LiveDataLink

Get current air quality data for any location. Returns US AQI index, PM2.5, PM10, ozone, NO2, SO2, and CO levels with health category rating. Use this for 'what's the air quality?', 'is it safe to go outside?', 'pollution levels', 'AQI in Los Angeles', 'should I wear a mask?', 'is there smoke in the air?', or any air quality or pollution question.

One-call financial-health read for a US bank or savings institution. Give a bank name or an FDIC certificate (CERT) number. Joins FDIC BankFind institution + financials (total assets, deposits, net income, return on assets/equity, active-vs-failed status) with the CFPB Consumer Complaint Database (complaint volume and top complaint products for the matched company) into a HEALTHY / STABLE / WATCH / FAILED read with the numbers behind it. FDIC is the primary signal; CFPB complaint data is best-effort and degrades gracefully if the bank's complaint records cannot be matched. Useful for picking a sponsor/partner bank, treasury counterparty checks, or deposit-safety questions. Informational, not a rating or advice.

One-call KYB/AML ownership-chain sanctions screen: answers the real question 'is anyone in this company's ownership chain sanctioned?', not just 'is the top-level name on a list?'. Give a company name or a 20-character LEI; the tool maps the ownership structure via GLEIF (keyless CC0 reference data) - the subject entity, its ULTIMATE parent (top of the chain), and its reported direct subsidiaries, capped at about 15 entities so a broad group stays bounded - then SCREENS each entity in that set against the local sanctions/watchlist matcher (OFAC SDN / EU / UN / BIS), the same first-party matcher company_trust_check uses. Returns the mapped ownership structure, a per-entity CLEAR / HIT result (each hit naming the matched list entry, source, and score), and an overall verdict: CLEAR (no entity matched) vs HITS-FOUND (at least one entity in the chain matched). This catches a sanctioned parent or subsidiary that screening only the counterparty name would miss - the exposure beneficial-ownership rules target. Best-effort: if GLEIF hops fail the subject is still screened; if the sanctions binding is unavailable the screen is noted as unavailable, never silently passed. Only relationships an entity self-reports to GLEIF are shown. A name match is not proof of identity and must be cleared. Informational public-record synthesis, not legal, compliance, or sanctions-clearance advice.

US labor & price statistics from the Bureau of Labor Statistics by friendly name. Available: unemployment_rate, labor_force_participation, employment_population_ratio, cpi, cpi_less_food_energy, nonfarm_payrolls, avg_hourly_earnings, avg_weekly_hours, ppi_final_demand. Returns a monthly time series. Keyless official BLS data.

Fetch any BLS time series by its raw series ID (e.g. 'LNS14000000' for the unemployment rate, or a state/industry series). For when you know the exact BLS series ID.

Get full catalog metadata for a single book by its Project Gutenberg id (title, authors, subjects, languages, copyright, download count, and whether its full text is indexed here).

Search INSIDE the indexed corpus of top public-domain books for a phrase or keywords and get back the matching passages, each with the book title, author, and a snippet around the match. This is the headline feature: agents can find where a passage appears across great books. Optionally restrict to one book by gutenberg_id.

Return the full text of an indexed book by Gutenberg id, paginated by passage. Use from_seq + max_passages to page through it. For books in the catalog that are NOT indexed locally, returns the public gutenberg.org plain-text URL so the agent can fetch it directly.

Search the full Project Gutenberg catalog (~78,500 public-domain books) live via Gutendex by title / author / subject keyword, with optional author, subject, and language filters. Ranked by keyword relevance then download popularity. Returns each book's Gutenberg id, title, author(s), language, and download count. Use book_fulltext_search to search inside the locally indexed top books.

Report the books store status: the catalog is served live via Gutendex (78,000+ books), plus the local D1 indexed-corpus counts (books with full text indexed, total indexed passages, last refresh timestamp).

Screen one or more US tickers for a mean-reversion 'bounce' setup on daily bars: price near support (recent pivot low) or the moving average, RSI oversold and turning up, a bullish latest candle, and volume at/above its recent average. Returns per-symbol {isBounce, score 0-100, reasons, price, rsi, distanceToSupportPct, supportLevel}. ALL thresholds are tunable inputs (rsi_threshold, ma_period, proximity_pct, lookback_days) so calibration is a parameter change. HEURISTIC signal for research, not investment advice.

Detect classic candlestick patterns on a ticker's recent daily bars: hammer, inverted hammer, bullish/bearish engulfing, doji, morning/evening star, and shooting star. Returns each detected pattern with {pattern, date, direction (bullish/bearish/neutral), barIndex}. HEURISTIC pattern detection with conservative default thresholds; for research, not investment advice.

Look up a Rust crate on crates.io: latest version, description, total downloads, repository, and homepage. Keyless.

