All services

FDA food recall enforcement reports, newest first by report date. All filters optional. Each record includes recall number, status (Ongoing/Completed/Terminated/Pending), classification (Class I/II/III), product description, reason for recall, initial-notification mechanism, voluntary-vs-mandated, recalling firm + city/state/country, distribution pattern, and recall + report dates. Backed by OpenFDA's /food/enforcement endpoint; public-domain US government records.

Unified scientific literature search across arXiv (preprints), PubMed (biomedical), and Semantic Scholar (cross-field, with citation counts). Returns a flat array of papers with stable schema: source, sourceId, doi, title, authors, abstract, year, publishedAt, citationCount, url, pdfUrl. Partial failures surface in the errors array rather than failing the whole call. Optional filters: since (YYYY-MM-DD), sources (subset), limit (max 20 per source).

AbuseIPDB subnet (CIDR) check — which IPs inside a network block have been reported for abuse. Pass network as a CIDR (e.g. 118.25.0.0/24; AbuseIPDB supports up to /16 for IPv4, /112 for IPv6). Returns the block metadata (network/netmask/min-max addresses, possible hosts, address-space description) plus reportedAddress: each flagged IP with numReports, abuseConfidenceScore, mostRecentReport, and country. Optional maxAgeInDays (1-365, default 30) and limit. Use to vet a hosting range, score a customer's netblock, or sweep your own allocation.

AbuseIPDB bulk blacklist — the most-reported abusive IPs above a confidence threshold, the canonical fail2ban / firewall block-feed. Returns ipAddress, countryCode, abuseConfidenceScore, and lastReportedAt for each entry, plus the list's generatedAt timestamp. Tune confidenceMinimum (25-100, default 90), limit (1-10000, default 100), ipVersion (4 or 6), and onlyCountries / exceptCountries (comma-separated ISO-2). Live crowd-sourced threat feed for populating drop lists, WAF rules, and edge blocklists.

Adverse drug event reports from FDA's Adverse Event Reporting System (FAERS) — 9M+ records since 1968 covering serious adverse events, hospitalizations, deaths, and disabilities. Search by drug name (brand/generic/substance, all OR-matched) and optionally filter by MedDRA reaction term. Returns report ID, received date, seriousness flags, patient demographics, MedDRA-coded reactions, implicated drugs (up to 5 per report), and reporting country. Backed by OpenFDA; data is public-domain US government records.

Decode a 17-character VIN to manufacturer-supplied vehicle metadata via NHTSA's vPIC database. Returns identity (year, make, model, trim, series, body class, manufacturer), assembly plant (city, state, country), engine (cylinders, displacement, HP, fuel type, configuration, engine model), transmission (style, speeds), and body/weight specs. Curated to the ~30 fields agents actually use from vPIC's ~140-field response. Backed by NHTSA.gov; data is public-domain US government records.

CPSC consumer-product recalls from SaferProducts.gov, newest first. Covers products outside FDA (food/drug/device) and NHTSA (vehicles): strollers, appliances, lithium batteries, furniture, toys, power tools, and more. All filters optional (with none set, returns the last 12 months). Each record includes recall number + date, title, CPSC URL, description, affected products (name/model/units), hazards, remedies, reported injuries, manufacturers/importers/distributors/retailers, where sold, manufacturing countries, images, and consumer-contact info. Public-domain US government data.

Paginated list of every motor vehicle manufacturer NHTSA tracks via vPIC. Each record includes the canonical Mfr_ID, full legal name, common short name (e.g., "Honda"), country, and the list of vehicle types the manufacturer produces (Passenger Car, Truck, Motorcycle, Bus, MPV, etc.). Pass the optional `manufacturer` param to substring-search Mfr_Name. 100 records per page. Backed by NHTSA.gov; data is public-domain US government records.

Real-time water data from USGS NWIS stream / river / groundwater gauges within a bounding box around lat/lon. Returns each site's latest reading per requested variable: streamflow (00060, ft³/s), gage height (00065, ft), water temperature (00010, °C), precipitation (00045, in), and others. Each reading: site code + name, lat/lon, variable name + description + unit, value (or null if no data / sentinel), qualifier codes (e.g., 'P' = provisional, 'A' = approved), observed timestamp. Free public-domain data from waterservices.usgs.gov.

Enumerate every model a manufacturer sold in a given model year via NHTSA's vPIC taxonomy database. Returns canonical NHTSA Model IDs + names plus the Make ID + name for reference. Useful as a discovery step before VIN decode (when the agent only knows make + year) or as input validation for vehicle.recalls / vehicle.complaints. Backed by NHTSA.gov; data is public-domain US government records.

US mortality statistics from CDC NCHS. dataset=leading-causes (default): annual deaths + age-adjusted death rate per 100k by state and top-10 cause of death, 1999-2017 — filter by state (full name, e.g. "California", or "United States"), year, cause (e.g. "Heart disease", "Cancer", "Suicide"). dataset=weekly-counts: provisional weekly death counts by jurisdiction with per-cause columns (all-cause, natural, COVID-19, heart disease, cancer, etc.), 2020-2023 — filter by state and mmwrYear. Rows returned raw from CDC with documented column names. Public-domain federal data.

