information-retrieval

Fetch any public URL and return the page as clean Markdown for LLM consumption (title, meta description, main content with headings/lists/links preserved). Pass render:true to execute JavaScript in a real browser for SPAs (slower, returns p

Search for factual information via DuckDuckGo + Wikipedia. Returns heading, abstract (plain-language summary), abstract_url, and results (list of relevant links). Best for: people, places, concepts, history, science. NOT for breaking news —

Returns geographic regions within the United States.

SIGNED portable track record of a predictor's live calls: resolved-only decided/correct counts, Wilson 95% lower bound, and a sha256 merkle root content-addressing the exact corpus of signed calls it summarizes (recomputable offline). Records under the min-decided floor carry clears_bar=false. Param: pubkey (64-hex ed25519), query window (30d|90d|all).

Domain registration lookup via RDAP (modern WHOIS). Returns registrar, registrar_url, created_at, updated_at, expires_at, days_until_expiry, name_servers array, status array, and registrant_country. Clean JSON — no raw WHOIS text to parse.

OAuth 2.0 authorization-server metadata (RFC 8414) with OpenID fallback: tries /.well-known/oauth-authorization-server then /.well-known/openid-configuration and returns the issuer, authorization/token/revocation/introspection/device endpoints, grant types, PKCE support, token auth methods, scopes, DPoP and PAR support. Also checks /.well-known/oauth-protected-resource for MCP-style resource metadata. $0.01 per server.

Semantic-version helper: compare two versions (-1/0/1 with which is newer), test whether a version satisfies a range (^, ~, >=, <, x-ranges, hyphen ranges, ||), or sort a comma/space list of versions descending with prerelease handling. Parses major/minor/patch/prerelease/build. $0.01 per operation.

Wikidata entity lookup: the Q-id, label, description, aliases, and key claims (instance of, country, population, inception, coordinates, official website, founder, headquarters) resolved to labels. Structured facts for grounding. $0.01 per lookup.

Provides system health status or real-time operational metrics.

Retrieves a ranked leaderboard of tool execution performance or results.

Fetch a public URL and return its main content as markdown.

Screening completo de sanções internacionais + PEP numa chamada só: OFAC, ONU, União Europeia, Reino Unido, Canadá, Austrália, Suíça, FinCEN, INTERPOL, FBI Most Wanted, Offshore Leaks, PEP e PEP com parentescos (13 consultas). Pra onboarding de cliente/compliance AML. Uso restrito a finalidade legítima; consultas são auditadas.

Company Page

Search a catalogue of free, legally downloadable works: public-domain books (Project Gutenberg), audiobooks (LibriVox), films and texts (Internet Archive collections), growing by tens of thousands of records a day and re-verified daily. Returns matching works with authors, year, language, rights status and direct download links (epub, txt, mp3, video files). Where to get it for free, with the link. $0.01 per search.

Look up domain registration facts via RDAP (registrar, status, dates, nameservers, DNSSEC). Use when you need live registry data and must not guess. Unregistered names return not_found.

The full ranked table: every service we hold probe history for, scored, ordered and tagged with its categories. Cursor-paginated via limit and offset. One purchase, the whole index.

Exports data or configuration from the system in a format suitable for external use or backup.

Title, description, headings and up to 20,000 characters of clean readable text from any public URL. Built for LLM context. Private and local addresses are refused.

Public-Domain Book Search (Project Gutenberg, 75k+ books). Search 75,000+ public-domain books on Project Gutenberg by title or author: book id, title, author, download count and a link to the full-text endpoint.

HTTP status, redirect chain with timings, total response time and security headers present or missing, for any public URL, measured from our server.

Federal Register search by topic, entity, rule, notice, order, or publication term with signed official evidence.

Get a specific technology by ID or name

robots.txt check: fetches the origin's /robots.txt server-side and reports whether a given URL path is allowed or blocked for a user agent, with the matched rule, the robots URL, the HTTP status, a timestamp and a tamper-evident receipt. Query parameters: url (required), user_agent (optional, defaults to *). Only robots.txt is fetched; no crawling. Pair with GET /api/v1/link-map or /api/v1/sitemap to plan an allowed fetch.

Returns a simplified version of brand data containing only essential information: domain, title, colors, logos, and backdrops. This endpoint is optimized for faster responses and reduced data transfer.