Vet a US motor carrier (trucking company) for a freight-brokerage 'is this safe and legit to broker a load to?' decision, in one call. Give a USDOT number, MC number, or carrier name. Joins FMCSA safety data (operating authority, insurance on file, BASIC safety scores, crash and out-of-service history vs the national average, safety rating) with sanctions screening (OFAC/UN/EU/BIS on the carrier's legal name), federal-court litigation history (CourtListener), and USAspending federal awards. Returns a GO / CAUTION / NO-GO verdict with the reasons, plus all the underlying fields. NO-GO is triggered by a sanctions match or lack of active operating authority; CAUTION by BASIC alerts, fatal crashes, missing liability insurance, high out-of-service rates, or litigation. This is an analytical aid, not a substitute for your own carrier-onboarding checks.

Get full metadata for a single case by its CAP id (name, citations, court, jurisdiction, decision date, reporter location, and the source URL for its full text).

Resolve a reporter citation (e.g. '347 U.S. 483', '347 U. S. 483', '384 U.S. 436') to the case it identifies. Matches official and parallel citations. Returns the case metadata including its CAP id for use with caselaw_opinion_text.

Fetch the full opinion text of a case on demand by its CAP id. Text is retrieved live from the public-domain CAP static mirror (not stored), and includes each opinion (majority, dissent, concurrence) with its author. Use max_chars to bound the response.

Search US court opinions (Caselaw Access Project, public domain) by case name / keyword, court, jurisdiction, and decision-date range. Returns matching case metadata with CAP ids and citations. Use caselaw_opinion_text with a returned id to read the full opinion. Note: v1 index covers the U.S. Reports reporter (official US Supreme Court reporter).

Generic SoQL query against any data.cdc.gov dataset. Use this when none of the curated tools fit. Accepts a 4x4 Socrata ID and a where-clause. SoQL reference: https://dev.socrata.com/docs/queries/

CDC drug overdose deaths by state and indicator (9j2v-jamp). 12-month rolling counts. Useful for opioid/fentanyl/stimulant policy research and treatment-program siting.

CDC excess deaths associated with COVID-19 (xkkf-xrst). Modeled expected vs observed deaths by state and week. Used to estimate true pandemic impact beyond reported COVID deaths.

CDC FluView state-level influenza surveillance (vh55-3he6). Returns weekly ILI (influenza-like illness) activity levels per state.

NCHS leading causes of death by state (bi63-dtpu). Returns total deaths and age-adjusted death rates per cause per state per year. Useful for chronic disease + injury mortality research.

CDC NORS foodborne / waterborne / enteric outbreak reports (iezt-77pi). Returns outbreak date, state, etiology, illnesses, hospitalizations, deaths, and implicated food/exposure.

COVID-19 vaccination coverage by US county (8xkx-amqh). Returns booster + primary series percentages over time. Useful for public-health gap analysis.

CDC weekly provisional deaths by state and cause (NCHS dataset muzy-jte6). Returns all-cause and selected-cause death counts per state per ISO week. Useful for excess-mortality and respiratory-disease seasonality analysis.

Business establishments, employment, and annual payroll from County Business Patterns. Optional NAICS industry filter. Used for industry research, competitive intel, supply chain analysis.

Labor force, unemployment, commute times, public transit usage, work-from-home rates for a US geography. Used for site selection, workforce analysis, commercial real estate.

Race, ethnicity, and age breakdown for a US geography. Returns counts for white, black, Asian, AIAN, NHPI, other, two-or-more, plus Hispanic/Latino total and median age. Source: ACS 5-year.

Look up Census FIPS codes by name. Supports state name or 2-letter code, ZIP code (5 digits), and (for state) substring matching. Use this to find the FIPS codes needed by other census_* tools.

Median household income, per capita income, housing units, owner vs renter occupancy, median home value, median gross and contract rent for a US geography. Used for real estate AI, market analysis, location-based pricing.

Get total population for a US geography (state, county, ZIP/ZCTA, city, census tract, MSA, or national). Returns total, male, female, and median age. Used for market sizing, location intelligence, demographic analysis.

Aggregate complaint counts by a single facet (product, issue, company, state, company_response, or submitted_via). Useful for ranking companies by complaint volume or finding the most common issue categories.

Fetch a single CFPB complaint by complaint_id. Returns the full record including narrative if consented.

Time-series trends of complaint volume. lens=overview shows total complaints over time; lens=product shows by product; lens=company shows by company; lens=issue shows by issue. Interval can be month, quarter, or year.

Search the CFPB Consumer Complaint Database (4M+ complaints submitted against financial companies since 2011). Filter by free-text term, company, product, state, date range, and narrative-presence. Returns complaint metadata plus public narratives when available.

Complaint counts and percentages per US state, with optional product filter and date range. Useful for state-level financial-consumer risk maps.

Auto-complete company names. Returns up to 10 suggestions matching the partial input. Use the results as exact values for cfpb_search_complaints' company parameter.

Return the public GHS (Globally Harmonized System) hazard classification for a chemical from the NIH/NLM PubChem database (keyless, public-domain data). Given a chemical name or PubChem CID, it resolves the compound and returns the GHS signal word (Danger/Warning) and the list of GHS hazard statements (e.g. 'H302: Harmful if swallowed'). If PubChem has no GHS classification on file for the compound, that is reported gracefully. This is informational public GHS classification data, not regulatory guidance or a safety data sheet - verify against an official SDS before handling any chemical.

