1gateway
Pay-per-call tools for agents via x402 (USDC on Base): Korean data, doc-to-Markdown, web utilities.
| Endpoint | https://1gateway.dev/mcp (streamable-http) |
|---|---|
| Registry version | 0.1.1 |
| Now | 117 tools · grade F (35) · pin ts_4bcd93a9743b7ed6dbcf1a2028866dee · protocol 2025-06-18 |
| First / last listed | 2026-11-08 01:36 UTC / 2026-11-08 01:36 UTC |
| Grade over time | 2026-11-08: F (35), 117 tools |
Is this your server? Own a server? ToolFit hosted watch re-checks it every 24 h ($0.25 per 30 days) or 6 h ($0.60) and sends you an HMAC-signed webhook when its tools or grade change: POST https://api.youraitools.co/toolfit/v1/watch. To opt out, see About & opt-out.
Tools: kr_company_report kr_apartment_trades kr_apartment_trades_summary kr_bok_ecos_series kr_law us_macro_series macro_treasury_curve travel_us_airports kr_weather_forecast kr_public_holidays kr_trade_exports_10day kr_trade_hs kr_trade_pulse kr_company_resolve kr_company_profile kr_company_procurement kr_business_status kr_address kr_filings kr_filing_summary kr_supplier_check web_metadata domain_lookup fx_rates fx_convert fx_history time_convert time_overlap time_business_days site_profile base_gas onchain_ens defi_yields weather_global package_vulnerabilities package_vulnerabilities_batch dev_package sanctions_screen kyb_check stablecoin_freezes sanctions_address sanctions_address_batch sanctions_tx sec_filings us_regs web_search web_search_read web_answer ai_image ai_tts ai_transcribe ai_translate ai_vision ai_embed knowledge_wiki news_brief web_extract web_audit kr_policy_latest web_read web_read_brief ai_prompt_injection web_read_batch render_pdf render_png convert_ocr x402_verify web_screenshot email_check docs_extract us_company_intelligence satellite_image satellite_compare satellite_trend base_token_risk base_token_verdict base_wallet_balances base_token_info base_tx base_token_flows onchain_prices base_wallet_related rwa_treasuries token_controls proof_of_reserve onchain_prices_batch token_report tx_explain sol_token_info sol_token_risk sol_meme_launches rh_stock_tokens sol_wallet_balances sol_tx llm_model_prices x402_api_recommend x402_lint x402_preflight hl_perp_metrics hl_funding_screener hl_funding_history hl_extremes sepolia_eth sepolia_eth_1 base_sepolia_eth base_sepolia_eth_1 crypto_perp_screener crypto_perp_basis crypto_perp_funding hl_candles hl_liquidations crypto_stablecoins crypto_pulse hl_orderbook crypto_etf hl_markets convert_to_markdown
kr_company_report | Use when an agent needs an English due-diligence brief on a South Korean company. Input: business_number, dart_corp_code, stock_code or q (exact name); format=json|markdown; news=true|false. Output: JSON summary, business overview, annual financials (revenue, profit, debt, YoY), major shareholders, procurement, DART events (90 d), risk, sanctions, data gaps, sources. AI-written; not advice. Exampl params: q, business_number, stock_code, dart_corp_code, format, news |
kr_apartment_trades | Use when you need actual apartment sale prices in a South Korean district for a month (property research, valuation, comps). Data: MOLIT (Korea land ministry) reported deals since 2006, updated daily. Input: region (5-digit LAWD_CD, e.g. 11680 Gangnam-gu), month (YYYYMM). Output: JSON trades with contract date, complex (Korean + romanized), area m2, floor, build year, price in KRW and USD, price p params: region*, month* |
kr_apartment_trades_summary | Use when you need a quick housing-market snapshot for a South Korean district-month instead of raw trades. Data: MOLIT reported apartment sales, cancelled deals excluded. Input: region (5-digit LAWD_CD, e.g. 11680), month (YYYYMM). Output: JSON count, median/average/min/max price and price per m2 and per pyeong in KRW and USD, breakdown by size class, top complexes by volume. Example: ?region=1168 params: region*, month* |
kr_bok_ecos_series | Use when you need official Bank of Korea statistics (base rate, money supply, key indicators) as a time series. Input: stat (ECOS table code, e.g. 722Y001), cycle (A/S/Q/M/SM/D), start, end (period format of cycle), optional item (e.g. 0101000). Output: JSON series with English labels, units, observations [{period,value}] (max 1,000 rows) and source attribution. Only BOK-authored tables are served params: stat*, cycle*, start*, end*, item |
