btc-tx

A composite US real-estate market profile for one geography. Fuses the FHFA House Price Index momentum, Census ACS demographics, housing, income, tenure and vacancy, national housing context, and Fair Market Rents into one cited JSON with computed derivatives such as gross rental yield and affordability. Aggregate market tier, not a per address valuation.

The FHFA House Price Index for a geography: the current index level plus year over year, quarter over quarter and five year growth, with momentum flags and a short history. State and metro CBSA levels are covered directly; county and ZIP resolve to the state level index. Public domain, US only.

Rental market indicators for a geography: HUD Fair Market Rents by bedroom count when a HUD token is configured, plus the Census ACS median gross rent as context. Falls back to the ACS rent when HUD is not configured. Aggregate market tier, US only.

Compare several US geographies on one real-estate metric: price momentum, gross rental yield, price to income, median home value, median gross rent or median household income. Returns a ranking plus rank, highest and lowest, spread and mean signals.

Check whether a password has appeared in known data breaches, using k-anonymity: the password is hashed locally and only a 5-character hash prefix is sent upstream, so the plaintext is never transmitted, logged or stored. Accepts a password, a SHA-1 hash or an NTLM hash. Returns compromised, breach_count and the hash prefix. Credential-exposure indicators, not a guarantee.

List the known public data breaches that affected a domain, from the Have I Been Pwned breach catalogue. Returns normalized breach metadata (name, date, account count, data classes, stealer-log and verified flags) plus a summary. This is which known breaches touched the domain, not whether a specific account is compromised. Breach indicators, not a guarantee.

Composite account-takeover risk score (0-100) fusing a privacy-preserving password exposure check with a domain's known breach history. The password is hashed locally (k-anonymity, never transmitted). Returns ato_risk_score, a category, per-signal reasons and the raw signals so the agent can re-rank. Risk indicators, not a guarantee.

Vulnerability intelligence for a single CVE id. Fuses NVD (CVSS base score and vector, CWE, patch links), CISA KEV known-exploited status, EPSS exploitation probability and OSV.dev affected and fixed versions into one cited JSON with a deterministic patch-priority score. Risk indicators, not advice.

Vulnerability scan for a software package by ecosystem, name and version, or by package-URL (purl). Queries OSV.dev for known advisories, collects their CVE ids and enriches them with NVD CVSS, CISA KEV and EPSS, then returns a prioritized list of advisories with exact fixed versions. Risk indicators, not advice.

Phishing/trust verdict for a website domain before an agent transacts with an unfamiliar merchant. Fuses registration age (RDAP), DNS/mail posture (SPF, DMARC, DNSSEC), TLS validity, Certificate Transparency history and a typosquat/homoglyph analysis into a composite trust score 0-100, a category (trusted / caution / untrusted / unknown), per-dimension flags and reasons. Trust indicators, not a gu

Pure-compute typosquat and homoglyph check on a hostname: edit-distance to a curated brand list, look-alike character normalization, brand-in-subdomain lures, punycode/IDN, abused free-hosting suffixes and throwaway TLDs. Returns is_typosquat plus the nearest brand, edit distance and reasons. No network — instant, cheap.

Clinical safety profile for a drug by brand, generic or active-ingredient name or NDC. Fuses FDA identity and approval status, key label sections, an adverse-event summary and a deterministic severity indicator into one cited JSON. Informational, not medical advice.

Adverse-event summary for a drug from the FDA FAERS database by name. Returns the top reported reactions, the serious and death-flagged fractions and a demographic breakdown as aggregate counts. Informational, not medical advice.

Key FDA structured-product-label sections for a drug by name: boxed warning, indications, dosing, contraindications, warnings, drug interactions and pregnancy. Informational, not medical advice.

Drug-interactions label section for a drug by name, with an optional check of whether the label mentions a second drug. A label-text heuristic, informational, not medical advice.

Adverse-event summary for a medical-device brand from the FDA MAUDE database. Returns counts of malfunctions, injuries and deaths by event type. Informational, not medical advice.

