_ registry / mcp http-sse · checked 24h ago

scrapeunblocker

https://scrapeunblocker.com

Registry code: 37ac45981d49bab8

api record
endpoint
https://mcp.scrapeunblocker.com/mcp
protocol
http-sse ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is scrapeunblocker live?
Yes — it answered the hub's last check (checked 24h ago). It answered 100% of checks over the last 30 days.
Is scrapeunblocker free to use?
Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.
What tools does scrapeunblocker have?
25 tools: fetch_html, fetch_parsed, fetch_markdown, search_and_read, list_plugins, amazon_product, walmart_search, ebay_search, ….
Is scrapeunblocker safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
218ms

last good check

priced tools
0

of 25 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 25 tools
25 auth-required 25 of 25 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • fetch_html auth-required never probed

    Fetch the fully rendered HTML of any public web page through the ScrapeUnblocker API (https://docs.scrapeunblocker.com). The page loads in a real browser, so JavaScript-rendered pages come back complete. Use it when you need the page markup, or when a plain HTTP fetch returns 403/429 or an empty page. Returns raw HTML.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "description": "The absolute URL to fetch (http/https)."
        },
        "wait_value": {
          "type": "string",
          "description": "The selector/expression paired with wait_method."
        },
        "wait_method": {
          "enum": [
            "css",
            "js"
          ],
          "type": "string",
          "description": "Optional render-wait: 'css' selector or 'js' expression."
        },
        "proxy_country": {
          "type": "string",
          "maxLength": 2,
          "minLength": 2,
          "description": "Optional ISO country code to route through, e.g. 'US'."
        },
        "sleep_seconds": {
          "type": "number",
          "description": "Extra seconds to wait after load.",
          "exclusiveMinimum": 0
        }
      }
    }
    arguments 37 lines
  • fetch_parsed auth-required never probed

    Fetch a web page through the ScrapeUnblocker API (https://docs.scrapeunblocker.com) and return AI-parsed structured JSON instead of raw HTML (product details, article content, listings). If the page holds no structured data, the result says so and returns the rendered HTML instead (billed like fetch_html).

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "description": "The absolute URL to fetch and parse."
        },
        "proxy_country": {
          "type": "string",
          "maxLength": 2,
          "minLength": 2,
          "description": "Optional ISO country code, e.g. 'US'."
        }
      }
    }
    arguments 20 lines
  • fetch_markdown auth-required never probed

    Fetch a web page in a real browser through the ScrapeUnblocker API (https://docs.scrapeunblocker.com) and return it as clean Markdown: the main content with absolute links, without scripts, styles, navigation or footer. Use it to read, quote or summarise a page; it is usually 2-25% the size of the HTML. Works on JavaScript-rendered pages and on pages that return 403/429 to a plain HTTP fetch. Billed as one request.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "description": "The absolute URL to read (http/https)."
        },
        "wait_value": {
          "type": "string",
          "description": "The selector/expression paired with wait_method."
        },
        "wait_method": {
          "enum": [
            "css",
            "js"
          ],
          "type": "string",
          "description": "Optional render-wait: 'css' selector or 'js' expression."
        },
        "proxy_country": {
          "type": "string",
          "maxLength": 2,
          "minLength": 2,
          "description": "Optional ISO country code to route through, e.g. 'US'."
        },
        "sleep_seconds": {
          "type": "number",
          "description": "Extra seconds to wait after load.",
          "exclusiveMinimum": 0
        },
        "main_content_only": {
          "type": "boolean",
          "description": "Drop navigation, page header, footer and sidebars (default true). False keeps the whole page."
        }
      }
    }
    arguments 41 lines
  • search_and_read auth-required never probed

    Search Google through the ScrapeUnblocker API (https://docs.scrapeunblocker.com) and read the top results in one call: returns Google's AI Overview when there is one, each of the first `results` pages (default 3, max 5) as Markdown, and the other organic results as title, URL and snippet. Use it to answer a question from the live web. Billed as one request for the search plus one per page read.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "keyword"
      ],
      "properties": {
        "keyword": {
          "type": "string",
          "minLength": 1,
          "description": "The search query."
        },
        "results": {
          "type": "integer",
          "maximum": 5,
          "minimum": 1,
          "description": "How many top results to read (default 3, max 5)."
        },
        "proxy_country": {
          "type": "string",
          "maxLength": 2,
          "minLength": 2,
          "description": "Optional ISO country code to search from and read the pages through, e.g. 'US'."
        }
      }
    }
    arguments 26 lines
  • list_plugins auth-required 24h ago

    List ScrapeUnblocker's ready-made site plugins: scrapers for specific sites that return clean structured JSON (Amazon, Walmart, Target, eBay, Zillow, Redfin, Booking.com, Airbnb, Indeed, Glassdoor, Google Trends / Shopping / Maps, YouTube, Spotify, App Store, Google Play, Trustpilot, Yelp, Ahrefs, Semrush and 100+ more). A plugin returns a site's data already parsed. Without arguments it lists every plugin with its parameters (* = required); `category` or `search` narrow the list; `name` returns one plugin's full parameter docs. Free - it calls nothing.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "properties": {
        "name": {
          "type": "string",
          "description": "A plugin name, for its full parameter docs."
        },
        "search": {
          "type": "string",
          "description": "Only plugins whose name or description mentions this, e.g. 'zillow' or 'reviews'."
        },
        "category": {
          "enum": [
            "Travel",
            "Google",
            "AI",
            "Search engines",
            "E-commerce",
            "Classifieds & Resale",
            "Groceries",
            "Real estate",
            "Vehicles",
            "Jobs",
            "Reviews & Companies",
            "Local & Maps",
            "Apps",
            "Video & Music",
            "Sports",
            "SEO & Ads"
          ],
          "type": "string",
          "description": "Only plugins in this category."
        }
      }
    }
    arguments 36 lines
  • amazon_product auth-required 24h ago