Resolve a chemical name (e.g. 'aspirin', 'caffeine') or a PubChem CID to its core identity and physical properties using the NIH/NLM PubChem public database (keyless, public-domain data). Returns the PubChem Compound ID (CID), IUPAC systematic name, molecular formula, molecular weight (g/mol), and the canonical SMILES structure string. Use it to disambiguate a substance and obtain a stable CID join key for further chemistry or safety lookups.

One-call clinical-trial-activity + local-specialist-availability read for a medical condition in a US geography - the question a trial sponsor, CRO, or site-feasibility analyst asks before choosing where to run a study. Joins three keyless public sources: ClinicalTrials.gov (exact count of RECRUITING trials for the condition, scoped to the geography and compared to the national total, plus the top lead sponsors and phase mix from the recruiting sample), the NPPES NPI Registry (local specialist availability - how many providers carry a specialty taxonomy relevant to the condition in the area, across physicians and NPs/PAs/pharmacists/RNs in the field), and optionally US Census ACS population context for the state (needs a Census key; degrades gracefully). The condition is mapped to a provider specialty heuristically; pass an explicit 'specialty' to override. Returns a readable brief with a headline banding trial activity (HIGH/MODERATE/LOW/NONE) and specialist availability. A source that fails is noted, not fatal. INFORMATIONAL research / site-feasibility synthesis, NOT medical advice or a directive to enroll in any trial.

Search Medicare-certified home health agencies from CMS Home Health Compare. Returns agency name, address, services offered, and quality ratings.

Search Medicare-certified hospice agencies from CMS Hospice Compare. Returns provider name, address, ownership, and quality measures.

Search Medicare-certified hospitals from the CMS Hospital General Information dataset. Returns facility name, address, ownership type, emergency-services flag, and CMS overall star rating (1-5). Filter by state, city, and partial facility-name match.

Search Medicare-certified nursing homes from CMS Nursing Home Compare. Returns name, address, ownership, certification status, total beds, and quality measures.

Current institutional accreditation status, accreditor, and (when published by DAPIP) last action date and programmatic accreditations.

Side-by-side comparison of 2-5 schools across cost, outcomes, and admissions metrics. Pass UNITIDs.

Student-body demographics for one school: race/ethnicity, gender, age (under/over 25), and geographic origin (in-state, out-of-state, foreign).

Cost and outcome metrics for one school: published tuition (in-state and out-of-state), average net price, six-year graduation rate, first-year retention, median earnings ten years after entry, admission rate, and SAT/ACT ranges.

Program-level outcomes (4-digit CIP code) for one school: median earnings one year after completion, median debt at completion, and award counts.

Search US colleges and universities by name, state, control type, size, or accreditor. Returns matching institutions with location, control, predominant degree, and enrollment.

Multi-year trend for one school sourced from the Urban Institute Education Data Portal (IPEDS). Choose a metric (enrollment, graduation_rate, retention, cost) and a year range.

One-call 'is this degree worth the cost' read for a US college (and optionally a named program). Joins the College Scorecard / IPEDS education domain (average net price, six-year completion rate, median earnings ten years after entry, and - when a program is named - program-level median debt and 1-year earnings) with a keyless BLS wage context (CES average hourly earnings, annualized) to place those earnings against the broad US private-sector wage. Returns a plain read - STRONG VALUE / FAIR / WEAK VALUE / INSUFFICIENT DATA - with the cost-vs-earnings evidence itemized and each sub-signal scored. A source that fails is noted, not fatal. Premium cross-source synthesis; Scorecard earnings cover federally-aided students only and lag by years. Informational only, not admissions, financial, or career advice.

One-call CONSUMER-RISK read for a company or brand, LED by the consumer-complaint picture. Joins three public-record legs, CFPB first: CFPB Consumer Complaint Database (complaint volume for the company plus the top complaint products and issues - the primary signal), product recalls (CPSC consumer products + openFDA drug/device/food enforcement, keyed by the company), and federal-court litigation (CourtListener dockets whose caption actually names the company). Returns a rolled-up read (LOW / MODERATE / ELEVATED consumer-risk signals) that leads with complaint volume and the top complaint products/issues, then folds in recall count and severity (FDA Class I / death-related = high) and litigation hits (total + last-3-years). A leg that fails is noted, not fatal. This is consumer-complaint-centered and distinct from product_liability_screen (recall/litigation-centered for manufacturers). NHTSA vehicle recalls need a specific year+make+model so are out of scope here (use recall_screen for a vehicle). Premium cross-source synthesis; informational public-record synthesis, NOT legal advice.

Get company profile and financial fundamentals. Returns sector, industry, employee count, business description, revenue, gross profit, EBITDA, profit margins, EPS, P/E ratio, forward P/E, dividend yield, beta, market cap, and shares outstanding. Use this for "tell me about Apple", "what does this company do?", "company financials", "what sector is Netflix in?", "how many employees does Tesla have?", or any company research question.