Current FDA drug-shortage records for a generic drug name: status, therapeutic category, dosage form, company and dates. Informational, not medical advice.

One macroeconomic or development indicator for one or more countries as a cited time-series. Fuses free authoritative sources (World Bank, IMF) and tags every value with its source, source code, year and country ISO3. Accepts a canonical indicator key or a raw World Bank code.

A curated headline basket of key macroeconomic and development indicators for one country: GDP, GDP per capita, growth, inflation, unemployment, population, government debt, current account, life expectancy and CO2 per capita. Latest value plus short history, each value cited to its source.

One indicator compared across several countries: the latest value for each plus computed signals — rank, highest and lowest, spread and mean. Each value is cited to its source.

IMF World Economic Outlook forecasts for a country: real GDP growth, inflation, nominal GDP, GDP per capita, government debt, current account and unemployment, including projected future years. Values are cited to the IMF WEO.

Detect structured PII in a text blob: emails, phones, credit cards, bank and tax ids, IP and MAC addresses, crypto addresses, dates of birth, geo coordinates and secrets. Returns findings with a confidence score plus a compliance summary. No transformed text. Structured PII indicators, not legal advice.

Detect and transform structured PII in a text blob. Returns the sanitized text plus a findings report. Modes: redact, mask, hash, or reversible tokenize (the token map is returned in the response — nothing is stored). Optional per-type mode overrides and an allow-list. Structured PII indicators, not legal advice.

Resolve one research paper and fuse its metadata across OpenAlex, Crossref, Unpaywall and Semantic Scholar into a single cited JSON. Give a doi, arxiv, pmid, pmcid, openalex_id or title and get canonical metadata, authors with ORCID and affiliations, venue, citation counts, an open-access PDF link and a full id crosswalk.

Search the scholarly literature by keyword or topic and get a ranked list of works with core metadata. Optional filters for year range, open-access only, concept and institution. Powered by OpenAlex. A cheap first step before /scholar/paper.

Citation graph of a paper: the works it references (outgoing) and the works that cite it (incoming), each as normalized records, plus the Semantic Scholar influential-citation count. Give a doi, arxiv, pmid, openalex_id or title. Ideal for literature review and prior-art mapping.

Disambiguate a researcher and return their profile: works count, citation count, h-index, institutions with ROR, top concepts and top works. Give an orcid for a resolved profile, or a name for ranked candidates. Distinct people are never merged.

Locate a free open-access PDF for a DOI. Returns whether an open-access copy exists and the best PDF link with its license, version and host type, from Unpaywall and OpenAlex. A cheap, focused open-access locator.

Pre-sign safety verdict for an off-chain EIP-712 signature (EIP-2612, Permit2, EIP-3009). Decodes what it authorizes (spender, token, amount, deadline), checks domain-spoof, approval-hygiene and scam-blocklist, returns allow, warn or block plus a 0-100 risk. Risk indicators, not advice.

Pre-sign safety verdict for a raw EVM transaction. Decodes the calldata against a known-signature registry, shows known-pattern effects (approval delta, transfer target), dry-runs eth_call for revert, checks scam-blocklist and approval-hygiene, and returns allow, warn or block plus a 0-100 risk. Risk indicators, not advice.

Recent global news articles from the GDELT Project by topic, country, entity or theme, normalized to title, link-back url, domain, source-country, language and ISO timestamp — plus coverage breakdowns (top source-countries, top domains, languages, count) derived from the same result. One call instead of querying and parsing GDELT yourself.

Native multilingual tone/sentiment for a topic from the GDELT Project: a tone histogram (emotional bins with example articles), a coverage-weighted average tone and label, the modal bin, and an optional tone trend over time. GDELT's own cross-language tone (a differentiator over English-only lexicon scoring).

Fusion intelligence for a world topic in ONE call: recent articles + coverage breakdowns (top source-countries, domains, languages) + a tone trend with the current average tone and direction — all normalized and cited. Saves 4-5 separate GDELT calls and their parsing. Research latency, not real-time trading.