    Fetches a single Amazon product and returns it as JSON: `title`, `brand` and `brandStoreUrl`, `parentAsin`, `manufacturer`, `modelNumber`, `partNumber`, `productCodes` (UPC, EAN, GTIN, ISBN), `condition`, the `amazonsChoice`, `bestSellerBadge`, `deal` and `coupon` markers, `price` + `currency`, `listPrice`, `savingsPercent` and `savingsAmount`, `unitPrice`, `subscribeAndSavePrice`, `shippingPrice`, `recentSales`, `availability` (+ a boolean `inStock`), `maxOrderQuantity`, `rating`, `reviewCount`, `ratingDistribution` (percent per star), `reviewSummary`, `seller`, `sellerUrl`, `sellerId`, `shipsFrom`, `fulfilledByAmazon`, `prime`, `delivery`, `returnPolicy`, `offersCount` and `offersFromPrice`, `bestSellersRank`, `features` (bullet points), `categories` (breadcrumb), `description`, `fromTheManufacturer` and `fromTheBrand` (text and images), `importantInformation`, `ingredients`, `whatsInTheBox`, `documents`, `warrantyAndSupport`, `productDetails`, `productOverview`, `dimensions`, `weight`, `dateFirstAvailable`, `variantDimensions` and `variants` (each with its own ASIN and options), `sustainability`, `protectionPlans`, `newerModel`, `sponsoredProducts`, `relatedProducts`, `images` (the whole gallery) and `videos`. A field the page does not show is null or empty. Identify the product with either `asin` (plus `marketplace`) or a full product `url`. Other sellers' full offers are not on the product page: only their count and lowest price are returned here, `/marketplace/amazon-offers` lists them. `prime` and `delivery` are what a visitor who is not signed in sees. Amazon prices each page in the currency of the delivery location it infers from the visitor's IP address, so `proxy_country` defaults to the marketplace's home country (amazon.com -> US) and the call is routed through proxies in that country. The country of the proxy that served the request is reported as `exitCountry`. Returns JSON. Billed like an API request; listing plugins bill one unit per result page they fetch, so keep max_results modest.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "properties": {
        "url": {
          "type": "string",
          "description": "Full Amazon product url, e.g. 'https://www.amazon.de/dp/B0BSHF7WHW'. The ASIN and marketplace are read from it, so `asin`/`marketplace` are not needed when a url is given."
        },
        "asin": {
          "type": "string",
          "description": "Amazon product id (10-char ASIN, e.g. 'B0BSHF7WHW'; books use their ISBN-10). Give either `asin` (with `marketplace`) or a full `url`."
        },
        "marketplace": {
          "type": "string",
          "description": "Regional Amazon site the ASIN belongs to. Prices and currency differ per marketplace. One of: amazon.com, amazon.co.uk, amazon.de, amazon.fr, amazon.it, amazon.es, amazon.nl, amazon.se, amazon.pl, amazon.com.be, amazon.com.tr, amazon.ca, amazon.com.mx, amazon.com.br, amazon.co.jp, amazon.in, amazon.ae, amazon.sa, amazon.sg, amazon.com.au. Default: amazon.com."
        },
        "proxy_country": {
          "type": "string",
          "description": "Proxy country the request is sent from (ISO-2, e.g. 'US', 'DE'). Defaults to the marketplace's home country so the price comes back in the expected currency."
        }
      }
    }
    arguments 22 lines
  • walmart_search auth-required never probed

    Searches Walmart for `query` and returns the products as JSON: `name`, `price` and `wasPrice`, `rating`, `reviewCount`, `brand`, `seller`, `availability`, `image`, a product `url`, `sponsored`, `unitPrice`, `priceRange`, `promotions`, `fulfillment`, `deliveryAvailable` and `variants`. The response also carries the search's `totalResults`, `pages`, `filters` and `sponsoredProducts`. Sort with `sort`, filter with `min_price`/`max_price`, and collect up to `max_results` across pages. Returns JSON. Billed like an API request; listing plugins bill one unit per result page they fetch, so keep max_results modest.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "query"
      ],
      "properties": {
        "page": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "1-based page to start from (~40 per page). Default: 1."
        },
        "sort": {
          "type": "string",
          "description": "Ordering: best_match, price_low, price_high, best_seller, rating_high, new. Default: best_match."
        },
        "query": {
          "type": "string",
          "description": "What to search, e.g. 'laptop' or 'coffee maker'."
        },
        "max_price": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "Highest price to include (USD)."
        },
        "min_price": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "Lowest price to include (USD)."
        },
        "max_results": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "How many products to collect across pages. Default: 40."
        },
        "proxy_country": {
          "type": "string",
          "description": "Proxy country the request is sent from (ISO-2, e.g. 'US', 'DE'). Defaults to US."
        }
      }
    }
    arguments 45 lines
  • ebay_search auth-required never probed

    Searches any regional eBay marketplace for `keyword` and returns the listings as JSON: `title`, `price` + `currency`, `condition` (with a normalised `conditionCode`), `seller` (username, feedback percentage and score), `shippingCost`, `sold`, `watchers`, `bids`, `image` and a clean item `url`. Filter with `condition`, `listing_type`, `min_price`/`max_price`, `free_shipping`, `seller` or `category`, sort with `sort`, and page with `page`/`page_size` (60, 120 or 240 per page). Set `marketplace` to search a specific site - prices, currency and availability differ between ebay.com, ebay.de, ebay.co.uk and the rest. When eBay finds no exact match it still serves a full page of its own loosely-related suggestions. That case is reported honestly: `exactMatches` is `false` and a `notice` explains it, so those listings are never mistaken for real matches. Returns JSON. Billed like an API request; listing plugins bill one unit per result page they fetch, so keep max_results modest.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "keyword"
      ],
      "properties": {
        "page": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "1-based page number. Default: 1."
        },
        "sort": {
          "type": "string",
          "description": "Ordering: best_match, newly_listed, ending_soon, price_asc, price_desc. Default 'best_match'. Default: best_match."
        },
        "seller": {
          "type": "string",
          "description": "Restrict the search to one seller's username."
        },
        "keyword": {
          "type": "string",
          "description": "Search phrase, e.g. 'iphone 13' or a part number like '1K0953519A'."
        },
        "category": {
          "type": "string",
          "description": "eBay category id to search inside, e.g. '131090' for vehicle parts and accessories."
        },
        "condition": {
          "type": "string",
          "description": "Item condition filter: new, open_box, refurbished, used, for_parts. Omit for every condition."
        },
        "max_price": {
          "type": "number",
          "description": "Highest price to include, in the marketplace's currency."
        },
        "min_price": {
          "type": "number",
          "description": "Lowest price to include, in the marketplace's currency."
        },
        "page_size": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "Listings per page - eBay's own page sizes: 60, 120, 240. Default: 60."
        },
        "marketplace": {
          "type": "string",
          "description": "Regional eBay site to search. Prices, currency and availability differ per marketplace. One of: ebay.com, ebay.co.uk, ebay.de, ebay.fr, ebay.it, ebay.es, ebay.nl, ebay.pl, ebay.at, ebay.ch, ebay.be, ebay.ie, ebay.ca, ebay.com.au, ebay.in, ebay.ph, ebay.com.sg, ebay.com.my, ebay.com.hk. Default: ebay.com."
        },
        "listing_type": {
          "type": "string",
          "description": "Listing format: all, buy_it_now, auction. Default 'all'. Default: all."
        },
        "free_shipping": {
          "type": "boolean",
          "description": "Only listings eBay marks as free delivery. Default: false."
        },
        "proxy_country": {
          "type": "string",
          "description": "Proxy country the request is sent from (ISO-2, e.g. 'US', 'DE'). Defaults to a country chosen for the marketplace."
        }
      }
    }
    arguments 65 lines
  • google_shopping auth-required never probed