One-call public-record trust read for a company - answers 'can I trust this company?' for KYB/vendor-diligence agents. Joins the LiveDataLink sources that carry a legitimacy or risk signal into a single standing read: an OFAC SDN / EU / UN / BIS sanctions screen (a hit is decisive), SEC EDGAR registration plus the latest filing date (legitimacy + recency), USAspending federal award history (the US government transacts with them), and EPA ECHO facility compliance (significant-non-compliance, penalty, and non-compliant-quarter flags). Returns a plain-English verdict band (ESTABLISHED PUBLIC-RECORD STANDING / STANDING WITH FLAGS / LIMITED FOOTPRINT / SANCTIONS SCREEN HIT), the positive signals, the flags to review, and the resolved identifiers. A source that fails is noted, not fatal. This is a public-record SIGNAL read, not a credit report, background check, or endorsement: absence of a record is not proof of wrongdoing and a match is not proof of guilt. Premium cross-source synthesis.

Get the chronological legislative action history for one bill (introductions, committee referrals, votes, becoming law). Requires Congress number, bill type, and bill number.

List the cosponsors of one bill with their party and state. Useful for mapping coalitions behind legislation. Requires Congress number, bill type, and bill number.

Get full detail for one bill, including title, sponsor, latest action, policy area, and a cosponsor party breakdown. Requires the Congress number, bill type, and bill number (e.g. 118, 'hr', 3076).

List recent U.S. House roll-call votes for a Congress, with vote number, question, result, and date. Defaults to the current Congress.

Get detailed profile for one member of Congress by bioguide ID (e.g. 'P000197'), including party history, terms served, and leadership roles.

List bills that have become public or private law in a given Congress. Defaults to the current Congress. Use law_type 'pub' for public laws or 'priv' for private laws.

Search or list recent U.S. federal bills and resolutions from Congress.gov. Returns the most recently updated bills, optionally scoped to a Congress number or filtered by a free-text query. Use this to find legislation by topic or to see what is currently moving.

Search members of Congress, optionally filtered by Congress number, two-letter state, and district. Returns name, party, chamber, and bioguide ID (use that ID with congress_member_details).

One-call FULL corporate-ownership tree for a company from GLEIF (keyless CC0 reference data). Give a company name or a 20-character LEI; the tool resolves the entity, climbs to its ULTIMATE parent (top of the ownership chain), then walks DOWN from that root to list the reported direct subsidiaries plus one level of grand-subsidiaries, each with its LEI, jurisdiction, and status (entity ACTIVE/INACTIVE + LEI registration ISSUED/LAPSED). The queried entity is marked in the tree so you can see where it sits. Distinct from resolve_entity, which returns the ultimate parent plus a subsidiary COUNT only: this returns the actual subsidiary LIST/tree for M&A, diligence, and counterparty mapping. The tree is capped (about 25 nodes) so a broad conglomerate stays bounded, with an 'and N more' note where GLEIF reports additional subsidiaries. Only relationships an entity self-reports to GLEIF are shown, so coverage varies by company. A failing hierarchy hop is noted, not fatal. Informational public-record synthesis; verify against GLEIF before relying on it.

One-call comparative 'cost of operating a business here' read for a US state (with optional metro context). Joins three independent public sources, each a real operating-cost dimension expressed RELATIVE to the US national average (national = 1.00) so the result is a readable, comparable index: LABOR cost from BLS QCEW private-sector average annual pay across all industries (keyless), ENERGY cost from EIA retail electricity price for the commercial and industrial sectors (state vs national), and local CONTEXT from US Census ACS median household income, per-capita income, and median gross rent (needs a Census key; degrades gracefully). Returns a headline relative-cost banding (LOW / MODERATE / HIGH cost vs national) from a labor-weighted composite of the labor and energy indices, with each dimension's numbers and its own banding shown. Labor and energy are state-level; a supplied metro refines the context leg and label only. A source that fails is noted, not fatal. Informational, not a guarantee.

Compute a composite 0-100 Counterparty Risk Score for a company name. Combines findings from sanctions screening (OFAC/UN/EU/BIS), SEC EDGAR (registered-filer signal), federal courts (litigation history), EPA ECHO (environmental enforcement), and USAspending (federal contract vetting) into a single weighted metric with an explainable evidence chain. Returns: score, risk band (clean/low/moderate/elevated/high/critical), itemized evidence with citations, sources queried, sources that failed, and a plain-text summary suitable for an AI agent to surface to a user. Sanctions hits zero the score regardless of other signals. Use this when you need a single-call counterparty risk verdict instead of stitching five separate queries.

Search federal and state court opinions by keyword, court, judge, party name, or date range. Returns case summaries with citations.

Resolve a legal citation (e.g. '410 U.S. 113') to its CourtListener case record.

Look up a federal docket by court ID and docket number. Returns party list and recent entries from PACER/RECAP.

Look up a judge profile by name or CourtListener person ID. Returns positions, education, and bench history.

Full-text search of court opinions. Returns opinion text snippets, authors, and citations.

Search SCOTUS and federal appellate oral argument audio. Returns audio URLs and transcript snippets.

Recent docket entries filed in a specific court, ordered newest first.

