ScrapingBot MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SCRAPING_BOT_API_KEY | Yes | Your ScrapingBot API key from your dashboard | |
| SCRAPING_BOT_API_URL | No | Points the server to another API for local development. Defaults to https://api.scraping-bot.io | |
| SCRAPING_BOT_USERNAME | Yes | Your ScrapingBot username from your dashboard |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| scrape_raw_htmlA | Fetch the HTML source of any public web page through ScrapingBot's proxies. Use useChrome for pages built with JavaScript. Prefer the dedicated tools: scrape_retail for product pages, scrape_real_estate, scrape_booking, scrape_search_engine for Google or Bing, and scrape_social_media for Instagram, TikTok, Facebook, LinkedIn, X/Twitter or Threads (blocked here). Costs 1 credit, 5 with useChrome, 10 with premiumProxy, 25 with both (and for Google pages); failed requests are refunded. Some protected sites always use a premium proxy and cost 10 credits (e.g. amazon.fr, cdiscount.com, fnac.com, leboncoin.fr, seloger.com, rightmove.co.uk, zillow.com). A request blocked by the site is retried once with a premium proxy, billed at the premium price only if it succeeds (the result then says so). |
| scrape_retailA | Extract structured product data (title, price, currency, images, brand, stock, EAN...) from an e-commerce product page such as Amazon, Cdiscount, Fnac or Zalando. Prefer it to scrape_raw_html for any product page. Returns JSON. Costs 1 credit, 5 with useChrome, 10 with premiumProxy, 25 with both (and for Google pages); failed requests are refunded. Some protected sites always use a premium proxy and cost 10 credits (e.g. amazon.fr, cdiscount.com, fnac.com, leboncoin.fr, seloger.com, rightmove.co.uk, zillow.com). A request blocked by the site is retried once with a premium proxy, billed at the premium price only if it succeeds (the result then says so). |
| scrape_real_estateA | Extract a property listing (price or rent, surface, rooms, bedrooms, location, images...) from real estate sites such as SeLoger, Leboncoin, Rightmove or Zillow. Returns JSON. Costs 1 credit, 5 with useChrome, 10 with premiumProxy, 25 with both (and for Google pages); failed requests are refunded. Some protected sites always use a premium proxy and cost 10 credits (e.g. amazon.fr, cdiscount.com, fnac.com, leboncoin.fr, seloger.com, rightmove.co.uk, zillow.com). A request blocked by the site is retried once with a premium proxy, billed at the premium price only if it succeeds (the result then says so). |
| scrape_bookingA | Extract a hotel or rental page (title, price, images, rating, rooms) or a search results page from Booking.com, Airbnb, Expedia, Hotels.com or Abritel. Put the stay dates in the URL. Returns JSON. Costs 1 credit, 5 with useChrome, 10 with premiumProxy, 25 with both (and for Google pages); failed requests are refunded. Some protected sites always use a premium proxy and cost 10 credits (e.g. amazon.fr, cdiscount.com, fnac.com, leboncoin.fr, seloger.com, rightmove.co.uk, zillow.com). A request blocked by the site is retried once with a premium proxy, billed at the premium price only if it succeeds (the result then says so). |
| scrape_groceryA | Extract a grocery product page (title, price, image, brand, nutritional values). Returns JSON. Costs 1 credit, 5 with useChrome, 10 with premiumProxy, 25 with both (and for Google pages); failed requests are refunded. Some protected sites always use a premium proxy and cost 10 credits (e.g. amazon.fr, cdiscount.com, fnac.com, leboncoin.fr, seloger.com, rightmove.co.uk, zillow.com). A request blocked by the site is retried once with a premium proxy, billed at the premium price only if it succeeds (the result then says so). |
| scrape_search_engineA | Get search engine results (organic results, related searches, people also ask...) as JSON. Use it instead of fetching google.com or bing.com pages with scrape_raw_html. Costs 30 credits; failed requests are refunded. |
| scrape_social_mediaA | Scrape a public social media profile, post or search (Instagram, TikTok, Facebook, LinkedIn, X/Twitter, Threads). Always use this tool for these networks, never scrape_raw_html. Choose the scraper and give its inputs: instagramProfile (account (name or profile URL); returns the 12 latest posts), instagramPost (url), tiktokProfile (url), tiktokHashtag (hashtag; max_video_count), facebookProfile (url; load_more_items_count), facebookPost (url), facebookOrganization (url), facebookMarketplaceItem (url; country), facebookMarketplaceSearch (keyword, city, country; items_limit), linkedinProfile (url; language), linkedinCompanyProfile (url; language), linkedinPost (url), linkedinSearchResult (keywords; page, language), twitterProfile (url; number_of_tweets), twitterSearch (search; posts_max_count), threadsProfile (url), threadsPost (url). Waits for the result for about a minute, otherwise returns a responseId for get_social_media_result: use that tool to wait longer, as calling this one again is billed again. Costs 30 credits; failed requests are refunded. |
| get_accountA | Get the ScrapingBot account of the API key: plan, credits used and remaining this period, when they reset, and the upgrade page. Check it before a series of scrapes, and tell the user when few credits are left (under about 10%) or when a scrape fails for lack of credits (HTTP 402): the plans are at https://www.scraping-bot.io/pricing. Costs no credit. |
| get_usage_historyA | Get the usage of the ScrapingBot account over the last days: credits spent per day, requests per API, success rate, and the latest requests (URL, API, success, credits, error). Useful to explain what used the credits or why requests fail. Costs no credit. |
| get_social_media_resultA | Get the result of a scrape_social_media request that was still pending, from its scraper and responseId. Waits about a minute. Costs no credit. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
The split between scrape_raw_html and the domain-specific extractors (retail, real estate, booking, grocery, search engine, social) is explicitly documented, including 'prefer X over raw_html' guidance, which removes most ambiguity. The residual overlap is scrape_retail vs scrape_grocery (both extract product title/price/brand from an e-commerce-like page) and scrape_booking vs scrape_real_estate for rental listings, where an agent could plausibly pick either.
Every tool is snake_case with a clear verb_noun form: scrape_<domain> for extraction and get_<resource> for retrieval (get_account, get_usage_history, get_social_media_result). The grouping is immediately legible and the async continuation tool is named to pair with its producer.
Ten tools is a tight, well-earned surface for a scraping service: one generic fetcher, five domain extractors, one search-engine tool, one social-media tool, and account/usage/async-result support. Nothing looks redundant or padding-like, and the set stays well under typical context-bloat thresholds.
The lifecycle is essentially covered: fetch, specialized extraction, account credit state, usage/error history, and an async result poller for the long-running social path. Minor gaps remain — no batch/bulk scraping, no screenshot or rendered-page artefact, and no way to discover which sites/APIs are supported other than the hardcoded examples in descriptions.