Decode a 3-character World Manufacturer Identifier (the first three characters of a VIN) to the assigning manufacturer. Returns full manufacturer legal name, common short name, make, vehicle type, and the date NHTSA published the assignment. Useful for partial-VIN analysis — crash reports, damaged-vehicle photos, fleet records — where only the WMI is recoverable. Backed by NHTSA.gov vPIC; data is public-domain US government records.

NHTSA consumer complaints for a US vehicle by (make, model, modelYear). Returns the top N records (newest-filed first) with ODI number, affected component, plain-English summary, crash/fire flags, injury and death counts, partial VIN, and incident + filing dates. Backed by NHTSA's public complaints database; data is public-domain US government records.

Chronological feed of NHTSA ODI (Office of Defects Investigation) investigations, newest first. Returns preliminary evaluations (PE), engineering analyses (EA), defect petitions (DP), and recall queries (RQ) — each with NHTSA ID, type code, open/close dates, status, subject, and full description (HTML stripped + raw). Useful for tracking what NHTSA is currently investigating (Tesla FSD, autonomous-vehicle crashes, Rivian suspension, etc.). NOTE: NHTSA's endpoint does NOT support make/model/year filtering — use vehicle.recalls or vehicle.complaints for vehicle-scoped lookups. Public-domain US government records.

NHTSA recall campaigns for a US vehicle by (make, model, modelYear). Returns every open + historical campaign with the NHTSA campaign number, manufacturer, affected component, plain-English summary/consequence/remedy text, and the parkIt / parkOutside fire-risk advisories. Backed by NHTSA's public recalls database; data is public-domain US government records.

US House of Representatives roll-call votes, newest first by action date. Each record includes year + roll number, congress/session, vote question + type + result, action date/time, bill reference (legis_num), description, grand totals (yea/nay/present/not-voting), AND per-party breakdown (Republican/Democratic/Independent yea/nay/present/not-voting counts). Filters (all optional, AND-combined): year, congress, result substring, bill substring (legis_num ILIKE), since/until (action_date), limit + offset. Locally aggregated from clerk.house.gov XML feeds (refreshed daily by cron). Public-domain US government records.

FDA animal and veterinary adverse event reports, newest first. All filters optional. Each record includes AER ID, dates, animal species/gender/breed/age/weight, reactions (VeDDRA-coded), drugs (brand + active ingredients + administration), primary reporter (Veterinarian/Owner/Other). Use cases: veterinary practice safety research, pet food adverse events, livestock drug surveillance. Backed by OpenFDA's /animalandveterinary/event endpoint; public-domain US government records.

Agent-readiness scan of any public website: scores 0-100 on MCP server, /.well-known/agent.json, llms.txt, OpenAPI validity, JSON-LD catalog and x402/MPP payability. Same published methodology as the asterpay.io checker. Paid via x402.

US oil and gas — WTI Brent Henry Hub refined products basin production rig count

FEMA Hazard Mitigation Assistance (HMA) funded projects — the pre- and post-disaster mitigation grants FEMA has actually obligated (HMGP, BRIC/PDM, FMA). Filter by state (2-letter), disasterNumber, programFy (program fiscal year), and/or programArea; at least one filter is required. Returns the total matching project count plus projects (identifier, program area, project type, status, recipient/subrecipient, county, disaster number, project amount and federal share obligated in USD, cost-share %, benefit-cost ratio, number of properties, approval/close dates), largest federal share first. Free, public-domain (OpenFEMA). Distinct from gov.public-assistance (post-disaster recovery grants) and gov.nfip-claims (flood losses paid) — this is mitigation funding: who got money to reduce future risk, where, and at what benefit-cost ratio.

Federal Reserve regional economic data: one snapshot of a FRED regional series across ALL its geographies (every U.S. state, county, or metro area) for a single period. Pass a regional series id (e.g. WIPCPI = per-capita personal income by state, or a state/county unemployment series) and get each region's name, FIPS region code, value, and per-region FRED series id, plus the group's units, frequency, and available date range. Add a date (YYYY-MM-DD) for a point-in-time cross-section; omit it for the latest. Authoritative St. Louis Fed (GeoFRED) data agents can't recite — per-state income, county unemployment, regional GDP — keyed by exact region codes. Free, public-domain. Companion to econ.fred (national series), econ.fred-categories (discover series ids), and census.demographics (ACS survey).

Live news search. Returns recent headlines with title, URL, snippet, publisher source, relative age, and a breaking-news flag — real-time coverage past any model training cutoff. Supports count (1-20), offset, country (2-letter), and freshness (pd=past day, pw=past week, pm=past month, py=past year). Use for current events, market-moving developments, monitoring, and "what happened with X" questions. For general web results see /api/search/web; for Hacker News specifically see /api/news/hn-top.

Live web search. Returns ranked results with title, URL, snippet description, site name, and page age — fresh information past any model training cutoff. Supports count (1-20), offset for paging, country (2-letter, e.g. US), freshness (pd=past day, pw=past week, pm=past month, py=past year, or a YYYY-MM-DDtoYYYY-MM-DD range), and safesearch (off/moderate/strict). Use for current events, fact verification, finding documentation, and research. Independent search index. For news-specific results with sources and timestamps see /api/news/search.

Analyze sentiment of up to 20 texts in batch