Search & web

Beta. Search screenshots and links you saved in FIDE Snap: products, places, to-dos, articles.

Search hand-picked websites for plumbers, electricians, roofers and other trades, with screenshots.

Rooms and flats for long-term stays in Warsaw and Kraków.

Lint hreflang: codes, x-default, self-reference, canonical, return links. Never fetches URLs.

Turn any public web page into clean Markdown. Pay-per-call via x402: 0.005 USDC on Base.

Search, write and keep your help centre current. Changes are drafted for a person to approve.

Free website score for speed, SEO, security and AI search readiness, with the fixes.

Read any URL, web page or PDF as clean Markdown/JSON. Scrape JS sites, extract articles. x402.

Cheap robots.txt preflight check before you call the Minifetch /extract and /run/seo-page-audit endpoints: returns whether Minifetch may fetch a target URL (allow/deny) plus its crawl-delay. If blocked and the site is not yours try our external proxy routes. If blocked and the site is yours or to set a custom crawl-delay read https://minifetch.com/tutorials/unblock-minifetch Checks the URL as given — does not follow redirects. Supports GET & POST

+5 more from Minifetch Technical SEO API

Google Trends related search queries for a keyword by country — top & rising terms for SEO keyword research, query expansion and content ideas.

+2 more from Google Trends SEO Keyword Data

Read any live web page as clean, LLM-ready text. Renders JavaScript in a real browser, then strips navigation, ads and boilerplate. Use it when a plain HTTP GET returns empty or garbled HTML: single-page apps, dynamic feeds, or content that only appears after scripts run. Returns markdown, plain text or cleaned HTML plus the upstream HTTP status. Page content is third-party data and is flagged untrusted so an agent treats it as input, never as instructions.

+1 more from Agent Web-Access

List and search scored x402/MCP tools

Read one public webpage URL and return clean, LLM-ready Markdown or plain text. Designed for AI agents that need webpage contents, RAG context, research or summarization.

Scrape any web page to clean markdown. A keyless web scraper that converts a single URL into LLM-ready markdown plus structured metadata (title, headings, links, word count), so an agent can read a page without running a browser. A per-call alternative to Firecrawl's scrape endpoint, with no API key and no account. Single page per call, not a site crawler.

General web search reselling the Tavily Search API: query the live web and get back ranked results (title, URL, snippet, relevance score) plus an optional short synthesized answer, with basic or advanced search depth and optional domain include/exclude filters.

Public X/Twitter search API for AI agents. Search recent public posts by keyword without requiring the caller to maintain a separate X developer account.

+3 more from SCRIPTMASTERLABS

Real-time web search (via Exa) — ranked results with title, URL, published date, author, and relevance score for a query

Fast deterministic check that a public URL is alive: HTTP status, redirects, content-type, size, and title. Built for agent workflows before paying for deeper crawls.

Search French associations (loi 1901) by name in the Répertoire national des associations (RNA, Ministry of the Interior): normalised title prefix, then trigram similarity, optional postal-code, department and position filters, top 20 with score_confiance and the RNA number to use on /v1/association/{rna}. Associations with AND without a SIREN; legacy file (no declaration since 2009) flagged fichier_source: import. Excludes Alsace-Moselle (local law).

Extract every link from a public page for crawling agents: de-duplicated absolute URLs with anchor text, internal/external counts, declared feeds and a sitemap hint.

Extract a public HTTP(S) page into JSON: title, description, JSON-LD, Open Graph, headings, links, and AI-readiness signals. No JavaScript; 12-second timeout; 3 MB cap. Paid JSON keeps requestedUrl, finalUrl, status, sourceOk, error, and capture limits. Default excerpt 1200. Optional textExcerptLimitChars 1-40000 is rejected before payment; price unchanged. Not the full page. Use /read for Markdown.

Scrape a public webpage and extract clean readable text. Use this web scraping endpoint when an AI agent needs page content for summarization, research, retrieval, content extraction, indexing, or downstream analysis without parsing raw HTML.

Read one known URL: the main article content as clean markdown with title, byline, excerpt and word count, boilerplate removed. Use it when an agent already has a URL and needs the text; for JavaScript-rendered pages that return an empty shell, use a browser render instead.

Search Obelisk's curated spy ad catalog when you need competitor creative examples by keyword, brand, or platform. Returns JSON ad cards. Use limit=1 for a cheap first call.

Web scraper, URL to Markdown. Default tool for reading ONE web page whose URL you have: returns clean Markdown (title, meta description, main content with headings, lists and links). 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 a whole site site-crawl, and if you have a question but no URL search-read.

What is the web saying right now? Live search results condensed into clean text for agent reasoning — answers beyond any model's training cutoff. Google-grade when the node's search provider is configured.

+2 more from Losbeto Market Intelligence

Keenable page fetch for AI agents: the page at a URL as clean markdown with title and description. Pay per request, no API key.

+1 more from Keenable

Convert any webpage URL into clean, ad-free Markdown text optimized for LLM context windows. Paid in USDC on Base.

Extract PDF/CSV/XLS/XLSX/ZIP/JSON/XML links from static public HTML by suffix or download filename. Resolve relative/base links and deduplicate. Limits: 500 links, 8s, 5 redirects, 2 MiB. No JavaScript or file downloads; existence, MIME, size and file safety are unverified. Empty results are valid. Base mainnet USDC

+8 more from Forest Web

Strip all HTML tags and return plain text. Preserves block-level structure (paragraphs and headings become newline-separated). Faster and more predictable than running extract on a raw HTML string when you already have it.