google.com, mail.google.com, www.google.co.in etc) - `device` (string): desktop (default) or mobile. - `js_scenario` (string): Stringified JSON object of browser interaction instructions. - `max_cost` (integer): Optional credit ceiling for auto_mode (integer >= 1). The request will not escalate to a configuration costing more than this many credits. 0 means no ceiling. Ignored unless auto_mode is True. - `premium_proxy` (boolean): Manual option: use a premium proxy (middle tier of classic/premium/stealth). Setting this disables auto_mode. - `render_js`: Whether to use headless-browser rendering. Omit to use the API default (true). Setting this explicitly switches the request to manual configuration (disables auto_mode). - `session_id`: Integer 0–10000000 to reuse an IP for up to 5 minutes. - `stealth_proxy` (boolean): Manual option: use a stealth proxy (strongest tier of classic/premium/stealth). Setting this disables auto_mode. - `timeout` (integer): Request timeout in milliseconds (1000–140000, default 140000). - `url` (string, required): The URL of the page to scrape. - `wait` (integer): Milliseconds to wait after page load (0–35000). - `wait_browser` (string): domcontentloaded (default), load, networkidle0, networkidle2. - `wait_for` (string): CSS or XPath selector to wait for before returning. - `window_height` (integer): Viewport height (default 1080). - `window_width` (integer): Viewport width (default 1920). Output parameters: - `result` ### `extract_page_data` (~1071 tokens) 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. Input parameters: - `ai_extract_rules` (string): JSON string of AI extraction rules. - `ai_selector` (string): CSS selector to focus AI extraction on part of the page. - `auto_mode` (boolean): On by default — ScrapingBee automatically picks the cheapest configuration that successfully fetches the page, escalating proxy strength only as needed (you are charged only for the winning config).… - `block_resources` (boolean): Block images/CSS to speed up rendering. - `cookies` (string): Semicolon-separated cookies to send to the target. - `country_code` (string): ISO 3166-1 alpha-2 country code (e.g. "fr", "us") to route the request through an IP in that country. Only takes effect when premium_proxy or stealth_proxy is True. - `custom_google` (boolean): Set to True if the url is a google domain in the following format: .google. (Example: translate.google.com, mail.google.com, www.google.co.in etc) - `device` (string): desktop (default) or mobile. - `extract_rules` (string, required): A JSON string defining extraction rules. SIMPLE SYNTAX: Use {"key_name": "css_or_xpath_selector"} format. - CSS selector example: {"title": "h1", "price": "span.price"}… - `js_scenario` (string): Stringified JSON object of browser interaction instructions. - `json_response` (boolean): Return the full JSON envelope instead of the raw body. - `max_cost` (integer): Optional credit ceiling for auto_mode (integer >= 1). The request will not escalate to a configuration costing more than this many credits. 0 means no ceiling. Ignored unless auto_mode is True. - `premium_proxy` (boolean): Manual option: use a premium proxy (middle tier of classic/premium/stealth). Setting this disables auto_mode. - `render_js`: Whether to use headless-browser rendering. Setting this explicitly switches the request to manual configuration (disables auto_mode). - `session_id`: Integer 0–10000000 to reuse an IP for up to 5 minutes. - `stealth_proxy` (boolean): Manual option: use a stealth proxy (strongest tier of classic/premium/stealth). Setting this disables auto_mode. - `timeout` (integer): Request timeout in milliseconds (1000–140000, default 140000). - `url` (string, required): The URL of the page to scrape. - `wait` (integer): Milliseconds to wait after page load (0–35000). - `wait_browser` (string): domcontentloaded (default), load, networkidle0, networkidle2. - `wait_for` (string): CSS or XPath selector to wait for before returning. - `window_height` (integer): Viewport height (default 1080). - `window_width` (integer): Viewport width (default 1920). ### `get_screenshot` (~619 tokens) 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. Input parameters: - `block_resources` (boolean): Block images/CSS to speed up rendering. - `cookies` (string): Semicolon-separated cookies to send to the target. - `country_code` (string): ISO 3166-1 alpha-2 country