Search U.S. Consumer Product Safety Commission (CPSC) product recalls via SaferProducts.gov (keyless). Filter by product name/keyword, title, manufacturer, hazard, recall number, and date range. Returns recall number, date, title, products, hazards, remedy, manufacturers, injuries, and the official CPSC recall URL. Data: CPSC/SaferProducts.gov.

Return the most recent U.S. CPSC product recalls (date-sorted, newest first) via SaferProducts.gov (keyless). Looks back a configurable window (default 90 days). Each result links to the official CPSC recall page. Data: CPSC/SaferProducts.gov.

Compare 2-5 cryptocurrencies side by side. Shows price, 24-hour change, market cap, volume, and rank for each coin in a comparison table. Use this for 'compare bitcoin and ethereum', 'BTC vs ETH vs SOL', 'which is bigger bitcoin or ethereum?', 'compare top cryptos', 'crypto head to head', or any multi-coin comparison question.

Get a detailed profile for any cryptocurrency including description, market data, supply info, all-time high/low, genesis date, blockchain, categories, and website links. Use this for 'tell me about bitcoin', 'what is ethereum?', 'solana info', 'describe cardano', 'crypto profile', 'coin details', or any question asking for background information about a specific cryptocurrency project.

Get the current price and market data for any cryptocurrency. Returns price in USD, 24-hour change, market cap, volume, and all-time high. Use this for 'what's the price of bitcoin?', 'how much is ethereum?', 'solana price', 'check dogecoin', 'BTC price', 'ETH value', 'crypto price check', or any question about a specific coin's current value. Supports all major cryptocurrencies: bitcoin, ethereum, solana, cardano, ripple/XRP, dogecoin, polkadot, avalanche, chainlink, polygon/MATIC, litecoin, uniswap, stellar, cosmos, NEAR, arbitrum, optimism, aptos, sui, toncoin, shiba inu, pepe, BNB, tether/USDT, USDC, and thousands more via CoinGecko ID.

See what's trending and hot in cryptocurrency right now. Returns the top trending coins on CoinGecko based on search activity and interest. Use this for 'what's trending in crypto?', 'hot cryptocurrencies', 'trending coins', 'what crypto is popular right now?', 'crypto buzz', 'what tokens are people looking at?', or any question about current crypto market interest and momentum.

Full detail for a single CVE by ID (format CVE-YYYY-NNNN). Returns CVSS scores, weakness IDs, references, and affected products from the NVD.

Recent CVEs published in the last N days (default 7, max 120). Optional vendor and severity filters (CRITICAL, HIGH, MEDIUM, LOW).

Free-text CVE search with optional date range. Matches keyword against CVE description text in the NVD.

Search CVEs by vendor with optional product and date range filters. Vendor is matched against the NVD CPE namespace, e.g. 'apache', 'microsoft'.

MITRE CWE detail by ID (format CWE-NNN or NNN). Returns name, abstraction, status, description, and parent/child CWE relationships.

Recent FEMA disaster declarations filtered by state, county, incident type, or date range. Returns disaster number, title, dates, and incident category.

Multi-year FEMA disaster summary for a location. Buckets declarations by incident type and year so insurance brokers and realtors can assess cumulative risk on the same address used in property_lookup.

One-call disaster-history and recovery read for a US area (county or place), keyed by NAME + state - distinct from location_risk_report, which scores a single site by address/lat-lon. Joins FEMA's OpenFEMA disaster declarations (the area's federally-declared disaster history: incident types, frequency, most-recent event, and the federal-assistance signal - which programs, Individual Assistance / Individuals & Households / Public Assistance / Hazard Mitigation, were authorized) with optional US Census ACS county population for exposure context (keyed off the FIPS codes the FEMA records carry; needs a Census key and degrades gracefully) and an optional best-effort parcel record for property context when an address is given (Maryland statewide / Texas-Harris County only). Returns a readable profile with a headline banding the area's disaster exposure LOW / MODERATE / HIGH from the declaration record. The FEMA leg is keyless and is the core signal; a source that fails is noted, not fatal. INFORMATIONAL public-record synthesis, NOT an insurance rating, a property flood-risk score, or a professional risk assessment.

Recent earthquakes from USGS. Filter by region (lat/lon + radius), state name, magnitude threshold, or time window.

Get structured XBRL financial facts for a company. Without 'concept', returns the top-level facts catalog (concepts the company has reported). With 'concept' (e.g. 'Revenues', 'Assets', 'EarningsPerShareBasic'), returns the time series of values for that concept.

Look up a public company's CIK (Central Index Key) by ticker symbol or company name. CIK is required for all other EDGAR tools. Returns matches ranked exact-ticker first.

Fetch the text content of a specific SEC filing. Returns the primary document (10-K, 10-Q, etc.) stripped of HTML, suitable for LLM consumption. Use edgar_recent_filings first to get the accession number.

Pull all recent SEC filings of a specific form type across all companies. Useful for monitoring (e.g. 'all 8-Ks today', 'all S-1s this week'). Returns accession numbers, filers, and filing dates.

Full-text search across all SEC filings via the EDGAR EFTS index. Filter by comma-separated form types and date range. Useful for finding filings that mention specific terms.