kr_law | Use when you need the official text of a South Korean statute, decree or rule, or one article of it. Statutes only: no court decisions or personal data. Input: q (statute name in Korean, e.g. 근로기준법) or mst (law serial no.), optional article (e.g. 2), limit (articles, 1-100, default 30). Output: JSON law metadata (ministry, effective date), articles [{label,title,text}] in original Korean, official params: q, mst, article, limit |
us_macro_series | Use when you need a US macro time series (pairs with Korea's Bank of Korea series). Input: series (unemployment_rate, cpi, core_cpi, payrolls, avg_hourly_earnings, ppi, public_debt, avg_rate_bills, avg_rate_notes, avg_rate_bonds), optional start, end (years, max 10-year span, default last 3 years). Output: JSON title, unit, frequency, observations [{period,value}], latest and source attribution. D params: series*, start, end |
macro_treasury_curve | Use when an agent needs the official US Treasury par yield curve for a day or a recent stretch. Input: optional date (YYYY-MM-DD, default latest), days (1-366 history ending at date). Output: JSON yields per tenor (1m to 30y, percent), 2s10s and 3m10y spreads in bp, inversion flags, change over the range, history. Weekend or holiday dates fall back to the prior business day. Example: ?days=5 Price params: date, days |
travel_us_airports | Use when an agent must know if a US airport has a ground stop, ground delay program, closure or arrival/departure delay right now. Input: optional airport (FAA/IATA 3-letter like JFK, or ICAO like KJFK); none = every affected airport. Output: JSON per airport flags, max delay minutes, events with reason, avg/max delay, trend, end/reopen times, FAA update time. Not for flight planning. Example: ?ai params: airport |
kr_weather_forecast | Use when you need the official weather forecast for a point in South Korea for the next ~3-5 days. Data: KMA (Korea Meteorological Administration) village forecast on a 5 km grid, issued 8 times a day. Input: lat, lon (WGS84 decimal; Korea only). Output: JSON hourly then 3-hourly temperature C, sky, precipitation type and probability %, rain and snow amounts, humidity %, wind; plus daily min/max. params: lat*, lon* |
kr_public_holidays | Use when you need South Korea's official public holidays for a year (business-day calculation, scheduling, settlement and payroll calendars). Data: KASI (Korea Astronomy and Space Science Institute) special-day register, incl. substitute and temporary holidays once promulgated. Input: year (YYYY, 2004-2100). Output: JSON list with date, weekday, Korean and English name, isPublicHoliday, kind. Exam params: year* |
kr_trade_exports_10day | Use when you need South Korea's earliest export read: the Korea Customs 10-day provisional release (days 1-10, 1-20, full month; out on the 11th, 21st and 1st). Input: optional month (YYYYMM) and period (10, 20, full); default latest. Output: JSON exports in USD with YoY %, latest 10-day increment, 10 key items (semiconductors, cars, ships...) and 10 markets (China, US, EU, Vietnam...) with YoY an params: month, period |
kr_trade_hs | Use when you need South Korea's monthly trade for a product by HS code (e.g. 8542 chips, 870323 cars, 2710 petroleum). Data: Korea Customs Service, finalized monthly. Input: hs (2-10 digit prefix), optional month (YYYYMM, default latest), limit (1-100), sort (exports, imports, balance, total). Output: JSON totals (exports FOB, imports CIF, balance in USD, kg) with YoY % and 10-digit HSK lines with params: hs*, month, limit, sort |
kr_trade_pulse | Use when you need a one-call read on South Korea's export cycle for macro, FX or chip-sector analysis. Data: Korea Customs 10-day and monthly releases. Input: none. Output: JSON headline (latest exports and YoY, semiconductor share, strongest/weakest item and market, 3-month average YoY, momentum), latest release by item and market, 12 monthly export totals with YoY, and HS 8542 integrated-circuit params: none |