    Runs the Google Shopping vertical (`udm=28`) for `q` and returns the product cards as JSON: `title`, `price`, `currency`, `currencyCode`, `originalPrice`, `discount`, `merchant`, `delivery`, `rating`, `reviewCount`, `image` and Google's own ids for the product (`productId`, `catalogId`, `offerId` - stable across searches, for tracking one product). Set `proxy_country`/`gl` to target a market (prices/merchants are region-specific) and `min_price`/`max_price` to filter. One render returns the first page of products (v1). Note: Google Shopping exposes no per-product URL, so `url` is omitted. `image` is the product's thumbnail URL. Returns JSON. Billed like an API request; listing plugins bill one unit per result page they fetch, so keep max_results modest.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "q"
      ],
      "properties": {
        "q": {
          "type": "string",
          "description": "Product search term, e.g. 'wireless headphones'."
        },
        "gl": {
          "type": "string",
          "description": "Market of search, ISO-2, e.g. 'us', 'de'. Sets prices/merchants. Default: us."
        },
        "max_price": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "Maximum price filter (whole units, gl currency)."
        },
        "min_price": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "Minimum price filter (whole units, gl currency)."
        },
        "max_results": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "How many products to return (v1: first page). Default: 60."
        },
        "proxy_country": {
          "type": "string",
          "description": "Proxy country the request is sent from (ISO-2, e.g. 'US', 'DE'). Prices/merchants are market-specific."
        }
      }
    }
    arguments 39 lines
  • google_local auth-required never probed

    Runs a Google Local (`tbm=lcl`) search for `keyword` and returns up to ~20 businesses as JSON: `name`, `rating`, `reviews`, `price`, `category`, `address`, `phone`, `website`, `hours`, and a top `review_snippet`. `phone` and `website` are null when Google does not render them for that result - service businesses (plumbers, contractors) almost always carry both. Local results are location-sensitive - set `proxy_country` (and optionally `gl`/`hl`) to target a market. Returns JSON. Billed like an API request; listing plugins bill one unit per result page they fetch, so keep max_results modest.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "keyword"
      ],
      "properties": {
        "gl": {
          "type": "string",
          "description": "Google country of search, ISO-2 lowercase, e.g. 'us', 'de'."
        },
        "hl": {
          "type": "string",
          "description": "Google UI language, e.g. 'en', 'de', 'fr'. Default: en."
        },
        "keyword": {
          "type": "string",
          "description": "Search phrase, e.g. 'coffee shops in chicago' or 'plumbers near SW1A'."
        },
        "proxy_country": {
          "type": "string",
          "description": "Proxy country the request is sent from (ISO-2, e.g. 'US', 'GB'). Local results are location-sensitive, so pick the country you want results for."
        }
      }
    }
    arguments 25 lines
  • maps_place_details auth-required never probed

    Returns the full data for one Google Maps place as JSON: `name`, `address` (+ `addressLines`), `phone`, `website`, `rating`, `categories`, `latitude`/`longitude`, `plusCode`, `hours` + `openNow`, `description`, `photo`, `cid`, `featureId`, `googleMapsUrl` and `relatedPlaces`. Identify the place with `place_id` (ChIJ...), a Maps `url`, or a raw `feature_id` (0xHEX:0xHEX). Location-neutral - the feature id resolves the place directly; `proxy_country` defaults to a US proxy to clear Google's consent wall. Returns JSON. Billed like an API request; listing plugins bill one unit per result page they fetch, so keep max_results modest.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "properties": {
        "gl": {
          "type": "string",
          "description": "Google country, ISO-2 lowercase, e.g. 'us'. Default: us."
        },
        "hl": {
          "type": "string",
          "description": "Google UI language, e.g. 'en', 'de', 'fr'. Default: en."
        },
        "raw": {
          "type": "boolean",
          "description": "Include the decoded place core array under `raw`. Default: false."
        },
        "url": {
          "type": "string",
          "description": "A Google Maps place URL: a /maps/place/... URL, a maps.app.goo.gl share link or a maps?cid= link. The place is read out of it."
        },
        "place_id": {
          "type": "string",
          "description": "A Google place_id, e.g. 'ChIJN1t_tDeuEmsRUsoyG83frY4'."
        },
        "feature_id": {
          "type": "string",
          "description": "A Maps feature id '0xHEX:0xHEX', e.g. '0x47e66e2964e34e2d:0x8ddca9ee380ef7e0'. Fastest - no resolve step."
        },
        "proxy_country": {
          "type": "string",
          "description": "Proxy country the request is sent from (ISO-2, e.g. 'US', 'DE'). Defaults to US - an EU country hits Google's consent wall. Default: us."
        }
      }
    }
    arguments 34 lines
  • indeed_jobs auth-required never probed