List recent Form 4 insider transaction filings for a company. Returns accession numbers and filing dates; for detailed transaction data, use edgar_filing_content on each.

List recent SEC filings for a company. Filter by form type (10-K, 10-Q, 8-K, 4, DEF 14A, etc.) and start date. Use ticker or CIK as identifier.

Monthly state-level electricity data from EIA. Filter by state (two-letter code or 'US' for national), sector (residential / commercial / industrial / transportation / all), and metric (price / sales / revenue / customers / generation). Default: US, all sectors, price.

Monthly US energy consumption by sector from EIA. Sectors: residential, commercial, industrial, transportation, total. Returns total energy consumed in BTU equivalents.

Weekly US retail gasoline prices from EIA. Filter by region (PADD1-PADD5 or national) and grade (regular, midgrade, premium, diesel, all). Useful for fuel-cost analysis, transportation logistics, and consumer price tracking.

US natural gas data from EIA. Series options: 'spot' (Henry Hub daily), 'futures' (NYMEX front-month daily), 'residential' (monthly retail to households), 'storage' (weekly working gas in storage). Default 'spot'.

Weekly US crude oil supply data from EIA. Metrics: 'production' (US field production), 'imports' (weekly oil imports), 'stocks' (commercial crude stocks), 'refinery_inputs' (gross refinery inputs). Filter by PADD region. Default: national production.

Monthly US electricity generation by source from EIA. Sources: solar, wind, hydro, nuclear, geothermal, biomass, all. Optional state filter (default national). Returns generation in megawatt-hours.

Flexible EIA series lookup. Pass any EIA series ID (e.g. 'PET.RWTC.D' for WTI crude daily, 'NG.RNGWHHD.D' for Henry Hub spot daily, 'ELEC.PRICE.US-ALL.M' for US average electricity retail price monthly). Returns time-series data for that series. Use this when no other tool covers your specific need.

One-call US energy market snapshot from EIA (public domain): the WTI crude (Cushing), Brent crude, and Henry Hub natural-gas benchmark prices, each enriched with derived context - latest level and date, 1-year change, where the current level sits within its own recent history (percentile), and the recent trend direction (rising/falling/flat). Answers 'what is oil/gas doing right now, and is it historically high or low' in a single call. A source that fails is noted, not fatal. Premium synthesis over the EIA domain; informational market data, not trading advice.

Build a consolidated cross-source dossier for a company in one call: SEC registration and identifiers (EDGAR), environmental footprint and regulated facilities (EPA ECHO), and sanctions/denied-party screening (OFAC/UN/EU/BIS) with a confidence score. Returns a per-source summary plus top records. This is a single AI-native lookup across data that otherwise lives in separate silos. Matches are name-based; verify identity before relying on any link.

Resolve a company across US government sources in one call. Searches SEC EDGAR, EPA ECHO, and the sanctions lists by name and returns the candidate match and strong identifiers (SEC CIK, ticker, EPA registry id) found in each. Use this to confirm WHO an entity is and gather its IDs before pulling detail. Matches are name-based candidates to verify, not certain identity links.

One-call environmental-compliance and contamination liability read for a SPECIFIC site or operator - the question a buyer, lender, or Phase-I ESA asks before a deal. Distinct from location_risk_report (which scores natural hazards plus a shallow count of nearby facilities): this drills DEEP into one named facility's EPA record via ECHO/FRS - overall compliance status, per-statute program standing (Clean Air/Water/RCRA/etc.), formal enforcement actions and penalty totals, significant-non-compliance and non-compliant-quarter flags - plus a best-effort parcel record for site context. Returns a verdict band (NO ADVERSE EPA RECORD / REVIEW RECOMMENDED / CONTAMINATION-COMPLIANCE CONCERN / NO FACILITY FOUND), the flags, and the evidence. A source that fails is noted, not fatal. This is an EPA public-record screen, not a Phase-I Environmental Site Assessment or a substitute for one. Premium cross-source synthesis.

List formal enforcement actions and penalties taken against a facility, plus a per-program summary of formal/informal actions, cases, and total penalties. Requires an EPA Registry ID (use epa_facility_search to find it).

Report a facility's current compliance status and recent non-compliance history by environmental program (Clean Air Act, Clean Water Act, RCRA hazardous waste, Safe Drinking Water Act). Shows quarters in non-compliance, quarters in significant non-compliance, and last inspection per statute. Requires an EPA Registry ID.

Get a Detailed Facility Report for one facility by its EPA Registry ID: name, address, permits held, and per-statute (CAA/CWA/RCRA/SDWA) compliance and inspection summaries. Use epa_facility_search first to obtain the registry_id.

Search EPA-regulated facilities by state, city, zip, and/or facility name. Returns each facility's Registry ID (needed for the other EPA tools), address, and a snapshot of its compliance status across Clean Air Act, Clean Water Act, RCRA (waste), and Safe Drinking Water programs. Provide at least one filter; broad queries (e.g. state only for a large state) may be rejected as too broad, so add a city, zip, or name.

