ScrapingBot

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Public web data for AI agents: scrape any page, plus Google, TikTok, Instagram and Amazon as JSON.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "ScrapingBot": {
      "url": "https://scrapingbot.io/api/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (23)

• listCapabilities read-only

  List every ScrapingBot tool, the API routes behind them and their parameters. Free.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• scrapeWebsite read-only

  Fetch any public web page and return its content as markdown (format: "html" for the raw HTML). 1 credit; render_js (pages built with JavaScript) 5; premium_proxy 10; stealth_proxy 75. screenshot: true attaches a screenshot image.

  Parameters:

  • url (required) — string
  • wait — integer
  • format — string — Page content as markdown (default, compact and readable) or the raw HTML
  • cookies — string
  • timeout — integer
  • wait_for — string
  • block_ads — boolean
  • render_js — boolean
  • screenshot
  • wait_browser — string
  • premium_proxy — boolean
  • stealth_proxy — boolean
  • block_resources — boolean
  • capture_runtime_issues — boolean

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• extractStructuredData read-only

  Fetch a web page and have AI pull out exactly the fields you want, as JSON. Pass ai_query (plain English, e.g. "title, price and stock") or ai_schema ({"field": "description"}). The page cost plus 5 credits.

  Parameters:

  • url (required) — string
  • wait — integer
  • cookies — string
  • timeout — integer
  • ai_query — string
  • wait_for — string
  • ai_schema
  • block_ads — boolean
  • render_js — boolean
  • screenshot
  • wait_browser — string
  • premium_proxy — boolean
  • stealth_proxy — boolean
  • block_resources — boolean
  • capture_runtime_issues — boolean

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• getScrapeJob read-only

  Look up an earlier scrape by the job_id it returned. Free.

  Parameters:

  • job_id (required) — string

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• pollJobUntilDone read-only

  Wait for a scrape job to finish, then return it. Free.

  Parameters:

  • job_id (required) — string
  • timeout_ms — integer
  • poll_interval_ms — integer

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• runBrowserScenario read-only

  Open a page in a real browser, run steps such as click, fill, scroll and wait, then return the resulting page as markdown. js_scenario: {"instructions": [{"fill": ["#q", "shoes"]}, {"click": "#go"}, {"wait": 1000}]}. From 5 credits.

  Parameters:

  • url (required) — string
  • js_scenario (required)
  • wait — integer
  • format — string — Page content as markdown (default, compact and readable) or the raw HTML
  • cookies — string
  • timeout — integer
  • wait_for — string
  • block_ads — boolean
  • render_js — boolean
  • screenshot
  • wait_browser — string
  • premium_proxy — boolean
  • stealth_proxy — boolean
  • block_resources — boolean
  • capture_runtime_issues — boolean

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• googleSearch read-only

  Google results as JSON: web (default), images, videos, news, shopping, places or maps (type), for any country (gl) and language (hl). Places and maps results include a cid for googleReviews. 10 credits.

  Parameters:

  • q (required) — string
  • gl — string
  • hl — string
  • ll — string — Maps/places viewport, e.g. @30.27,-97.74,12z
  • num
  • tbs — string
  • page
  • type — string — What to search: web results (default), images, videos, news, shopping, places or maps.
  • sortBy — string
  • autocorrect — boolean

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• googleReviews read-only

  Reviews of a place from Google Maps, by the cid, fid or placeId in a googleSearch places or maps result. sortBy newest, mostRelevant, highestRating or lowestRating; pass nextPageToken for more. 10 credits.

  Parameters:

  • gl — string
  • hl — string
  • cid — string
  • fid — string
  • sortBy — string
  • placeId — string
  • nextPageToken — string

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• instagramUser read-only

  An Instagram profile: bio, follower, following and post counts, links and the numeric user id other tools need. Pass one of username, user_id or url. 5 credits.

  Parameters:

  • url — string
  • user_id
  • username — string

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• instagramSearch read-only

  Search Instagram accounts, hashtags, places or posts (search_type), or everything at once (global). 5 credits.