    Searches Indeed for `query` in `location` and returns the job listings as JSON: `title`, `company`, `location`, `salary` (with parsed `min`/`max`), `jobTypes`, `companyRating`, a `snippet`, `datePosted` (YYYY-MM-DD), `sponsored` (Indeed's paid placement) and a clean job `url`. Filter with `country`, `job_type`, `days` (posting age), `remote`, sort with `sort` (`date` returns the collected jobs newest first, sponsored ones included), and collect up to `max_results` across pages. Indeed sits behind Cloudflare + PerimeterX - handled for you. Returns JSON. Billed like an API request; listing plugins bill one unit per result page they fetch, so keep max_results modest.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "query"
      ],
      "properties": {
        "days": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "Max posting age in days: 1, 3, 7, 14."
        },
        "sort": {
          "type": "string",
          "description": "Ordering: relevance, date. Default: relevance."
        },
        "query": {
          "type": "string",
          "description": "What to search, e.g. 'software engineer' or 'nurse'."
        },
        "start": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "0-based result offset to start from. Default: 0."
        },
        "radius": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "Search radius in miles/km around the location."
        },
        "remote": {
          "type": "boolean",
          "description": "Only remote jobs. Default: false."
        },
        "country": {
          "type": "string",
          "description": "Indeed country site: us, uk, ca, au, in, ie, de, fr, nl, es, it, at, ch, be, pl, se, sg, za, nz, mx. Default: us."
        },
        "job_type": {
          "type": "string",
          "description": "Job type: fulltime, parttime, contract, internship, temporary."
        },
        "location": {
          "type": "string",
          "description": "Where, e.g. 'Austin, TX' or 'London'."
        },
        "max_results": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "How many jobs to collect across pages. Default: 30."
        },
        "proxy_country": {
          "type": "string",
          "description": "Proxy country the request is sent from (ISO-2, e.g. 'US', 'DE'). Defaults to the country's site."
        }
      }
    }
    arguments 61 lines
  • run_plugin auth-required never probed

    Run one ScrapeUnblocker site plugin and return its JSON - e.g. a Target or Walmart search, a Zillow listing search, Google Trends for some keywords, an app's App Store reviews. `params` uses the plugin's own parameter names (snake_case); a list value is fine where a parameter takes several. Each run is billed like an API request; listing plugins bill one unit per result page they fetch, so max_results sets the cost.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "name"
      ],
      "properties": {
        "name": {
          "enum": [
            "skyscanner_flights",
            "skyscanner_hotels",
            "skyscanner_carhire",
            "booking_hotels",
            "booking_reviews",
            "airbnb_search",
            "airbnb_room",
            "airbnb_reviews",
            "tripadvisor_list",
            "tripadvisor_reviews",
            "google_local",
            "google_images",
            "maps_place_details",
            "maps_reviews",
            "google_trends",
            "google_shopping",
            "google_jobs",
            "google_hotels",
            "google_hotels_property",
            "google_news",
            "google_ads_transparency",
            "google_ads_transparency_advertisers",
            "google_ai_mode",
            "google_lens",
            "gemini",
            "chatgpt",
            "bing_search",
            "bing_images",
            "duckduckgo_search",
            "yahoo_search",
            "yahoo_images",
            "brave_search",
            "brave_images",
            "amazon_product",
            "amazon_search",
            "amazon_bestsellers",
            "amazon_reviews",
            "amazon_offers",
            "amazon_seller",
            "walmart_search",
            "walmart_product",
            "target_search",
            "target_category",
            "target_product",
            "bestbuy_search",
            "bestbuy_product",
            "homedepot_search",
            "costco_search",
            "costco_product",
            "etsy_search",
            "etsy_product",
            "shein_search",
            "zalando_search",
            "aliexpress_search",
            "aliexpress_product",
            "alibaba_search",
            "alibaba_product",
            "alibaba1688_search",
            "alibaba1688_product",
            "tiktok_shop_search",
            "tiktok_shop_product",
            "tiktok_shop_store",
            "oopbuy_search",
            "smyths_inventory",
            "smyths_details",
            "smyths_search",
            "smyths_category",
            "wish_search",
            "wish_product",
            "shopee_search",
            "shopee_product",
            "taobao_search",
            "taobao_product",
            "flipkart_search",
            "flipkart_product",
            "lazada_search",
            "lazada_product",
            "allegro_search",
            "allegro_product",
            "falabella_search",
            "falabella_product",
            "magazineluiza_search",
            "magazineluiza_product",
            "mediamarkt_search",
            "mediamarkt_product",
            "cdiscount_search",
            "cdiscount_product",
            "idealo_search",
            "idealo_offers",
            "rakuten_search",
            "rakuten_product",
            "indiamart_search",
            "indiamart_product",
            "bedbathandbeyond_search",
            "bedbathandbeyond_product",
            "petco_search",
            "petco_product",
            "neobits_product",
            "lowes_search",
            "lowes_product",
            "menards_search",
            "menards_product",
            "grainger_search",
            "grainger_product",
            "ebay_product",
            "ebay_search",
            "vinted_search",
            "leboncoin_search",
            "woolworths_search",
            "woolworths_category",
            "woolworths_specials",
            "woolworths_product",
            "coles_search",
            "coles_category",
            "coles_specials",
            "coles_product",
            "aldi_au_search",
            "aldi_au_category",
            "aldi_au_specials",
            "aldi_au_product",
            "kroger_search",
            "kroger_product",
            "instacart_search",
            "instacart_product",
            "publix_search",
            "publix_product",
            "bodegaaurrera_search",
            "bodegaaurrera_product",
            "zillow_search",
            "zillow_detail",
            "redfin_search",
            "redfin_detail",
            "rightmove_search",
            "idealista_search",
            "idealista_detail",
            "immobilienscout24_search",
            "mobile_de",
            "autoscout24_search",
            "indeed_jobs",
            "glassdoor_jobs",
            "glassdoor_reviews",
            "glassdoor_salaries",
            "naukri_jobs",
            "wellfound_jobs",
            "wellfound_job",
            "wellfound_company",
            "wellfound_company_search",
            "career_site_jobs",
            "upwork_jobs",
            "trustpilot_reviews",
            "g2_reviews",
            "g2_search",
            "capterra_reviews",
            "capterra_search",
            "product_hunt",
            "crunchbase_company",
            "crunchbase_search",
            "yelp_search",
            "yelp_business",
            "yelp_reviews",
            "naver_place_search",
            "naver_place_details",
            "google_play_app",
            "google_play_search",
            "app_store_app",
            "app_store_search",
            "app_store_reviews",
            "youtube_channel",
            "youtube_search",
            "youtube_transcript",
            "spotify_search",
            "spotify_artist",
            "spotify_album",
            "spotify_track",
            "spotify_playlist",
            "sofascore_events",
            "sofascore_match",
            "sofascore_search",
            "sofascore_team",
            "sofascore_player",
            "sofascore_tournament",
            "similarweb_overview",
            "ahrefs",
            "semrush_overview",
            "meta_ad_library"
          ],
          "type": "string",
          "description": "The plugin to run, by its plugin name."
        },
        "params": {
          "type": "object",
          "description": "The plugin's parameters, e.g. {\"query\": \"coffee maker\", \"max_results\": 20}.",
          "propertyNames": {
            "type": "string"
          },
          "additionalProperties": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "number"
              },
              {
                "type": "boolean"
              },
              {
                "type": "array",
                "items": {
                  "type": [
                    "string",
                    "number"
                  ]
                }
              }
            ]
          }
        }
      }
    }
    arguments 229 lines
  • amazon_reviews auth-required 24h ago

