information-retrieval

Fetch one URL and return clean article Markdown without navigation, ads or cookie banners.

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.

Fetch a URL and grade its HTTP security headers (HSTS, CSP, X-Frame-Options, etc.)

Returns computed results and answers to queries processed through a computational knowledge engine.

Retrieves customer reviews for a specified location.

Provides simplified computational answers and mathematical results for queries.

Computed repo maintenance/abandonment verdict (score + reasoning) from live GitHub data

Search a governed snapshot of implemented, validated Polymathica PDE and scientific-computing solvers. Returns validation versions, bounded evidence locations, implementation modules and provenance without claiming a fresh solver execution.

Return a bounded, source-labelled set of public-domain Bible passages and neutral reflection prompts for one of six predefined topics.

Return bounded ranked OpenBible.info cross-reference identifiers with displayed text resolved only from BSB or WEB.

Fetch a PDF by URL and return its text as Markdown-ish plain text, page by page

A full Markdown report on a topic you specify, researched on the live web at the time of the request, with every source linked. As long as the topic needs, never cut short. Typically 2-4 minutes; allow 360 s before giving up. POST {"topic":"..."}.

Compare a bounded passage in the public-domain BSB and WEB without blending or interpreting the source texts.

Checks whether a domain appears technically configured for email delivery, from direct public DNS records only: MX presence, SPF presence, DMARC presence and policy, and an optional DKIM selector check. Queries DNS over HTTPS against a public resolver -- no test emails sent, no mailbox existence verification, no personal data, no leaked-email databases, no proprietary deliverability dataset.

Check a specific dataset, paper, repository, or model URL against the indexed open-science corpus and receive a conservative, source-linked commercial-use and redistribution status. Never infers permission from an absent or ambiguous licence -- returns unknown rather than guessing.

Search live drug and medicine metadata from the U.S. FDA's openFDA API: brand/generic name, active ingredients with strength, dosage form, route, manufacturer/labeler, product type, marketing status, and NDC codes -- plus an optional short (~400 character) label excerpt (purpose or indications only) and an optional recall/enforcement flag. Composed entirely from openFDA's NDC Directory, Drug Label, and Drug Enforcement APIs, all public domain (CC0 1.0 Universal). Never returns full label section

Resolve a person from strong identifiers through People Data Labs and return signed, limitation-aware evidence

Find literal query evidence across bounded public news sources with timestamps

Search a bounded Crossref snapshot for research-paper DOI metadata with stable DOI links, source provenance and conservative linked-work rights fields. Returns metadata only and excludes abstracts and full text.

Find source-linked scientific datasets by topic. Returns structured metadata pointers, declared licence fields, provenance and freshness without redistributing dataset files.

Find source-linked scientific machine-learning model records by topic. Returns metadata and provenance pointers only; model weights are not downloaded or resold, and missing licence evidence remains unknown.

Find source-linked scientific software and repositories by topic. Returns metadata, declared licence evidence and provenance pointers without downloading or reselling repository contents.

Search U.S. federal regulatory documents -- final rules, proposed rules, notices, and presidential documents -- by keyword, document type, issuing agency, and publication date range. The only source used is the Federal Register's own public API (federalregister.gov), published by the National Archives and Records Administration's Office of the Federal Register.

Static scan of YOUR public GitHub repo: TODO/FIXME debt, oversized files, stray console.log, possible hardcoded secrets (heuristic), README/.gitignore/LICENSE. Deterministic, no AI. POST {"repo":"https://github.com/owner/name"}. Repos over 25 MB are refused before payment.