kr_company_resolve | Use when an agent must identify a South Korean company before looking up its profile or public-procurement record. Input: one of business_number (10 digits), dart_corp_code, stock_code (KRX, e.g. 005930) or q (company name, exact match ignoring 주식회사/(주)/spacing); first wins. Output: JSON companies with stable companyId, Korean and English names, stock code, DART code, match type, ambiguous flag. D params: q, business_number, stock_code, dart_corp_code |
kr_company_profile | Use when an agent needs a normalized profile of a South Korean company for KYB, research or sales. Input: id (companyId from /v1/kr/company/resolve). Output: JSON profile: names, business/corporate/DART/stock ids, market, KSIC code, founding date, fiscal year end, address, homepage, KONEPS supplier registration. No CEO names. DART data is a weekly snapshot of KRX-listed companies (asOf in response params: id* |
kr_company_procurement | Use when an agent needs a South Korean company's government contract wins for sales, credit or competitor research. Input: id (companyId) or business_number; optional from/to (YYYY-MM-DD, max 366 days, default last 12 months), category (goods,works,services,foreign), min_amount, limit, offset. Output: JSON summary (award count, total and largest KRW, top agencies) and awards with title, agency, am params: id, business_number, from, to, category, min_amount, limit, offset |
kr_business_status | Use when an agent must check that a South Korean business is still operating before paying, contracting or onboarding it (KYB, invoice checks). Input: b_no (1-20 business registration numbers, comma-separated, hyphens ok). Output: JSON per number: status (active, suspended, closed, unregistered), VAT taxpayer type, closure date, tax-type change and e-invoice dates, companyId. Data: National Tax Se params: b_no* |
kr_address | Use when an agent must normalize or translate a South Korean address (shipping, checkout, KYC forms). Input: q (Korean address or part of one, e.g. road name + number or neighborhood + lot number), optional limit (1-5). Output: JSON matches with official road-name and lot-number addresses in Korean and English, postal code, building name, admin and road codes. Data: Ministry of the Interior road-n params: q*, limit |
kr_filings | Use when an agent needs recent material disclosures of a South Korean listed company (rights offerings, CBs, buybacks, M&A, litigation, earnings, periodic reports). Input: corp (DART corp_code, KRX stock code or kr-dart- id) or q (exact name), optional days (1-365, default 30); or date (YYYY-MM-DD, KST). Output: JSON list with rceptNo, date, Korean title, English type label, DART link. Summaries: params: corp, q, date, days, limit |
kr_filing_summary | Use when an agent needs a Korean corporate disclosure in English. Input: rcept_no (14-digit DART receipt number from /v1/kr/filings). Output: JSON with headline, what_happened, key_figures (amounts, ratios, share counts with units), parties, key_dates, why_it_matters, confidence, original Korean title and DART link. Machine-generated paraphrase, not the official text. Unknown rcept_no or model out params: rcept_no* |
kr_supplier_check | Use when an agent must vet a South Korean supplier or counterparty before paying, contracting or onboarding it. Input: one of business_number, dart_corp_code, stock_code or q (exact company name). Output: JSON summary (riskLevel, riskFlags such as closed/suspended or sanctions match, per-section status) plus NTS status, DART profile, 12-month KONEPS award summary and OFAC/EU/UK screening of the En params: q, business_number, stock_code, dart_corp_code |
web_metadata | Use when an agent needs to know what a URL is before reading it, or to build a link preview or citation. Input: url (public http/https). Output: JSON with final URL after redirects, HTTP status, content type, title, description, site name, language, canonical, preview image, favicon, Open Graph and Twitter tags, RSS/Atom feeds, hreflang alternates, JSON-LD types, robots, first H1. No JavaScript is params: url* |
