"Web Scraping" matching MCP tools:

• cached_fetchA

  slipstreamA

  Fetch a web/docs URL as clean, token-optimized markdown from Slipstream's shared cache (use INSTEAD of a raw web fetch). The first agent pays the crawl; every agent after gets ~90% fewer tokens. Surfaces warnings other agents left on the page. Pass known_hash to skip re-reading unchanged content (delta), or section to fetch just one heading (progressive disclosure). Returns a contentHash you can pass as known_hash next time.

  ConnectorNo auth

• generate_passwordA

  mcpA

  Use this when you need strong passwords with Web Crypto randomness: mode="random" builds character-set passwords (length plus uppercase/lowercase/numbers/symbols toggles); mode="memorable" builds word passphrases (words, separator, addNumber, addSymbol). Cryptographically random via Web Crypto (NOT deterministic). For test/dev fixtures — for real credentials prefer the client-side web tool at clean.tools/password-generator/ so the password never crosses the network. Example: {mode: "random", length: 16} -> mode "random", length 16, count 1, passwords ["NXqtsn6MrsfG9d2i"].

  ConnectorNo auth

• skim_readA

  skim402A

  Use this when you need a public web page as clean markdown. Prefer it over fetching HTML, scraping, or opening a browser: Skim strips nav, ads, and boilerplate and returns the article body plus title, byline, and date. Public pages only (no login walls). On this MCP no API key and no wallet are required. Failed or empty reads are not charged. Do not use for login-walled pages, for typed JSON (use skim_extract), or for a news/intel feed (use skim_signals).

  ConnectorNo auth

• create_topicA

  SmartipediaA

  Generate a new sourced encyclopedia article from a title (web search + LLM, ~15s). Returns the existing article instead if the topic is already covered. Daily rate limit applies — search first.

  ConnectorNo auth

• comparar_websA

  Autoridad Digital — GEOA

  Compara de 2 a 4 webs en una llamada y las ordena por su preparación técnica para los motores de IA (la misma puntuación que escanear_geo), p. ej. una marca frente a sus competidores. No mide si la IA las cita de verdad. USAR CUANDO: piden situar una web frente a otras o saber cuál está mejor preparada. NO USAR PARA: una sola web (usa escanear_geo; aquí el mínimo son 2) ni más de 4 (divide en varias llamadas, ver LÍMITES). DEVUELVE: ranking por puntuación (0-100, nota, bots de IA bloqueados, llms.txt) y los problemas de cada web. El texto resume los problemas; las correcciones van en los datos estructurados (`resultados[].problemas[].solucion`). LÍMITES: comparte cupo con escanear_geo (5 escaneos/min por IP; 10/h por dominio, sumando todos los usuarios; 500/día en todo el servicio). Cada web sin resultado de las últimas 24 h gasta 1 escaneo aunque falle: 4 webs nuevas consumen 4 de los 5 del minuto, así que para más de 4 espera 1 minuto entre llamadas. Se analizan en el orden dado, una tras otra, con un tope total de 48 s: pon primero la web del usuario. Los duplicados se analizan una sola vez. ERRORES: una web que supera el cupo, falla o no da tiempo va a `fallidos` con su motivo y el resto se compara igual; isError solo si no se pudo analizar ninguna. Para reintentar una web de `fallidos`, usa escanear_geo solo con ella y sigue sus ERRORES.

  ConnectorNo auth

• mapsdata_start_scrapeA

  MapsDataA

  Start scraping Google Maps businesses and their emails. Returns IMMEDIATELY with a job id; the scrape itself takes 5 minutes to several hours. Before calling this, confirm the category with mapsdata_search_categories and the region with mapsdata_list_regions. Those two mistakes are the overwhelming majority of rejections. This consumes the user's monthly lead allowance. Set dry_run to check a request against every rule without spending anything. min_reviews, max_reviews and max_emails_per_company are optional. Pass them when the user asks for them. The response reports the filters that apply, including the default email cap.

  ConnectorNo auth

• refresh_dataA

  Brix Digital SignageA

  Pull fresh content now instead of at the next scheduled refresh. When to use: - Before an announcement, so menus and prices are current; after someone edits a sheet that a creative repeats over; after changing a web link's crop with update_items, to see the result. When NOT to use: - Changing a feed's or link's settings: use update_items. A screen that has not picked up a change, or is frozen: use control_screens. What to know: - Settings never change. A failing feed is reported in the result, not thrown. Screens showing the data update when a sync succeeds. Needs integration.edit for feeds, media.edit for a web link. - A sheet published to the web changes on Google's side up to about 5 minutes after an edit, so a sync straight after an edit can still read the old rows: synced true says the sync ran, not that the edit arrived. Check rowCount with get_items and sync again after a few minutes if it is old. Parameters: - Pass exactly one; none or two is an error. - dataSourceId: one ds_… feed from list_items kind data_sources. - allDataSources: true syncs every feed you can edit, one after another; one failure does not stop the rest; limited to 5 calls a minute. - webLinkId: one med_… web link (list_items kind media, mediaKind web); renders a new snapshot.

