Web & Data

Translate many independent strings in one request — each with a caller ID preserved in the response — with per-item status, glossary and tone support, and partial success so one bad item never fails the batch, so agents can localize whole string tables in a single call.

Fetch a URL and detect the full technology stack from HTTP response headers, HTML meta tags, cookies, and script patterns — returns CMS, framework, CDN, server, analytics, and security tool detections so agents can profile any web target without a browser.

Parse and validate any phone number in any format, identify its country, line type (mobile/landline/VOIP/toll-free/premium), carrier region, and return all standard format variants — so agents can validate contacts, normalize phone data, and classify line types without a paid telecom API.

Fetch any article or web page and extract clean readable text stripped of navigation, ads, and boilerplate — returns the main content body, word count, estimated reading time, detected language, and key sentences so agents can read the web without a browser or third-party scraping service.

Event extraction / event parsing — turn any caption, announcement, listing, or page text into a normalized calendar event via Claude Haiku. Resolves relative dates ("this Saturday 7pm") against post time + timezone, handles all-day/multi-day, and returns title, start/end, venue, address, city, price, organizer, url. Purpose-built for structured event data (no schema to define — unlike generic extractors); pairs with /event-classify (cheap filter) and /calendar/ics (publish step).

Query a domain's DNS record across 10 geographically distributed public resolvers simultaneously — returns what each resolver sees, whether results are consistent, propagation percentage, and a readiness score so agents can confirm DNS changes have fully propagated globally.

One call combines domain availability, heuristic value appraisal, and TLD pricing into a single acquisition brief — tells an agent whether a name is available, what it's worth, and what it costs across TLDs, concurrently and with graceful partial-failure handling.

Extract structured data from resume/CV text using Claude Haiku — returns name, contact info, skills, work experience, and education as clean JSON arrays so agents can automate applicant screening, candidate databases, and recruiting workflows from raw resume text.

One call vets a URL end to end — traces its full redirect chain, checks it against malware/phishing databases, audits its security headers, and inspects its SSL certificate — concurrent with graceful partial-failure handling, so agents get a complete safety verdict before following a link.

Resolves all DNS record types for a domain, parses SPF/DKIM/DMARC from TXT records, and compares A records across Google/Cloudflare/Quad9 resolvers for propagation consistency.

Query a domain's DNS record across 10 geographically distributed public resolvers simultaneously — returns what each resolver sees, whether results are consistent, propagation percentage, and a readiness score so agents can confirm DNS changes have fully propagated globally.

Extract structured data from resume/CV text using Claude Haiku — returns name, contact info, skills, work experience, and education as clean JSON arrays so agents can automate applicant screening, candidate databases, and recruiting workflows from raw resume text.

One call vets a URL end to end — traces its full redirect chain, checks it against malware/phishing databases, audits its security headers, and inspects its SSL certificate — concurrent with graceful partial-failure handling, so agents get a complete safety verdict before following a link.

Search Reloadly's gift card catalog (300+ brands, 14,000+ products/denominations across countries). Returns each product's id, brand, country, denomination range or fixed amounts, and sender fee/discount — everything needed to build a POST /api/giftcard/quote call.

Live grid carbon intensity, deterministic. Answers "how clean is the grid right now", "gCO2 per kWh in Germany", "cleanest hour to run a job today". Current intensity + forward curve (to 48h) + cleanest and dirtiest slots, from NESO (GB national + 14 DNO regions) and energy-charts/Fraunhofer ISE (DE FR NL BE AT ES IT NO). No LLM, no key. Pair with /api/energy/compute-window for full job scheduling.

Fast real-time news scan across 44+ curated domains (configs/search_domain_profiles.json), every item source-attributed. Settlement proof: ProofOfSettledOutcome (kind 30120, data/proof_settled_outcomes.jsonl). The quick-scan tier below research.topic-deep-researcher's slower, citation-grade report.

List your prepaid cards (status, last4, balance — never full card numbers; those are per-card via GET /cards/:id).

Fetch a repository's README, decoded to UTF-8 text (name, path, size, content, URL). Optionally pin to a branch/tag/sha via ref. Useful for summarizing or indexing a project. Read-only; no caller key needed.

Structured extraction: give a JSON Schema plus a URL or raw text, get back JSON matching the schema.

Look up an ISO 639 language. Pass code in any form — 639-1 (en), 639-2/B (ger) or 639-2/T (deu) — or name (English, partial match). Returns the English name and all sibling codes (alpha-2, alpha3-B, alpha3-T), so you can normalize a messy language tag to canonical ISO identifiers and resolve the bibliographic-vs-terminological alpha-3 split (e.g. German = de / deu / ger). Bundled authoritative ISO 639 data.

Full-text search across all of Hacker News (via the Algolia HN API). Search stories or comments by keyword, sorted by relevance or by date (newest first). Filter by tags (story/comment/ask_hn/show_hn/poll) and by author. Each hit: title, URL, author, points, comment count, story/comment text, created time, and canonical HN URL. Net-new vs news.hn-top (curated feeds) and news.search (general news).

Look up country metadata via REST Countries. Pass alpha2 (2-letter ISO 3166-1), alpha3 (3-letter), or name (with optional fullText=true for exact match). Returns common + official name, ISO codes, region + subregion, independence + UN-member flags, capital(s), population, area km², landlocked flag, neighboring borders (alpha-3), timezones, currencies (code → name + symbol), languages, calling code, flag emoji + SVG/PNG URLs, lat/lng coordinates, Google Maps + OSM URLs, driving side, top-level domains.

Look up an IETF RFC by number. Pass number as RFC2616, 2616, or the integer 2616. Returns the RFC title, authors, publication date, status (e.g. INTERNET STANDARD, PROPOSED STANDARD, DRAFT STANDARD, INFORMATIONAL, EXPERIMENTAL, HISTORIC, BEST CURRENT PRACTICE), stream (IETF/IAB/IRTF/Independent/Legacy), DOI, canonical rfc-editor.org URL, and the full standards relationship chain: which RFCs this one obsoletes / is obsoleted by, and which it updates / is updated by. Authoritative data from the IETF/RFC Editor index. Use this to resolve whether a spec is current or superseded before relying on it.

Hacker News feed of items. Pass kind = top (default) | new | best | ask | show | job to pick the feed. Returns each item's id, type, author, time (unix + ISO), title, URL, text (for self-posts), score, descendant + kid counts, parent (for comments), dead/deleted flags, and canonical news.ycombinator.com URL. Default limit = 30, max 100. Useful for tech-sentiment + topic tracking.