Report a facility's air (Clean Air Act) or water (Clean Water Act / Safe Drinking Water Act) violations and the related compliance summaries. Set media to 'air', 'water', or 'all'. Requires an EPA Registry ID.

FIRST EPSS exploit prediction score for a CVE. Returns probability (0-1) of exploitation in the next 30 days plus the percentile rank.

One-call care-quality + provider-identity read for a named US healthcare FACILITY (hospital, nursing home, home-health agency, or hospice). Joins two keyless federal sources: CMS Care Compare (data.cms.gov) for the facility's quality signal - the CMS star rating and, for a hospital, the measure-group highlights (mortality, safety of care, readmission, timely-and-effective care measured better / no different / worse vs national), plus ownership, type, and for a nursing home the health-inspection / staffing / quality-measure star breakdown, certified beds, abuse flag, and fines - and the NPPES NPI Registry for the facility's legal identity (organizational NPI, taxonomy, city/state, active status). Provide a facility name (e.g. 'Cleveland Clinic', 'Mayo Clinic Hospital'); optionally add a 2-letter state to disambiguate and a type (hospital / nursing_home / home_health / hospice) to pin the CMS dataset. When no type is given the tool infers the provider category from the NPPES taxonomy and probes the CMS datasets in order. A leg that fails is noted, not fatal. This is an INFORMATIONAL public-record read, NOT medical advice, a substitute for CMS Care Compare, or an endorsement of any facility.

Search the FBI's public Wanted/fugitive list by name or keyword. Returns matching subjects with aliases, the responsible field offices, and a link. Complements sanctions screening for person due diligence. Keyless.

FDA 510(k) clearances for medical devices. The 510(k) pathway is how most non-high-risk devices come to market in the US. Filter by manufacturer (applicant), device name, product code, or decision date range. Used for competitive intel, device R&D scouting, M&A research.

FDA medical device recalls. Filter by device name or recalling manufacturer, classification (Class 1 most severe), or date range. Used for medical device supply chain monitoring and hospital biomed compliance.

FDA Adverse Event Reporting System (FAERS) reports for a specific drug. Each result describes a reported adverse reaction including patient demographics, reactions, outcome, and seriousness. Used for pharmacovigilance and post-market safety analysis.

Look up FDA drug label info by NDC code, brand name, or generic name. Returns indications, dosage, warnings, contraindications, mechanism, manufacturer, and DEA scheduling. Used for clinical decision support, pharmacy automation, drug-info chatbots.

FDA drug enforcement actions (recalls). Filter by product name, recall classification (I=most severe, II, III), state, or date range. Useful for pharmacy compliance, supply chain monitoring, pharmacovigilance.

FDA food enforcement actions (food recalls). Filter by product description, recall classification, state, or date range. Used for retail food safety monitoring, supply chain compliance, restaurant management.

Branch-office deposit data from the FDIC Summary of Deposits (annual snapshot). Returns deposits per branch sorted by deposit volume, useful for measuring local-market banking concentration.

List FDIC bank failures. Filter by state and/or date range. Returns failure date, institution name, location, estimated cost, and resolution type. Sorted most-recent first. Use this for systemic-risk research, historical bank-stability analysis, or compliance work.

Get quarterly financial data for a specific bank by CERT number (FDIC Certificate Number). Returns recent quarters of assets, deposits, loans, capital ratios, income, and asset quality metrics. Most recent quarters first.

Institution history events for a specific bank by CERT: mergers, acquisitions, name changes, charter conversions, failures. Returns most-recent first.

Search FDIC-insured banks and savings institutions by name, state, or city. Returns CERT number, name, location, total assets, deposits, net income, ROA, ROE, charter class. Use the CERT number for follow-up queries to fdic_financials or fdic_history.

Industry-level summary financials. Returns year-by-year aggregates across all FDIC-insured institutions, optionally filtered to a single state. Useful for macro banking-sector analysis.

Get full detail for a single federal candidate by FEC candidate_id (e.g. 'P80001571'). Includes office, party, status, election years, and mailing address. Use fec_candidate_search to find the candidate_id.

Get aggregate campaign finance totals for a candidate by FEC candidate_id, broken down by election cycle. Includes total receipts, disbursements, individual contributions, cash on hand, and debts. Filter to one cycle with the cycle parameter.

Search federal candidates (President, House, Senate) by name, state, office, or party using FEC data. Returns candidate IDs needed for the other FEC tools.

Search FEC-registered political committees (campaign committees, PACs, party committees, Super PACs) by name, state, or committee type. Returns committee IDs.

List independent expenditures (FEC Schedule E) supporting or opposing a candidate or made by a committee. Shows spender committee, amount, date, support/oppose, and description. Provide candidate_id or committee_id.

FEMA flood zone designation for an address or coordinate. Returns the zone code, plain-English risk, BFE if applicable, FIRM panel reference, and whether NFIP insurance is mandated for federally-backed mortgages.