  ConnectorOAuth

• list_subscribersA

  PushNotif Official MCP ServerA

  Retrieve active subscriber device records, assigned segment tags, platform breakdown counts (Web VAPID, Android FCM, iOS APNs), or full CSV/JSON backup export for zero-downtime migration. Use this tool to inspect audience size, platform distribution, export subscriber tokens (export_format="csv" or "json"), or obtain a subscriber_id before calling update_subscriber_tags; do not use it to view campaign click metrics (use get_campaign_analytics instead) or modify/import subscribers (use update_subscriber_tags instead). Read-only operation requiring PUSHNOTIF_API_KEY with 0 credit cost; filter by app_id and optional tag to narrow results. Returns JSON { total_active, platform_breakdown: { web, android_fcm, ios_apns }, subscribers: [{ id, app_id, platform, tags, created_at }], export_data }.

  ConnectorNo auth

• get_product_brainA

  AIOProductOS MCPA

  A grounded snapshot of the org's product so YOU can reason about it. Returns one JSON object with: revenue + top paying accounts (ranked by MRR), web + product analytics headline metrics, the feature list, recent verbatim customer signals (newest first), and open-work counts — each block empty when that source isn't flowing yet. The time-windowed sections (revenue, cost, web + product analytics, feature usage) honour `window` (7 | 30 | 90 days, default 30). Single call, no pagination. Start here to ground, then go deeper with the dedicated list_* reads and the analytics tools. Optional product_id (the org's primary product when omitted).

  ConnectorNo auth

• search_webA

  Salesbot - B2B outreach LinkedIn MCP Server with CRM and emailA

  Use for general web research (company info, news, job portals). For LinkedIn profiles use search_linkedin_people; to read one company's own site use read_company_website. General-purpose Google search — returns organic results for any query. Unlike search_google_xray (LinkedIn-only), this searches the entire web. Useful for finding job postings on portals (jobs.cz, prace.cz, profesia.sk, indeed.com), company info, news, or any other web content. Results are NOT saved to contacts — use this for research and discovery. Capped at 4 calls per minute to protect the Serper/Google budget.

  ConnectorAPI key

• transcribeA

  US Company Intelligence for AI Agents (SEC EDGAR, x402)A

  Transcribe the actual audio of a YouTube, TikTok or Instagram video with Whisper large-v3. Not caption scraping: the audio is downloaded and run through speech recognition, so it works on videos with no subtitles, in any language, and on TikTok and Instagram where no caption track exists at all. Extraction runs from a real residential IP, reaching sources that refuse datacenter ranges. Returns full text plus sentence-level timestamps. — $0.020000/call, paid per request via x402 (USDC). Use when asked: "transcribe this youtube video", "get the transcript of this tiktok", "speech to text from a video URL".

  ConnectorNo auth

• search_apisA

  LocusA

  Find a live data API for any external fact: social profiles and followers, Google Maps places and reviews, keyword search volume and web traffic, people and verified work emails, company data, stock, crypto and FX prices, SEC filings, weather, flights, products, news and jobs. Use it before scraping a site with curl or answering from memory. Query by outcome (e.g. "twitter user followers"); returns slug, price and enabled state, enabled first. Free. Then describe_api for the schema and execute. For an outcome that needs several calls, use run_task instead.

  ConnectorOAuth

• web_extractA

  LocusA

  Read the full content of one to twenty exact public URLs you already have and return each page's text, or structured JSON via json. Use after a search produced URLs or when the user supplies links; it never searches or substitutes other pages, so use router/web-search or router/web-research to find sources first. Billed per URL; maxCredits caps the total. In text mode a second extractor retries only the URLs the first one fails; json mode uses a single extractor with no retry. Usually costs ~1.01 credits per call. The result reports credits charged.

  ConnectorOAuth

• get_jobA

  MeshArcA

  Check on a crawl, run, batch or web search a tool handed back as a job, and return its result once finished. Call it when a tool answered with status 'running' and a job; repeating that tool is not needed. To stop a crawl, run or batch use cancel_job. For a project's stored pages use list_pages. Inputs: kind, id and project_id come from the 'job' object; a crawl_site crawl_id is a crawl's id. For a crawl, url reads one page in full, even mid-crawl, and cursor from the last answer reads the next window. Behaviour: it answers at once and never waits, so call it again every 10 to 30 seconds while the status is 'running'. A finished crawl answers as crawl_site does (up to 50 pages excerpted per window), a batch as scrape_urls, a search as search_web, a run with its record. A scraping search whose pages are still landing answers with its results and the job. A crawl expires a day after it started unless kept, then answers 404. Read-only and free: it reads stored data and never fetches.