    Returns the review data an Amazon product page shows to a signed-out visitor, as JSON: the overall `rating`, total `reviewCount` (global ratings), the 5..1-star `histogram` (percent per star), the AI `customersSay` summary (overall text plus per-aspect `sentiment`, `mentions`, `positive`, `negative`, `summary` and the quoted review `excerpts` Amazon shows for the aspect) and the top `reviews` (each with `id`, `url`, `author`, `rating`, `title`, `body`, `date`, `country`, `fromOtherCountry`, `verified`, `helpfulVotes`, `variant` and `images`). Identify the product with `asin` (plus `marketplace`) or a product `url`. Scope: Amazon only shows its full review list to signed-in customers, so this endpoint returns the public slice on the product page - typically 5 to 13 top reviews, local ones first and then reviews from other countries - not a complete review export. When Amazon hides the top reviews behind a sign-in prompt (common on amazon.com), `reviewsGated` is `true` and `reviews` is empty; the rating, histogram and customers-say data, including its review excerpts, are still returned. Every field is always present and is `null` when the page does not show it. `proxy_country` defaults to the marketplace's home country; the country of the proxy that served the request is reported as `exitCountry`. Returns JSON. Billed like an API request; listing plugins bill one unit per result page they fetch, so keep max_results modest.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "properties": {
        "url": {
          "type": "string",
          "description": "Full Amazon product url, e.g. 'https://www.amazon.de/dp/B0D1XD1ZV3'. The ASIN and marketplace are read from it, so `asin`/`marketplace` are not needed when a url is given."
        },
        "asin": {
          "type": "string",
          "description": "Amazon product id (10-char ASIN, e.g. 'B07PXGQC1Q'; books use their ISBN-10). Give either `asin` (with `marketplace`) or a product `url`."
        },
        "marketplace": {
          "type": "string",
          "description": "Regional Amazon site the ASIN belongs to. Reviews are read from that store. One of: amazon.com, amazon.co.uk, amazon.de, amazon.fr, amazon.it, amazon.es, amazon.nl, amazon.se, amazon.pl, amazon.com.be, amazon.com.tr, amazon.ca, amazon.com.mx, amazon.com.br, amazon.co.jp, amazon.in, amazon.ae, amazon.sa, amazon.sg, amazon.com.au. Default: amazon.com."
        },
        "proxy_country": {
          "type": "string",
          "description": "Proxy country the request is sent from (ISO-2, e.g. 'US', 'DE'). Defaults to the marketplace's home country. The reviews come from the marketplace itself, so any proxy country returns the same reviews."
        }
      }
    }
    arguments 22 lines
  • browse_page auth-required never probed

    Load a web page in a real browser through the ScrapeUnblocker API (https://docs.scrapeunblocker.com), run ordered browser actions on it (click, type into a search box, choose an option, press a key, scroll, wait), then return the resulting HTML. Steps act on the website and are NOT idempotent - they run once per call and are not retried. A failed step returns which step failed plus the page HTML at that point. Billed as one request.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "url",
        "steps"
      ],
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "description": "The absolute URL to open (http/https)."
        },
        "steps": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "action"
            ],
            "properties": {
              "clear": {
                "type": "boolean",
                "description": "For 'type': clear the field first."
              },
              "value": {
                "type": [
                  "string",
                  "number"
                ],
                "description": "Action payload: text to type/select, text for wait_for_text, a key name for press_key (e.g. 'Enter'), milliseconds for wait, or 'bottom'/pixels for scroll."
              },
              "action": {
                "enum": [
                  "wait_for",
                  "wait_for_text",
                  "wait",
                  "click",
                  "type",
                  "select",
                  "press_key",
                  "scroll"
                ],
                "type": "string",
                "description": "The action to perform."
              },
              "selector": {
                "type": "string",
                "description": "CSS selector the action targets (required for wait_for/click/type/select)."
              },
              "timeout_ms": {
                "type": "integer",
                "maximum": 9007199254740991,
                "description": "Per-step timeout override in ms.",
                "exclusiveMinimum": 0
              },
              "selector_type": {
                "enum": [
                  "css",
                  "xPath",
                  "className",
                  "tagName"
                ],
                "type": "string",
                "description": "How to interpret `selector` (default 'css')."
              }
            }
          },
          "minItems": 1,
          "description": "Ordered browser actions to run after the page loads (wait_for, wait_for_text, wait, click, type [human-like], select, press_key, scroll), then the HTML is captured."
        },
        "wait_value": {
          "type": "string",
          "description": "The selector/expression paired with wait_method."
        },
        "wait_method": {
          "enum": [
            "css",
            "js"
          ],
          "type": "string",
          "description": "Optional render-wait before the steps: 'css' selector or 'js' expression."
        },
        "proxy_country": {
          "type": "string",
          "maxLength": 2,
          "minLength": 2,
          "description": "Optional ISO country code to route through, e.g. 'US'."
        },
        "sleep_seconds": {
          "type": "number",
          "description": "Extra seconds to wait after load.",
          "exclusiveMinimum": 0
        }
      }
    }
    arguments 96 lines
  • capture_xhr auth-required never probed