domain_lookup | Use when an agent must check a domain: does it resolve, who hosts its DNS and mail, is email authenticated, how old is it, when does it expire. Input: domain (e.g. example.com; URLs accepted). Output: JSON DNS records (A, AAAA, CNAME, MX, NS, TXT, CAA, SOA), mail provider, parsed SPF and DMARC, DNS provider, and RDAP registration (registrar, created, expires, age in days, status, DNSSEC). No conta params: domain* |
fx_rates | Use when you need an official daily FX rate or currency conversion (USD, EUR, KRW, JPY, CNY, GBP + 24 more). Input: base (default EUR), optional symbols (comma list), date (YYYY-MM-DD, last ~90 days; weekends use the prior fixing), amount. Output: JSON rates for the fixing date, % change vs prior fixing, converted amounts, raw ECB EUR rates. Source: ECB statistics, updated each TARGET day ~16:00 C params: base, symbols, date, amount |
fx_convert | Use when you need to convert an amount between currencies (USD↔KRW, EUR→JPY, ...) at the official ECB reference rate, today or on a past date. Input: from, to (1–10 comma-separated), amount (default 1), optional date (YYYY-MM-DD since 1999-01-04; weekends use the prior fixing). Output: JSON per target rate, inverse rate and converted result, the fixing date used. Source: ECB statistics; reference params: from*, to*, amount, date |
fx_history | Use when you need a historical exchange-rate series or a period summary (e.g. USD/KRW over the last quarter). Input: symbols (1–10), base (default EUR), start and end (YYYY-MM-DD since 1999-01-04; default last 30 days; max 366 days). Output: JSON daily series of ECB fixings, and per currency first/last, % change, min/max with dates, average and daily volatility. Source: ECB statistics; reference o params: symbols*, base, start, end |
time_convert | Use when scheduling across time zones or turning a local time into UTC without guessing DST. Input: to (IANA zones or KST, PST, CET...), optional from (zone of a local time, default UTC), time (ISO 8601, Unix seconds, or now). Output: JSON UTC instant, Unix time, and per zone: local ISO time with offset, weekday, abbreviation, DST and business-hours flags, day difference. Example: ?time=2026-10-12 params: to*, from, time |
time_overlap | Use when scheduling a meeting across time zones. Input: zones (2-10, IANA or KST/PST/CET), date, work_start/work_end (default 09:00-18:00), include_weekends. Output: JSON overlap windows in UTC and every zone's local time, top 3 one-hour slots ranked by distance from each zone's day edges, partial windows when no full overlap, next DST change per zone. Example: ?zones=America/New_York,Europe/Londo params: zones*, date, work_start, work_end, include_weekends |
time_business_days | Use when computing due dates, SLAs, settlement or delivery dates. Input: start date, then days (add -260..260 business days) or end (count business days between), optional country KR, US, GB, DE, FR or JP for public holidays (omit = weekends only). Output: JSON result date or business/calendar day counts, holidays skipped on the way, holiday scope. Example: ?start=2026-12-22&days=5&country=US Pric params: start*, days, end, country |
site_profile | Use when an agent must vet or research a website in one call (lead research, security or SEO check, is this site legit). Input: url or bare domain. Output: JSON page metadata, HTTP status, HTTPS and HTTP-to-HTTPS redirect, server and hosting hints, 7 security headers, robots.txt (sitemaps, AI-crawler rules), llms.txt presence, plus domain DNS, mail provider, SPF/DMARC and RDAP registrar, age and e params: url* |
base_gas | Use when an agent must price, time or route a transaction. Input: optional chain (base default, ethereum, arbitrum, monad, all). Output: JSON base fee, priority tiers (last 20 blocks), suggested maxFeePerGas, block fullness, typical cost of transfer, approve, DEX swap, mint, deploy in gas token (ETH, MON) and USD (Base adds L1 data fee); chain=all adds a compare table and the cheapest chain per ac params: chain |
onchain_ens | Use when an agent must send funds to an ENS name or label a wallet. Input: name (e.g. ens.eth, ENSIP-15 normalized) or address. Output: JSON resolve: address, resolver, avatar/url/description/twitter/github records, contenthash (name+address: matchesExpected); reverse: primary name only if forward-verified. Ethereum mainnet registry; wildcard/offchain resolvers not followed. Example: ?name=ens.eth params: name, address |
