other

HUD Fair Market Rents (FMR) for a US county or state — HUD’s annual gross-rent estimate (rent + utilities) by bedroom size (efficiency through 4-bedroom), the basis for Housing Choice Voucher payment standards and other HUD programs. Look up by 5-digit county FIPS (returns the county/metro rents, broken out per ZIP where HUD publishes Small Area FMRs) or by 2-letter state (returns every metro area + county). Optional year (defaults to latest). Source: HUD USER FMR API (US public domain).

NFL players from balldontlie — search by name and page through results. Each player: id, name, position, height, weight, jersey number, college, experience, age, and current team. Cursor-paginated (pass meta.cursor as cursor to continue).

Curated XBRL financial metrics for a US public company by stock ticker. Pulls SEC EDGAR's companyfacts JSON (per-CIK XBRL filings) and extracts a top-line set of ~15 financial metrics with their most recent annual + quarterly values. Each metric returns: end date, start date (or null for balance-sheet snapshots), value, fiscal year/period, originating form (10-K/10-Q), and filed date. Available metric keys (pass any comma-separated subset via the metrics param, or omit to get all): revenue, grossProfit, operatingIncome, netIncome, eps, epsDiluted, rdExpense, totalAssets, totalLiabilities, stockholdersEquity, cash, longTermDebt, operatingCashFlow, capex, sharesOutstanding. Backed by SEC.gov; underlying data is public-domain US government records.

Sports prediction markets across Polymarket and Kalshi in one call — game lines, futures, and props (NFL/NBA/MLB/NHL/soccer/tennis/etc). Optionally narrow with league (a tag/category keyword, e.g. nfl, soccer, world-cup) and cap with limit. Each hit is tagged with its venue and returns the question, live YES/NO price (implied probability), USD volume, close date, and the venue URL. Read-only, keyless.

Search US federal court dockets — civil and criminal — from the RECAP/PACER archive. Full-text q (case name, party, e.g. "United States v. Bankman-Fried"), optional court (CourtListener court id like "cand", "nysd", "ca9"), filedAfter/filedBefore (YYYY-MM-DD), page. Or pass docketNumber (+ court) for exact lookup. Each docket: id, case name, court, docket number, date filed/terminated, nature of suit, assigned judge, public docket URL. Criminal-case research, litigation monitoring, KYC/due-diligence. Sibling endpoints: /api/law/case-search (opinions full-text), /api/law/opinion (full opinion text).

Strait of Hormuz flag rollup: the flag states of the live-AIS vessel population ranked by vessel count, each with a per-flag sanctioned tally, plus distinct-flag count and sanctioned share. Flags are derived best-effort from the MMSI MID (ITU-T M.585). Quality-gated on live AIS. Operators and inbound/outbound direction are omitted, not faked: no operator field is stored and transit direction is not tracked per vessel.

Check a watch condition by ID, returning whether it triggered and updating the caller-specific baseline.

Check if a domain name is available for registration by querying RDAP and DNS — pass a bare name (e.g. mybrand) to sweep it across 10 popular TLDs simultaneously, or a full domain (e.g. mybrand.com) to check that single domain — returns registration status, expiry date if registered, and available/taken TLD lists so agents can find the best domain for a brand or project.

Conform messy or inconsistent JSON to a target schema using Claude Haiku — renames keys, coerces types (string→number, "true"→boolean, etc.), and fills missing fields with null, returning JSON that matches the exact shape the caller specified so agents can normalize data from varied sources into one consistent structure.

Moderate text content using Claude Haiku — flags categories like harassment, hate, sexual content, violence, self-harm, and spam with per-category severity and an overall allow/flag/block recommendation, so agents can screen user-generated content before publishing or storing it.

Moderate text content using Claude Haiku — flags categories like harassment, hate, sexual content, violence, self-harm, and spam with per-category severity and an overall allow/flag/block recommendation, so agents can screen user-generated content before publishing or storing it.

Extract named entities from text using Claude Haiku — people, organizations, locations, dates, emails, URLs, money amounts, and products — returned as structured typed arrays so agents can pull structured signals out of unstructured text in one call.

Translate structured content — JSON, HTML, Markdown, templates, UI strings — without breaking structure. Preserves keys, tags, markdown, URLs, emails, variables, placeholders, code blocks, and brand names, honors a caller glossary, and validates that no placeholder was dropped, so agents can localize app content safely.

Check if a domain name is available for registration by querying RDAP and DNS — returns registration status, whether it's taken or free, expiry date if registered, and availability of the same name across 10 popular TLDs simultaneously so agents can find the best domain for a brand or project.

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.

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.

Conform messy or inconsistent JSON to a target schema using Claude Haiku — renames keys, coerces types (string→number, "true"→boolean, etc.), and fills missing fields with null, returning JSON that matches the exact shape the caller specified so agents can normalize data from varied sources into one consistent structure.

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.

China A-share single-stock money-flow: main-force (institutional) net inflow over recent sessions, with net amount, main-force ratio and daily breakdown. The 'is smart money buying this stock' check Chinese retail investors run before chasing. A股个股主力资金流：查任意A股近N日主力净流入、净额、主力占比，散户追涨前先看主力在不在买。A株個別銘柄の資金フロー。Flujo de capital por accion del mercado A.

Determine a domain's age from registration data and archival history — tries RDAP, then port-43 WHOIS, then a Wayback-based estimate (age_source: rdap | whois | wayback_estimate | null), returning creation date, age in years, first Wayback Machine capture, total archived snapshots, and a maturity signal so agents can assess domain trustworthiness and detect freshly registered domains used for fraud or phishing — including .io and other TLDs without public RDAP.

Fetch public metadata for any GitHub repository — stars, forks, open issues, language breakdown, license, contributors, last commit date, topics, and an activity/health score — so agents can evaluate dependencies, research projects, and assess open source health without the GitHub API complexity. Pass repo as ?repo=owner/repo (GET) or {"repo":"owner/repo"} (POST).

Estimate the market value tier of a domain name using transparent heuristics — length, TLD premium, dictionary-word presence, pronounceability, keyword value, and numeric/hyphen penalties — returns a value tier and 0-100 quality score so agents can triage domain portfolios and prioritize acquisitions without a paid appraisal service.

Determine a domain's age from registration data and archival history — returns creation date, age in years, first Wayback Machine capture, total archived snapshots, and a maturity signal so agents can assess domain trustworthiness and detect freshly registered domains used for fraud or phishing.

Estimate the market value tier of a domain name using transparent heuristics — length, TLD premium, dictionary-word presence, pronounceability, keyword value, and numeric/hyphen penalties — returns a value tier and 0-100 quality score so agents can triage domain portfolios and prioritize acquisitions without a paid appraisal service.