    Load a web page in a real browser through the ScrapeUnblocker API (https://docs.scrapeunblocker.com) and return the JSON its own API calls received: every XHR/fetch response whose URL contains `capture_xhr` (a fragment such as '/api/search'), in order, with status and body. Use it when a site renders from a JSON API that refuses direct requests: the page makes the call, so it succeeds. Optional `steps` make the page fire the call (a search, 'load more'); steps act on the website and run once. Up to 20 responses; the page HTML is not returned. Billed as one request; when the site refuses every matching call (403/429) the call fails and is free.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "url",
        "capture_xhr"
      ],
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "description": "The absolute URL to open (http/https)."
        },
        "steps": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "action"
            ],
            "properties": {
              "clear": {
                "type": "boolean",
                "description": "For 'type': clear the field first."
              },
              "value": {
                "type": [
                  "string",
                  "number"
                ],
                "description": "Action payload: text to type/select, text for wait_for_text, a key name for press_key (e.g. 'Enter'), milliseconds for wait, or 'bottom'/pixels for scroll."
              },
              "action": {
                "enum": [
                  "wait_for",
                  "wait_for_text",
                  "wait",
                  "click",
                  "type",
                  "select",
                  "press_key",
                  "scroll"
                ],
                "type": "string",
                "description": "The action to perform."
              },
              "selector": {
                "type": "string",
                "description": "CSS selector the action targets (required for wait_for/click/type/select)."
              },
              "timeout_ms": {
                "type": "integer",
                "maximum": 9007199254740991,
                "description": "Per-step timeout override in ms.",
                "exclusiveMinimum": 0
              },
              "selector_type": {
                "enum": [
                  "css",
                  "xPath",
                  "className",
                  "tagName"
                ],
                "type": "string",
                "description": "How to interpret `selector` (default 'css')."
              }
            }
          },
          "description": "Optional browser actions that make the page fire the call. Runs once."
        },
        "max_chars": {
          "type": "integer",
          "maximum": 9007199254740991,
          "description": "Cap on the returned text (default 60000).",
          "exclusiveMinimum": 0
        },
        "capture_xhr": {
          "type": "string",
          "maxLength": 500,
          "minLength": 1,
          "description": "A fragment of the API URL the page calls, e.g. '/api/search' (plain substring)."
        },
        "proxy_country": {
          "type": "string",
          "maxLength": 2,
          "minLength": 2,
          "description": "Optional ISO country code to route through, e.g. 'US'."
        }
      }
    }
    arguments 90 lines
  • google_search auth-required never probed

    Run a Google search through the ScrapeUnblocker API (https://docs.scrapeunblocker.com) and return the results page as JSON: organic results with their real URLs, favicons, sitelinks and star ratings, ads, the AI Overview, People also ask, related searches with their links, the knowledge panel, top stories, videos, local and shopping results. Set `full_urls` when you need the exact page URL of every result.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "keyword"
      ],
      "properties": {
        "keyword": {
          "type": "string",
          "minLength": 1,
          "description": "The search query."
        },
        "full_urls": {
          "type": "boolean",
          "description": "Wait until Google gives out every result's real URL. Set it when you need the exact page URL of all results (e.g. to cite or open them); leave it off for quick answers. Google releases a results page's links a few at a time, the last ones up to about 40 seconds after the search: without it a result whose link has not come yet has the site's home page as its `url` (or a Google redirect link), with it the call takes up to about 40 seconds longer. Billed the same."
        },
        "proxy_country": {
          "type": "string",
          "maxLength": 2,
          "minLength": 2,
          "description": "Optional ISO country code to search from, e.g. 'US'."
        },
        "pages_to_check": {
          "type": "integer",
          "maximum": 10,
          "description": "How many result pages to collect (default 1).",
          "exclusiveMinimum": 0
        }
      }
    }
    arguments 30 lines
  • list_elements auth-required never probed

    Fetch a page through the ScrapeUnblocker API (https://docs.scrapeunblocker.com) and return its interactive elements (buttons, inputs, selects, links, forms), each with a ready-to-use selector, as JSON {url, count, elements:[...]} instead of raw HTML. Use it to find the selectors a page's buttons, inputs and links answer to.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "description": "The absolute URL to load and inspect (http/https)."
        },
        "wait_value": {
          "type": "string",
          "description": "The selector/expression paired with wait_method."
        },
        "wait_method": {
          "enum": [
            "css",
            "js"
          ],
          "type": "string",
          "description": "Optional render-wait: 'css' selector or 'js' expression."
        },
        "proxy_country": {
          "type": "string",
          "maxLength": 2,
          "minLength": 2,
          "description": "Optional ISO country code to route through, e.g. 'US'."
        },
        "sleep_seconds": {
          "type": "number",
          "description": "Extra seconds to wait after load before inspecting.",
          "exclusiveMinimum": 0
        }
      }
    }
    arguments 37 lines
  • amazon_search auth-required never probed

    Searches any regional Amazon marketplace for `keyword` and returns the result cards as JSON: `asin`, `title`, `price` + `currency`, `listPrice`, `rating`, `reviewCount`, a clean product `url`, `image`, and the `sponsored` / `prime` flags. Filter with `min_price` / `max_price`, order with `sort` (featured, price_asc, price_desc, avg_review, newest), and page with `page`. Fetch each result's full detail (all fields above plus features and images) through `POST /marketplace/amazon-product`. Some cards show no price on the search page (Amazon defers it, or the item has buying options); those return `price: null` and are kept in the list rather than dropped. `proxy_country` defaults to the marketplace's home country so prices are in the expected currency. Returns JSON. Billed like an API request; listing plugins bill one unit per result page they fetch, so keep max_results modest.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "keyword"
      ],
      "properties": {
        "page": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "1-based page number. Default: 1."
        },
        "sort": {
          "type": "string",
          "description": "Result order: featured, price_asc, price_desc, avg_review, newest. Default 'featured'. Default: featured."
        },
        "keyword": {
          "type": "string",
          "description": "Search phrase, e.g. 'wireless headphones' or a brand + model."
        },
        "max_price": {
          "type": "number",
          "description": "Highest price to include, in the marketplace's currency."
        },
        "min_price": {
          "type": "number",
          "description": "Lowest price to include, in the marketplace's currency."
        },
        "marketplace": {
          "type": "string",
          "description": "Regional Amazon site to search. Prices and currency differ per marketplace. One of: amazon.com, amazon.co.uk, amazon.de, amazon.fr, amazon.it, amazon.es, amazon.nl, amazon.se, amazon.pl, amazon.com.be, amazon.com.tr, amazon.ca, amazon.com.mx, amazon.com.br, amazon.co.jp, amazon.in, amazon.ae, amazon.sa, amazon.sg, amazon.com.au. Default: amazon.com."
        },
        "proxy_country": {
          "type": "string",
          "description": "Proxy country the request is sent from (ISO-2, e.g. 'US', 'DE'). Defaults to the marketplace's home country so prices come back in the expected currency."
        }
      }
    }
    arguments 39 lines
  • google_images auth-required never probed