Check if a trucking company is legally authorized to operate and has valid insurance. Returns operating authority status (common, contract, broker - active/inactive/revoked), BIPD insurance, cargo insurance, bond/surety status, and whether they're allowed to haul freight. Use this for questions like 'can this carrier legally operate?', 'do they have insurance?', 'is this broker licensed?', 'verify carrier authority', 'check trucking company credentials', 'is this freight company legit?', or any carrier compliance check.

Compare 2 to 5 trucking companies side by side on safety, fleet size, insurance, and authority. Returns a comparison table: fleet size, driver count, safety rating, crash history, BASIC safety scores, authority status, insurance, and out-of-service rates. Use this for questions like 'which carrier is safer?', 'compare these trucking companies', 'which freight company should I use?', 'evaluate these carriers against each other', 'help me pick between these haulers', or any carrier vetting decision.

Look up a trucking company, freight carrier, or motor carrier by DOT number or MC number. Returns company name, address, phone, fleet size, number of drivers, safety rating, operating authority, insurance status (BIPD, cargo, bond), crash history, inspection rates, and out-of-service percentages. Use this for questions like 'is this carrier safe?', 'look up this trucking company', 'check this DOT number', 'verify this carrier', 'what's their safety rating?', or any freight carrier lookup. Covers all US carriers registered with FMCSA.

Search for trucking companies, freight carriers, or motor carriers by company name. Find any carrier's DOT number, MC number, location, fleet size, and operating status. Supports partial name matching. Use this for questions like 'find this trucking company', 'what's the DOT number for Werner?', 'search for freight carriers in Texas', 'look up this logistics company', or any carrier name search. Returns up to 50 matching carriers from the FMCSA national database.

Get safety information for a trucking company by DOT number. Returns either CSA BASIC percentile scores (where FMCSA publishes them, rare per FAST Act 2015 restrictions) OR a public safety summary built from crash counts, fatal/injury crashes, driver/vehicle/hazmat out-of-service rates, and inspection volumes (always available). Use this for questions like 'is this carrier safe?', 'what's their safety record?', 'how many crashes?', 'should I hire this carrier?', 'check their inspection history', or any trucking safety evaluation. Higher BASIC percentiles = worse record. For OOS rates, lower is better; national averages provided for comparison.

List the most popular FRED series in a category. Category IDs are numeric (e.g. 32991 = Interest Rates, 32263 = Money Stock, 9 = National Accounts). Use this to browse FRED structurally rather than via search.

Compare 2 to 5 FRED series side-by-side over the same date range. Returns observations for each series. Useful for ratio analysis (e.g. compare 10Y vs 2Y yield) or cross-series correlation.

Get time-series observations for a FRED series ID. Workhorse query for any economic indicator. Optional date range, units transformation (lin, chg, pch, log, etc.), and frequency aggregation (m, q, a).

Quick-access wrapper for the most-queried FRED indicators by friendly name. Avoids needing to memorize FRED series IDs. Valid indicators: unemployment_rate, fed_funds, fed_funds_target, cpi, core_cpi, gdp, real_gdp, ten_year_yield, two_year_yield, thirty_year_yield, thirty_year_mortgage, m2, industrial_production, retail_sales, nonfarm_payrolls, housing_starts, case_shiller, vix, wti, brent, natural_gas_henry_hub, dollar_index, consumer_sentiment, initial_claims, pce_inflation, recession_indicator.

Browse FRED economic releases (e.g. Employment Situation, CPI, GDP). With upcoming_dates=true, returns the upcoming release calendar instead. Useful for knowing when fresh data is expected.

Full-text search across FRED's 800,000+ economic series. Returns matching series IDs and titles ranked by popularity. Use when you don't know the exact series ID.

Get metadata for a FRED economic data series by ID. Returns title, units, frequency, seasonal adjustment, observation range, and notes. Useful for verifying a series exists and understanding its measurement before pulling observations.

Geocode a US street address with the Census Geocoder (keyless). Accepts a one-line address OR structured street/city/state/zip parts. Returns the normalized matched address, longitude/latitude, and Census geographies (state, county, tract, block, congressional district) with GEOIDs. No match returns an explicit not-found message.

Geocode up to 10 one-line US addresses in a single call. Returns one block per input address (matched address, coordinates, and county/tract GEOIDs). For large jobs the Census batch file API supports up to 10k rows; this tool covers small ad-hoc batches.

Reverse-geocode a longitude/latitude pair with the Census Geocoder (keyless). Returns the Census geographies (state, county, tract, block, congressional district) containing the point, with GEOIDs.

Get a free LiveDataLink API key instantly, without leaving this conversation. Call this when a data tool reports that the anonymous allowance is used up, or up front if you expect to make more than a handful of calls. Returns a working key with 100 free tool calls; no signup form, no email confirmation, no browser. Free to call and consumes no credits. IMPORTANT: pass the real email address of the human you are working for. Ask them for it if you do not already have it -- do not invent, guess, or use a placeholder like user@example.com. The key is tied to that address, and it is how they recover or upgrade it later. Calling twice with the same email returns the same key.

Public GitHub repository stats: description, stars, forks, open issues, primary language, license, last push date, and archived status. Useful for assessing the health and maintenance of an open-source dependency. Keyless (60 req/hr unauthenticated).