code (e.g. "fr", "us") to route the request through an IP in that country. Only takes effect when premium_proxy or stealth_proxy is True. - `custom_google` (boolean): Set to True if the url is a google domain in the following format: .google. (Example: translate.google.com, mail.google.com, www.google.co.in etc) - `device` (string): desktop (default) or mobile. - `js_scenario` (string): Stringified JSON object of browser interaction instructions. - `json_response` (boolean): Deprecated, removed in Version 3. Return the full JSON envelope (page content plus the base64 image under its "screenshot" key) instead of the raw image. - `premium_proxy` (boolean): Whether to use a premium proxy for the request. Use it only if you are getting blocked by the website, that is when you get a 500 status code. - `render_js`: Whether to use headless-browser rendering. - `screenshot_full_page` (boolean): Whether to take a screenshot of the full page or just the viewport. - `screenshot_selector` (string): A CSS selector to take a screenshot of a specific element. - `session_id`: Integer 0–10000000 to reuse an IP for up to 5 minutes. - `stealth_proxy` (boolean): Whether to use a stealth proxy for the request. Use it only if you are getting blocked by the website while using premium_proxy, that is when you get a 500 status code. - `timeout` (integer): Request timeout in milliseconds (1000–140000, default 140000). - `url` (string, required): The URL of the page to scrape. - `wait` (integer): Milliseconds to wait after page load (0–35000). - `wait_browser` (string): domcontentloaded (default), load, networkidle0, networkidle2. - `wait_for` (string): CSS or XPath selector to wait for before returning. - `window_height` (integer): Viewport height (default 1080). - `window_width` (integer): Viewport width (default 1920). ### `get_file` (~390 tokens) 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. Input parameters: - `cookies` (string): Semicolon-separated cookies to send to the target. - `country_code` (string): ISO 3166-1 alpha-2 country code (e.g. "fr", "us") to route the request through an IP in that country. Only takes effect when premium_proxy is True. - `custom_google` (boolean): Set to True if the url is a google domain in the following format: .google. (Example: translate.google.com, mail.google.com, www.google.co.in etc) - `device` (string): desktop (default) or mobile. - `premium_proxy` (boolean): Whether to use a premium proxy for the request. Use it only if you are getting blocked by the website. - `render_js` (boolean): Whether to use headless-browser rendering (default False). - `session_id`: Integer 0–10000000 to reuse an IP for up to 5 minutes. - `timeout` (integer): Request timeout in milliseconds (1000–140000, default 140000). - `url` (string, required): The URL of the file to fetch. ### `get_scrapingbee_usage` (~77 tokens) 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. ### `get_walmart_search_results` (~344 tokens) 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 --input-file queries.txt --output-dir results`. Input parameters: - `add_html` (boolean): Whether to return the HTML along with the search results. - `delivery_zip` (string): The zip code to use for delivery localization. - `device` (string): The device to use for the search (desktop, mobile, tablet). - `domain` (string): The domain to use for the search (Example: com, ca, com.mx, etc.) for localization. - `fulfillment_speed` (string): The fulfillment speed to use for the search (today, tomorrow, 2_days, anytime). - `fulfillment_type` (string): The fulfillment type to use for the search (in_store). - `light_request` (boolean): Whether to use a light request or not. - `max_price`: The maximum price to use for the search. - `min_price`: The minimum price to use for the search. - `query` (string, required): The search query to perform. - `screenshot` (boolean): Force a browser screenshot (returns base64 image). - `sort_by` (string): The sort order to use for the search (best_match, price_low, price_high, best_seller). - `start_page` (integer): The page number to return (default 1). - `store_id` (string): Specific Walmart store ID for localization. - `tag` (string): Response-header label only. ### `get_walmart_product_details` (~228 tokens) 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 --input-file queries.txt --output-dir results`. Input parameters: - `add_html` (boolean): Whether to return the HTML along with the product details. - `delivery_zip` (string): The zip code to use for delivery localization. - `device` (string): The device to use for the request (desktop, mobile, tablet). - `domain` (string): The domain to use for the search (Example: com, ca, com.mx, etc.) for localization. - `light_request` (boolean): Whether to use a light request or not. - `product_id` (string, required): The unique identifier for the Walmart product. - `screenshot` (boolean): Force a browser screenshot (returns base64 image). - `store_id` (string): Specific Walmart store ID for localization. - `tag` (string): Response-header label only. ### `get_youtube_search_results` (~350 tokens) 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 --input-file queries.txt --output-dir results`. Input parameters: - `creative_commons` (boolean): Return only videos with Creative Commons license. - `duration` (string): Filter by duration: '<4' (short), '4-20' (medium), '>20' (long). - `hd` (boolean): Return only HD videos. - `hdr` (boolean): Return only HDR videos. - `is_360` (boolean): Return only 360-degree videos. - `is_3d` (boolean): Return only 3D videos. - `is_4k` (boolean): Return only 4K videos. - `live` (boolean): Return only live streams. - `location` (boolean): Return only videos with location metadata. - `purchased` (boolean): Return only purchased movies. - `result_type` (string): Filter by type: 'video', 'channel', 'playlist', 'movie'. - `search` (string, required): The search query. - `sort_by` (string): Sort order: 'relevance' (default), 'rating', 'view_count', 'upload_date'. - `subtitles` (boolean): Return only videos with subtitles/captions. - `tag` (string): Response-header label only. - `upload_date` (string): Filter by date: 'today', 'last_hour', 'this_week', 'this_month', 'this_year'. - `vr180` (boolean): Return only VR180 videos. ### `get_youtube_video_metadata` (~112 tokens) 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 --input-file queries.txt --output-dir results`. Input parameters: - `video_id` (string, required): The unique YouTube video ID (e.g., 'rfscVS0vtbw'). ### `get_youtube_video_subtitles` (~144 tokens) 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 --input-file queries.txt --output-dir results`. Input parameters: - `language` (string): Language code (e.g., 'en', 'es', 'fr'). Default is 'en'. - `subtitle_origin` (string): 'auto_generated' (default) or 'uploader_provided'. - `tag` (string): Response-header label only. - `video_id` (string, required): The unique YouTube video ID. ## Diagnostics Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-scrapingbee-mcp/mcp#diagnostics ## Score history - 2026-10-18: 66 - 2026-10-17: 65 - 2026-10-16: 65 - 2026-10-15: 64 - 2026-10-14: 64 - 2026-10-13: 63 - 2026-10-12: 63 - 2026-10-11: 62 - 2026-10-10: 62 ## Common questions ### What is the ScrapingBee MCP server? ScrapingBee is an MCP server listed in the public MCP registry as com.scrapingbee/mcp. Scrape any web page, search Google/Amazon/Walmart/YouTube and extract data via the ScrapingBee API. This page covers its hosted endpoint (https://mcp.scrapingbee.com/mcp). ### Is the ScrapingBee MCP server safe to use? ScrapingBee scores 66 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm. ### What tools does the ScrapingBee MCP server expose? ScrapingBee exposes 18 tools: get_amazon_search_results, get_amazon_product_details, get_amazon_pricing, ask_chatgpt, fast_search, and 13 more. Their descriptions and schemas cost roughly 6,923 tokens of context every time the server is loaded. ### Does the ScrapingBee MCP server require authentication? No. We connected to ScrapingBee without credentials and it answered, so anything it exposes is reachable by anyone who knows the address. ### Is the ScrapingBee MCP server still maintained? ScrapingBee is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced. ## Links - Remote endpoint: https://mcp.scrapingbee.com/mcp - Authorisation metadata: https://mcp.scrapingbee.com/.well-known/oauth-protected-resource/mcp - Repository: https://github.com/ScrapingBee/mcp-server - Website: https://www.scrapingbee.com/mcp/ - Changelog RSS feed: https://verifymcp.io/servers/com-scrapingbee-mcp/mcp.xml - Changelog JSON feed: https://verifymcp.io/servers/com-scrapingbee-mcp/mcp.json - HTML version of this page: https://verifymcp.io/servers/com-scrapingbee-mcp/mcp