Summarize any text or web page into a concise summary plus key bullet points using Claude Haiku — accepts raw text or a URL (which it fetches and extracts), enforces an input cap, and returns a clean structured summary so agents can compress documents and articles in one call.

Turn unstructured text into structured JSON matching a caller-supplied schema using Claude Haiku — the agent declares the fields and types it wants, and gets back populated JSON with values pulled from the text and coerced to the right types, so agents can structure any prose into the exact shape their pipeline expects.

Compare registration, renewal, and transfer prices for a TLD across major registrars, or for a single domain name across many TLDs — returns sorted reference pricing so agents can find the cheapest place to register, budget domain acquisitions, and spot predatory renewal markups without checking each registrar manually.

Translate up to 500 words between languages using Claude Haiku — auto-detects source language, supports 30+ target languages, preserves formatting, and returns the translation with detected source so agents can localize short content cheaply. For longer text use /translate/long.

Generate common typo and look-alike variations of a domain and check which are already registered — catches character swaps, omissions, additions, homoglyphs, and alternate TLDs so agents can detect typosquatting and brand-impersonation domains targeting a company.

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.

Check username availability across 20+ social platforms and developer sites simultaneously — returns which platforms have a profile registered under that handle so agents can find people, verify identities, scout brand handles, or check name availability before registration.

Extract article / main content from any URL or PDF to clean, LLM-ready Markdown (web scraper / reader / html-to-markdown) — strips scripts, nav, ads, and boilerplate while preserving headings, links, lists, tables, code blocks, and blockquotes; extracts the text layer from PDFs. Returns Markdown body, title, word count, and a quality grade so agents can read articles and documents without a browser or paid scraping service.

Look up domain registration metadata via RDAP — returns registrar, creation/expiry dates, nameservers, status flags, and an actionability score so agents can assess domain trustworthiness or availability risk.