    Runs the Google Images vertical (`udm=2`) for `q` and returns the image results as JSON. Every result carries `imageUrl` (the full-resolution origin image, not a Google thumbnail; for an image found inside a document such as a PDF, which has no URL of its own, it is Google's thumbnail and `sourcePageUrl` is the document), `sourceDomain` and `googleImagesUrl` (the Google Images viewer link, i.e. the `/imgres?...` URL a browser copies from the result tile), plus `sourcePageUrl`, `title`, `sourceName`, `thumbnailUrl`, `width`, `height` and `fileSize` where available. Set `proxy_country` to target a market: the Google market (`gl`) follows it automatically, and `gl` is only an optional override. `pages` fetches up to 5 result pages of ~100 each; every page fetched is billed as one request. `time_range` (past hour/day/week/month/year) or `date_from`/`date_to` limit the results to images Google found in that period, so a repeated scan returns only what is new. Returns JSON. Billed like an API request; listing plugins bill one unit per result page they fetch, so keep max_results modest.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "q"
      ],
      "properties": {
        "q": {
          "type": "string",
          "description": "Image search term, e.g. 'eiffel tower'."
        },
        "gl": {
          "type": "string",
          "description": "Optional Google market override (ISO-2, e.g. 'us', 'de'). Leave empty and the market follows `proxy_country` ('us' when neither is set). The market, not the proxy country, is what decides which images rank."
        },
        "pages": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "How many Google Images result pages to fetch (1-5, ~100 results each; Google stops at ~400-500 per query). Each page fetched is billed as one request. Default: 1."
        },
        "date_to": {
          "type": "string",
          "description": "Only images Google found on or before this date (YYYY-MM-DD). Works alone or with `date_from`; cannot be combined with `time_range`."
        },
        "date_from": {
          "type": "string",
          "description": "Only images Google found on or after this date (YYYY-MM-DD). Works alone or with `date_to`; cannot be combined with `time_range`."
        },
        "time_range": {
          "type": "string",
          "description": "Only images Google found within this recent period: `hour`, `day`, `week`, `month` or `year` (Google Images' Tools > Time filter). Use it to get just the new results on repeated scans. Cannot be combined with `date_from`/`date_to`."
        },
        "max_results": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "Optional cap on the number of results returned (default: all results of the fetched pages)."
        },
        "proxy_country": {
          "type": "string",
          "description": "Proxy country the request is sent from (ISO-2, e.g. 'US', 'DE'). Image results are market-specific."
        }
      }
    }
    arguments 45 lines
  • youtube_search auth-required never probed

    Searches YouTube for `query` and returns the results as JSON. For each video: `videoId`, `title`, `url`, `channel` (name/id/url), `publishedText`, `viewCount` (+ text), `lengthSeconds` (+ text), `thumbnails`, `descriptionSnippet`, `badges`, `verified` and `isLive`. Filter with `type` (video / channel / playlist / all) and `sort` (relevance / date / views / rating), and collect up to `max_results` across pages. Returns JSON. Billed like an API request; listing plugins bill one unit per result page they fetch, so keep max_results modest.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "query"
      ],
      "properties": {
        "sort": {
          "type": "string",
          "description": "Ordering: relevance, rating, date, views. Default: relevance."
        },
        "type": {
          "type": "string",
          "description": "Result type: video, channel, playlist, movie, all. Default: video."
        },
        "query": {
          "type": "string",
          "description": "Search terms."
        },
        "max_results": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "How many results to collect across pages (~20 per page). Default: 20."
        },
        "proxy_country": {
          "type": "string",
          "description": "Proxy country the request is sent from (ISO-2, e.g. 'US', 'DE'). Defaults to US."
        }
      }
    }
    arguments 31 lines
  • youtube_transcript auth-required never probed

    Returns a YouTube video's captions as JSON: timestamped `segments` (`start`, `dur`, `text`) and a joined `text`, plus `availableLanguages`, the picked `language`, `isAutoGenerated`, and the video's `title`, `author` and `lengthSeconds`. Pass a video id or any YouTube video URL; choose a caption language with `lang`. Ideal for LLM/RAG pipelines, subtitles and content analysis. Returns JSON. Billed like an API request; listing plugins bill one unit per result page they fetch, so keep max_results modest.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "video"
      ],
      "properties": {
        "lang": {
          "type": "string",
          "description": "Preferred caption language code, e.g. 'en'. Omit for the default/first track. A prefix like 'en' matches 'en-US'."
        },
        "video": {
          "type": "string",
          "description": "Video id (dQw4w9WgXcQ) or any YouTube video URL."
        },
        "format": {
          "type": "string",
          "description": "Output shape: segments, text. 'segments' returns timestamps; 'text' returns only the joined plaintext. Default: segments."
        },
        "proxy_country": {
          "type": "string",
          "description": "Proxy country the request is sent from (ISO-2, e.g. 'US', 'DE') for the watch page. Defaults to US."
        }
      }
    }
    arguments 25 lines
  • zillow_search auth-required never probed

