Search & web

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.

Fetch a URL and return clean, token-efficient markdown

Long-term rental listings in Da Nang, Vietnam: search by district, property type, bedrooms and monthly price in VND. Use when an agent needs current rentals with prices, districts and listing URLs (contacts are on the listing page). One payment of 0.01 USDC buys 5000 calls on Base, Solana, Arc or Stellar.

+1 more from helprentdanang.com

Search entities. Find a person, company, or knowledge graph entity by free-text query — a name, partial name, nickname, stock ticker, @handle, or website domain.

Scrape a URL and return clean Markdown (via Firecrawl). Priced above Firecrawl's own per-scrape cost.

Google Trends interest by region for a keyword. Returns the subregional breakdown of Google Trends search interest inside a country - by state, province, or region - each ranked 0-100 relative to the strongest region. For regional demand mapping, geo targeting, and finding where a keyword over-indexes before spending on it.

Stack Overflow Q&A. Programming question and answer search with scores, accepted-answer flags, tags, and answer bodies via the Stack Exchange API.

Residential proxy fetch (up to 2MB). Returns HTTP 200 with the target body; read X-Target-Status for the origin status. Billed for the forwarded request, not for a 2xx origin response. For larger responses use /v1/proxy/large; at >17 requests a session pass is cheaper.

+1 more from AproxPay

Search US drug products by NDC, brand, generic name, ingredient, manufacturer, dosage form, route, source, or identifier.

Returns clean, normalized datasets of AI model benchmarks, pricing, leaderboard scores, and Ethereum EIPs, parsed from sources that are costly to scrape.

+1 more from VoidFeed

Fetch any public web page and return clean, readable Markdown with navigation, ads, and boilerplate stripped. For agents that need article text or documentation as Markdown.

Read the mandatory public disclosure of one domain and return company, postal address, e-mail, phone, VAT and register data with a source for every value.

+2 more from fetchwerk Web Extraction

Quick extractive summary of any web page: fetch the URL, extract the main article, and return the key sentences (TextRank) instead of the full text. For agents that want the gist of a page, not a full scrape. No AI — fast and deterministic. Want an abstractive AI rewrite, or to summarize a PDF/DOCX or your own text? POST /api/summarize-text ($0.01).

+4 more from WebberSites x402 Data API

Book a paid Resy reservation for the authenticated user using a slot config token.

Extract emails, URLs, money values, dates, and candidate capitalized phrases using transparent deterministic patterns.

+1 more from DopamineDesk AI Marketplace

Fetch and parse a domain's robots.txt file — returns all crawl rules by user-agent, sitemap URLs, crawl delay settings, and checks whether a specific path is allowed or blocked for any bot — so agents can respect crawl policies and locate sitemaps before scraping.

+21 more from NetIntel

Quick factual lookup: a plain-language summary (abstract) plus up to 5 relevant links from Wikipedia. Best for people, places, concepts, history and science. Returns links, not page content: to get the content of the top results in the same call, use search-read. Not for breaking news: use news-search. Params: query (required).

x402 endpoint check: validate an x402 endpoint and audit its Bazaar listing before you pay for it or list it. One unpaid probe (never pays the target) grades the 402 challenge, schemas, examples, name, tags and latency, and adds Coinbase's validator verdict, the live Bazaar listing (30-day calls, payers, stale metadata) and search rank for its own name and tags. Returns score, grade and prioritized fixes. 0.005 USDC/call; failed calls are free.

Summarize a URL, raw text or HTML at the length you request - short, medium or long - with the source noted. Neutral and factual, no invented facts. Try GET /summarize/sample. Part of the AgentIndex content kit (pdf, web-read, extract, summarize, detect-language) - see GET /capabilities.

Extract structured data from a URL or raw text into strict JSON matching a schema you provide. Fields the content doesn't support come back null - never an invented or approximate value, and an unmatchable schema returns an explicit error. Try GET /extract/sample. Part of the AgentIndex content kit (pdf, web-read, extract, summarize, detect-language) - see GET /capabilities.

Live image search: ranked image results (title, source page, image URL, thumbnail URL, dimensions) from an independent search index as clean JSON. Strict safe-search is on by default.

Skim: JS-rendered reader — full headless browser render for SPAs and JS-gated pages; clean markdown ~4x smaller than raw HTML.

+1 more from skim402.com

Crawl a website from a starting URL and return each page as clean markdown: breadth-first over internal links, bounded by page count and depth, honouring robots.txt, with per-page title, status, depth and outbound links. Use it when an agent needs a whole section of a site rather than one known page.