  Parameters:

  • keyword (required) — string
  • search_type (required) — string

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• instagramMedia read-only

  Instagram content by mode: an account's posts, reels or tagged posts (user_id), one post by shortcode or url, a post's comments, the replies to a comment (comment_id), or an account's active stories (username). 5 credits.

  Parameters:

  • mode (required) — string
  • url — string
  • count — integer
  • user_id
  • media_id
  • username — string — Username (stories)
  • shortcode — string
  • comment_id — string — Parent comment id (comment_replies)
  • end_cursor — string
  • pagination_token — string
  • code_or_id_or_url — string

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• instagramFollowers read-only

  List or search an Instagram account's followers or following, by numeric user_id from instagramUser. query searches the whole list; max_id pages. For very large accounts Instagram shows only about 50 recent followers, so use query to find someone. 5 credits.

  Parameters:

  • user_id (required) — string — Numeric user id (from instagramUser)
  • direction (required) — string
  • query — string — Search the list by username or name
  • max_id — string — next_max_id from the previous page

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• tiktokVideo read-only

  A TikTok video's stats, caption, author, sound and download links, by video URL. 1 credit.

  Parameters:

  • url (required) — string

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• tiktokUser read-only

  A TikTok profile by username: bio, counts, verified badge and numeric user id; include_posts returns the latest videos instead. 1 credit.

  Parameters:

  • unique_id (required) — string
  • include_posts — boolean

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• tiktokSearch read-only

  Search TikTok creators (search_type: users) or videos (videos) by keyword. Videos page: for page 2 onward pass the previous response's data.cursor as cursor and its data.searchId as search_id. Users search returns a single page and ignores cursor. 1 credit.

  Parameters:

  • query (required) — string
  • search_type (required) — string
  • count — integer
  • cursor — Videos only: the previous response's data.cursor, for the next page
  • search_id — string — Videos only: the previous response's data.searchId; required with cursor for page 2 onward

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• tiktokComments read-only

  Comments on a TikTok video (url), or the replies to one comment (comment_id plus the video url or video_id). 1 credit.

  Parameters:

  • url — string — Video URL (required for comments)
  • count — integer
  • cursor — integer
  • video_id — string — Video id (replies only; or pass url)
  • comment_id — string — Set to fetch the replies to this comment

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• tiktokFollowers read-only

  A TikTok account's followers or the accounts it follows, by numeric user_id (data.user.id from tiktokUser). Up to 50. 1 credit.

  Parameters:

  • user_id (required) — string — Numeric user id (data.user.id from tiktokUser)
  • direction (required) — string
  • count — integer

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• amazonSearch read-only

  Search Amazon US products by keyword: title, price, rating, Prime and photo for each. page for more. 10 credits.

  Parameters:

  • query (required) — string
  • page
  • department — string

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• amazonProduct read-only

  Everything on an Amazon product page by ASIN: price, rating, availability, bullet points, specifications, photos and variations. 10 credits.

  Parameters:

  • asin (required) — string

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• amazonProducts read-only

  Full details for up to 20 ASINs in one call, the same as amazonProduct for each. 10 credits per product returned; ASINs that fail are free.

  Parameters:

  • asins (required) — array — Up to 20 ASINs; 10 credits per product returned

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• amazonSuggestions read-only

  The suggestions Amazon shows as a shopper types: useful for keyword research. 10 credits.

  Parameters:

  • query (required) — string — What a shopper has typed so far
  • limit — integer
  • department — string — Search alias such as aps, electronics, stripbooks

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• amazonRankings read-only

  Amazon's Best Sellers or New Releases for a department, in rank order, with price and rating. 10 credits.

  Parameters:

  • list (required) — string
  • category (required) — string — Amazon department slug
  • page — integer

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• providerRequest read-only

  Call any Google, Instagram, TikTok or Amazon endpoint by path, for the few the other tools do not cover (listCapabilities lists them). Costs the same as that API.

  Parameters:

  • provider (required) — string
  • endpoint (required) — string
  • params — object

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.