information-retrieval

Resolve a domain's TXT records (SPF, DKIM, verification strings) via keyless Cloudflare DNS-over-HTTPS. For agents auditing email auth and domain ownership records.

Returns geolocation and network information for a given IP address.

Structured Wikidata entity data by Q-id via the Wikidata API, no key. Returns labels, descriptions, aliases, claims, and sitelinks. For agents resolving entities to canonical facts and cross-language labels.

Fetch dbSNP variant summary by rsID number: alleles and global minor allele frequencies across reference studies (1000 Genomes, ExAC, etc.). Keyless NCBI E-utilities. For agents querying SNP frequency data.

Resolve a domain's MX (mail server) records via keyless Google DNS-over-HTTPS. Returns priority and mail host data. For agents checking email routing and deliverability.

Investiga un tema en la web y devuelve una síntesis con fuentes citadas (títulos + URLs). Úsalo para research pagado por consulta cuando un agente necesita información actual con fuentes. input=tema a investigar.

Genera FAQ (preguntas + respuestas) de un texto/tema. Para docs/soporte. input=texto o tema.

Returns a full decision journal entry — directional_bias, calibrated_confidence, anomaly_score, and agreement_score — plus a decision_id, combining signal, anomaly, and calibration checks into one auditable record for agent decision pipelines.

Generate deterministic related SEO query variants

Search PubMed biomedical literature by term; returns matching PMIDs and total count. Keyless NCBI E-utilities. For agents discovering biomedical papers and citation IDs.

Convierte un texto en un vector (embedding) para búsqueda semántica, RAG, clustering o memoria. El bloque base que todo agente de IA necesita. Alto volumen. input=texto.

Query verified x402 & agent-economy intel: facilitator quirks (PayAI v1/v2, EIP-3009 gas-free), discovery registries (bazaar index-on-settle, no-KYC), USDC-on-Base gotchas, live agent income channels. Returns ranked fact snippets for agents building on x402.

Social mindshare ranking.

Clasifica un texto por tema/categoría. Alto volumen para enrutar/etiquetar. input=texto.

Rankea una lista de documentos por su cercanía de SIGNIFICADO a una consulta (similitud coseno sobre embeddings). RAG listo para usar, sin que el agente monte su propia base vectorial. input='consulta || documento 1 || documento 2 || ...' (separados por ||).

Retrieves advertising demand data based on user intent signals.

Returns news articles or updates.

Breaks down any text into character, word, and sentence counts, estimated LLM token count, and reading time, computed instantly with nothing stored. Useful for context-budget checks before an API call, content-length validation, and editorial word-count requirements.

Looks up normalized package metadata from the Python Package Index, version, dependencies, license, homepage, and yank/deprecation status, trimmed down from the much larger raw index response. For agents auditing or generating requirements files before running pip install.

Ask a question about War and Peace and get back the most relevant passages from the book itself, with chapter and location citations. Retrieval only — full-text search, not a generated summary or answer. No license, no API key required.

Ask a question about Crime and Punishment and get back the most relevant passages from the book itself, with chapter and location citations. Retrieval only — full-text search, not a generated summary or answer. No license, no API key required.

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

URL expansion API: safely follow a short or redirecting link (up to 6 hops, SSRF-guarded) and return the final URL, complete redirect chain, and final HTTP status — see where a link REALLY goes before touching it. For link-safety checks, affiliate auditing, and phishing triage.

Look up any topic on the web's largest collaboratively-edited encyclopedia and get back the title, short description, lead summary paragraph, thumbnail image, and canonical article URL as structured JSON. For entity enrichment, fact-checking, and research agents that need a grounded summary instead of a hallucinated one. Cached 24 hours, attribution included.