    Searches Zillow for `location` (a city/state or ZIP) and returns the listings as JSON: `price`, `beds`, `baths`, `area`, `address`, `homeType`, `zestimate`, `rentZestimate`, `daysOnZillow`, coordinates, broker and a clean `url`. Filter with `status` (for_sale / for_rent / sold), `min_price`/`max_price`, `beds`, `baths` and `home_type`, sort with `sort`, and collect up to `max_results` across pages. Rental results can include apartment buildings (`isBuilding: true`): they have no `zpid` and carry `lotId`, `buildingName`, a rent range (`price` to `maxPrice`), `units` and `availableUnits` instead. Returns JSON. Billed like an API request; listing plugins bill one unit per result page they fetch, so keep max_results modest.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "location"
      ],
      "properties": {
        "beds": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "Minimum bedrooms."
        },
        "page": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "1-based results page to start from. Default: 1."
        },
        "sort": {
          "type": "string",
          "description": "Ordering: newest, price_asc, price_desc, relevant, beds, sqft, lot. Default: newest."
        },
        "baths": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "Minimum bathrooms."
        },
        "status": {
          "type": "string",
          "description": "Listing status: for_sale, for_rent, sold. Default: for_sale."
        },
        "location": {
          "type": "string",
          "description": "City/state or ZIP to search, e.g. 'Austin, TX' or '78704'."
        },
        "home_type": {
          "type": "string",
          "description": "Property type filter: houses, condos, townhomes, multi_family, apartments, manufactured, lots_land. Omit for all."
        },
        "max_price": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "Maximum price (or monthly rent)."
        },
        "min_price": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "Minimum price (or monthly rent)."
        },
        "max_results": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "How many listings to collect across pages (~41 per page). Default: 41."
        },
        "proxy_country": {
          "type": "string",
          "description": "Proxy country the request is sent from (ISO-2, e.g. 'US', 'DE'). Defaults to US."
        }
      }
    }
    arguments 65 lines
  • trustpilot_reviews auth-required never probed

    Returns a company's Trustpilot profile and reviews as JSON. `company` is the reviewed domain (e.g. `www.nike.com`). The response has a `company` summary (`trustScore`, `totalReviews`, `ratingDistribution` 1-5, `categories`, `contact`) and a `reviews` array - each with `url`, `rating`, `title`, `text`, `verified`, `verificationLevel`, `verificationSource`, `source`, `pending`, `merged`, `author` (name, country, review count, `id`, `image`, `profileUrl`, `reviewsOfThisCompany`), `reply` (the company's response, with dates) and `date` / `experiencedDate` / `updatedDate`. Page with `page`/`pages` (20 reviews per page), and filter with `stars`, `sort` (recency/relevancy), `language`, `date`, `search`, `verified` or `replies`. Returns JSON. Billed like an API request; listing plugins bill one unit per result page they fetch, so keep max_results modest.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "company"
      ],
      "properties": {
        "date": {
          "type": "string",
          "description": "Only reviews from a recent window: last30days, last3months, last6months, last12months. Omit for all time."
        },
        "page": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "1-based page to start from (20 reviews/page). Default: 1."
        },
        "sort": {
          "type": "string",
          "description": "Ordering: recency, relevancy. Default 'recency' (newest first). Default: recency."
        },
        "pages": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "How many consecutive pages to fetch from `page` onward (20 reviews each). Stops early at the last page. Default: 1."
        },
        "stars": {
          "anyOf": [
            {
              "type": "array",
              "items": {
                "type": "integer",
                "maximum": 9007199254740991,
                "minimum": -9007199254740991
              }
            },
            {
              "type": "integer",
              "maximum": 9007199254740991,
              "minimum": -9007199254740991
            }
          ],
          "description": "Only reviews with these star ratings (1, 2, 3, 4, 5). Repeatable, e.g. stars=4&stars=5."
        },
        "search": {
          "type": "string",
          "description": "Keyword to search within the company's reviews."
        },
        "company": {
          "type": "string",
          "description": "The reviewed company's domain, e.g. 'www.nike.com' or 'nike.com'. A full site URL or a pasted Trustpilot review URL is also accepted."
        },
        "replies": {
          "type": "boolean",
          "description": "Only reviews the company has replied to. Default: false."
        },
        "language": {
          "type": "string",
          "description": "Review language ISO-2 code (e.g. 'en', 'de') or 'all'. Default 'all'. Default: all."
        },
        "verified": {
          "type": "boolean",
          "description": "Only verified reviews (Trustpilot's verified badge). Default: false."
        },
        "proxy_country": {
          "type": "string",
          "description": "Proxy country the request is sent from (ISO-2, e.g. 'US', 'DE'). Defaults to a country chosen for the site."
        }
      }
    }
    arguments 71 lines
  • booking_hotels auth-required never probed

    Searches Booking.com for `location` and returns the properties as JSON: `name`, `price` (with `checkin`/`checkout`), `reviewScore`, `address`, coordinates, `image` and a hotel `url`. Set `adults`, `children`, `rooms` and `currency`, and collect up to `max_results` across pages. Prices only appear when check-in/check-out dates are given. Returns JSON. Billed like an API request; listing plugins bill one unit per result page they fetch, so keep max_results modest.

    mcp-tool

    {
      "type": "object",
      "$schema": "http://json-schema.org/draft-07/schema#",
      "required": [
        "location"
      ],
      "properties": {
        "rooms": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "Number of rooms."
        },
        "adults": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "Number of adults."
        },
        "checkin": {
          "type": "string",
          "description": "Check-in YYYY-MM-DD (needed for prices)."
        },
        "checkout": {
          "type": "string",
          "description": "Check-out YYYY-MM-DD."
        },
        "children": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "Number of children."
        },
        "currency": {
          "type": "string",
          "description": "Price currency: USD, EUR, GBP, AUD, CAD, CHF, JPY, CNY, INR, BRL, MXN, PLN, SEK, NOK, DKK, AED, SGD, ZAR, TRY, RUB. Default: USD."
        },
        "location": {
          "type": "string",
          "description": "City or place to search, e.g. 'Austin' or 'Paris'."
        },
        "max_results": {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "description": "How many properties to collect across pages. Default: 25."
        },
        "proxy_country": {
          "type": "string",
          "description": "Proxy country the request is sent from (ISO-2, e.g. 'US', 'DE')."
        }
      }
    }
    arguments 53 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 37ac45981d49bab8.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/37ac45981d49bab8/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/37ac45981d49bab8/badge.svg)](https://brick.blue/agent/37ac45981d49bab8?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.

_ also on scrapeunblocker.com 2 entries

Served from the same domain, which is what was measured. Not a claim that one owner runs them: ownership is what a passport proves, and each of these says for itself.