Balance and unspent outputs for a Bitcoin address. Returns confirmed and mempool balance, funded and spent totals, transaction count and a capped UTXO set for a legacy, p2sh or bech32 address. Informational, not advice.

Decoded Bitcoin transaction by txid: inputs and outputs, fee, size, weight and virtual size, replace-by-fee flag, and confirmation status with a confirmation count. Informational, not advice.

Bitcoin block metadata by height or hash (or the chain tip when neither is given), fused with the current difficulty-adjustment context, a computed halving countdown and a network hashrate snapshot. Informational, not advice.

US federal income tax estimate for a tax year: taxable income, tax, marginal and effective rate, per-bracket breakdown, with an optional state estimate. Pure computation over your inputs, not tax advice.

US payroll tax estimate: Social Security and Medicare on wages, or self-employment tax, including the additional Medicare surtax. Pure computation over your inputs, not tax advice.

US capital gains tax estimate: long-term 0/15/20 percent rates or short-term ordinary rates, plus the net investment income tax. Pure computation over your inputs, not tax advice.

US take-home paycheck estimate: federal income tax plus payroll tax and an optional state estimate, giving net pay per period and disposable income. Pure computation over your inputs, not tax advice.

Reference tables for a US tax year and filing status: income brackets, standard deduction, FICA constants, and capital-gains breakpoints. Pure lookup, not tax advice.

AI-search visibility (AEO) audit of a website for answer engines and agents. Fetches the target's own public surface and computes a composite visibility score 0-100 with a rating (poor, fair, good, excellent) across six axes: answerability, structured data, AI-crawler access, crawlability, llms.txt readiness and MCP well-known readiness, plus a prioritized list of fixes. Deterministic, no LLM. Vis

Focused check of a site's /llms.txt and /llms-full.txt: presence, size and llmstxt.org structural validity (an H1 title, a blockquote summary, sections of markdown links). Returns a readiness score plus fixes. Cheap sub-check of the full AEO audit.

robots.txt AI-crawler access matrix: for the 2026 cohort of AI and answer-engine crawlers (GPTBot, ChatGPT-User, OAI-SearchBot, ClaudeBot, Claude-User, PerplexityBot, Google-Extended and more) reports allowed, blocked or unlisted per bot, whether the default rule blocks everything, declared sitemaps and a score. One network operation.

Deterministic on-page technical-SEO audit of a single web page. Fetches the page (redirects + response headers) and runs 24 mechanical rules across six categories (indexability, title/meta, headings, structured data, images, i18n/mobile). Returns a 0-100 score, letter grade, per-rule pass/warn/fail checklist with fixes, and an indexability-critical flag. No LLM, no keys.

Delegation-risk verdict for a Solana validator from public on-chain data. Give one of vote (vote-account) or identity (node) pubkey and get a verdict of safe, caution, avoid or not_found, a 0-100 risk score, per-dimension flags, reasons and weighted signals across delinquency, commission, commission-rug history, skip-rate percentile, vote-credit performance, agent version lag and superminority con

Resolve a Solana validator identity pubkey to its vote-account (or the reverse) and optionally get the top-N lowest-risk safe validators by score. Give vote or identity to resolve, or top_n for safe candidates. Cheap first step before validator/vet.

Profile of a DePIN hotspot or gateway from public data. Give network (helium) and an entity or asset key and get owner wallet, subnetworks (IOT, MOBILE), obfuscated location (city, state, country and H3 cell), elevation, gain, onboarding fee and computed flags for asserted location, multi-network and deployment completeness. Each value is cited to its source.

Portfolio of a DePIN operator or investor wallet from public data. Give network (helium) and a Solana wallet pubkey and get the hotspot count, a breakdown by subnetwork, the geographic spread, token balances (HNT, IOT, MOBILE, DC) and computed signals for deployment diversification and concentration. Each value is cited.

Network health and token-economics verdict for a DePIN network from public data. Give network (helium) and get coverage size (IOT and MOBILE node counts), token supply for HNT, IOT, MOBILE and DC read on-chain, the emission and halving context, and a coverage-scale indicator. Each value is cited to its source.