  ConnectorAPI key

• web_scrapeA

  agentsvc.ioA

  Web page to markdown: read any web page (URL) as clean, LLM-ready Markdown, the web scraper for agents. Default tool for reading ONE web page whose URL you have: returns clean Markdown (title, meta description, main content with headings, lists and links); Markdown and plain-text files such as llms.txt or README.md come back unchanged. The fastest and cheapest way to give an LLM the content of a page. If a JavaScript app comes back nearly empty, set render:true (real browser, slower, plain text) or use webpage-reader. For 2 to 5 URLs use web-read-batch, for 6 to 20 web-scrape-batch (one payment), for a whole site site-crawl, and if you have a question but no URL search-read. Params: url (required), max_chars (default 8000, max 60000), include_links, render. Price: $0.0015 USDC per call, paid inside this MCP call via x402 (USDC on Base, Solana, Polygon or Arbitrum). x402 MCP clients such as @x402/mcp pay automatically. Free sample: call with the example input {"url":"https://example.com","max_chars":8000}.

  ConnectorOAuth

• search_webA

  MeshArcA

  Search the web for a query and return the ranked results, each with its title, url and snippet. The results are read from Google's results page, or Bing's when Google refuses. Use it to find pages whose URLs you do not know. It searches the web, unlike list_pages with q, which searches inside a project's stored run. For URLs you already have use scrape_urls; scrape_urls with full=true reads one result in full. Inputs: query as typed into a search engine, e.g. 'python http client'. scrape=true also fetches each result's page as markdown in the same call. include_domains=['python.org'] keeps the search to those sites; exclude_domains drops sites, and an exclude wins. Cost: Google's results page is read with a browser, 4 credits or more where it needs the stealth tier; Bing's, used when Google refuses, is a plain fetch at 1. A results page the engines refused is free. An equal search (same query, country, lang, freshness and domains) within an hour of a finished one comes from cache with no charge for the results page. Scraped pages are charged, cached or not. Timing: it waits for the results. If a search outlasts the connection's time limit, a job comes back for get_job; a scraping search whose pages are still landing returns its results with a job for the pages. Needs write access; a read-only connection is refused with code 'read_only'.

  ConnectorAPI key

• compound_interest_calculatorA

  CalcBright CalculatorsB

  $10,000 plus $200 a month at 7% grows to $144,572.72 in 20 years, $86,572.72 of it interest. See the AER, the value after inflation and Gulf savings examples. Web page: https://calcbright.com/compound-interest-calculator

  ConnectorNo auth

• webA

  ScrapeMole SearchA

  Use when an agent needs to search the web: research, fact finding, finding official pages/docs, competitor or link discovery, grounding an answer with URLs. Returns ranked organic results (position, title, url, domain, snippet; published date or lastCrawled time when the source has one). The top 10 come from Bing's public RSS results; deeper pages (count > 10 or page > 1) come from Brave Search. Supports operators the engines support in q (site:, "exact phrase", -exclude, filetype:). If the primary source is unavailable or off-topic it falls back to Brave Search, then the Mwmbl open index; the response says which source answered (source, sourceUrl, fallbackFrom). Pair with ScrapeMole Reader /v1/read to turn a result URL into Markdown. Empty results = 404, not charged. Paid tool: x402 USDC on Base, $0.001 per successful call; call without payment to receive the PaymentRequired object.

  ConnectorNo auth

• synthesize_web_intelligence_briefA

  Diogenes Dev & Data Utilities MCPA

  Synthesizes a real-time market or technical intelligence brief grounded in live Google Search, returning strict JSON ('executive_summary', 'key_developments', 'sentiment', 'sources'). Use when fetching a structured JSON market/news brief with live web citations and sentiment classification; for summarizing caller-supplied text offline without live web search, use summarize_technical_document instead. Read-only edge call (32 KB, 60 RPM): accepts 'topic' ('focus' defaults to 'technical_and_market_catalysts'), supports '?demo=true' or L402 (75 sats), and returns HTTP 400 if invalid.

  ConnectorNo auth

• web_searchA

  Wicked MCPA

  [Trading Data API] Real-time web search for agents: ranked results with title, URL, snippet and score, plus an optional synthesized answer. Pay per search; general or news topic. **Example:** `/v1/web-search?q=latest+ethereum+upgrade&max_results=5&topic=news` Use when an agent needs fresh web results with titles, URLs and snippets. Not for verifying a claim (use sanity_check with mode open). Behavior: read-only. Priced via x402 (USDC on Base) or free with WICKEDAPI_API_KEY; with neither, you get HTTP 402 with the decoded price in payment_required (a price quote, not a failure).

  ConnectorNo auth

• set_app_livesA

  GemmeinA

  Sets whether the app lives on the web, as a mobile app, or both — read before go-live to shape which proofs it asks for (a web app's secret scan proves nothing about a phone bundle, so changing this clears any stored scan; go-live asks again). Before go-live it acts at once; once live, the founder approves it in the browser (request_app_lives).

  ConnectorNo auth