13 Services from agentreader.dev

Fetches any web page URL and returns the main article content as clean, LLM-ready markdown with boilerplate removed

Extracts structured JSON from any web page, HTML, or text by applying a caller-supplied JSON Schema, powered by Claude with guaranteed schema conformance.

Screens a person, entity, vessel name or crypto address against OFAC SDN and Consolidated sanctions lists, returning a verdict with scored fuzzy matches and full provenance.

Extracts full plain text, page count, and word count from a PDF at a given URL, handling files up to 25 MB.

Performs DNS lookups via Cloudflare DoH for any domain, returning structured JSON answers with TTLs for record types A, AAAA, CNAME, MX, NS, TXT, SOA, SRV, CAA, and PTR.

AI-powered summarization of any web page, raw text, or HTML into a dense, factual summary preserving key numbers, names, and conclusions

Extracts structured metadata from any web page including title, description, canonical URL, Open Graph/Twitter card tags, favicons, JSON-LD types, language, and headings.

Fetches and parses an XML sitemap or sitemap index URL into structured JSON, returning up to 5000 URLs with lastmod and priority metadata, or the list of child sitemaps for index files.

Fetches and parses any RSS, Atom, or RDF feed URL into normalized JSON with feed metadata and up to 100 items including title, link, publish date, author, summary, and categories.

Returns the complete per-check trust history for a specific x402 resource URL, including delivery rate, response validity, latency, and price stability based on real paid test purchases.

Extracts all hyperlinks from a web page as structured JSON, including absolute URL, anchor text, internal/external classification, and nofollow flag, up to 2000 unique links.

Converts raw HTML strings into clean, LLM-ready markdown by stripping scripts, styles, and boilerplate

Render any web page in a real headless browser and return a PNG screenshot with configurable viewport and full-page capture support