defi_yields | Use when an agent must compare lending yields on Base. Input: optional protocol (aave-v3,compound-v3,morpho,moonwell) and asset (USDC,WETH,cbBTC,wstETH,cbETH,EURC). Output: JSON per market supply/borrow APY, utilization, supplied/borrowed amount and TVL in USD, sorted by supply APY, with block. Computed from contract state; base rates, rewards excluded; not advice. Example: ?asset=USDC Price: $0.0 params: protocol, asset |
weather_global | Use when an agent needs the weather anywhere in the world. Input: lat, lon, optional hours (0-72 hourly steps, default 24), tz (IANA zone for daily summaries, default UTC). Output: JSON current temperature, symbol, wind, humidity, cloud, pressure; hourly series; daily min/max, precipitation, max wind, symbol for ~10 days. Data: MET Norway. Example: ?lat=51.5072&lon=-0.1276&tz=Europe/London Price: params: lat*, lon*, hours, tz |
package_vulnerabilities | Use when an agent must check a dependency before installing or upgrading: is this exact package version vulnerable? Input: package, ecosystem (npm, PyPI, Go, Maven, crates.io, NuGet, RubyGems, Packagist...), version. Output: JSON vulnerable yes/no, counts by severity, advisories (GHSA/CVE id, summary, severity, CVSS, CWE, fixed versions, links). Data: OSV.dev. Example: ?package=lodash&ecosystem=np params: package*, ecosystem*, version* |
package_vulnerabilities_batch | Use when an agent must scan a project's dependencies before install, upgrade or merge. Input: packages, up to 20 ecosystem:name@version, comma-separated (npm, pypi, go, cargo/crates.io, maven, nuget...). Output: JSON summary (vulnerable count, critical/high/moderate/low), per package vulnerable yes/no, counts, top advisories with CVE, severity, fixed versions, osv.dev links. Data: OSV.dev, CC BY 4 params: packages*, ecosystem |
dev_package | Use when an agent must decide whether to add or keep a dependency. Input: package, ecosystem (npm, PyPI, crates.io), optional version (default latest). Output: JSON flags (deprecated, yanked, outdated, vulnerable, no_license, no_release_2y), latest version, license, publish dates, maintainer count, downloads, repository, OSV advisories. Example: ?package=request&ecosystem=npm Price: $0.01 USDC (Ba params: package*, ecosystem*, version |
sanctions_screen | Use when an agent must check a person, company, vessel or aircraft against the U.S. Treasury OFAC SDN list before paying, onboarding or shipping. Input: name (fuzzy, aliases included), optional type, min_score, limit. Output: JSON potential matches with score, SDN entry, programs, countries, aliases, OFAC link, list as-of date, data age. Not a legal determination. Example: ?name=Lazarus+Group Pric params: name*, type, min_score, limit, lists |
kyb_check | Use when an agent must vet a company or counterparty before paying, onboarding or invoicing. Input: name, optional country (ISO2), lei, vat (EU, with prefix). Output: JSON summary (sanctions hits, LEI found/status, VAT valid), sanctions matches across OFAC SDN, EU and UK lists, GLEIF entity record with parents, VIES VAT result; a down VIES/GLEIF marks only that part. Not a legal determination. Exa params: name*, country, lei, vat |
stablecoin_freezes | Use when an agent needs recent issuer freezes of USDC, EURC (Ethereum, Base) and USDT (Ethereum), or whether an address is frozen now. Input: optional address, days (1-7, default 1), chain (all, ethereum, base), token. Output: JSON events (token, chain, freeze/unfreeze/destroy_funds, address, amount, block, approx time, tx), counts per token, live frozen status per token for the address. Issuer ac params: address, days, chain, token |
sanctions_address | Use when an agent must check a crypto wallet against the digital currency addresses on the U.S. Treasury OFAC SDN list before paying or accepting funds. Input: address (EVM matched on every EVM chain; BTC, TRX, SOL...), optional chain. Output: JSON listed yes/no, SDN entry, programs, listed currency and network, OFAC link, list as-of date, data age. Not a legal determination. Example: ?address=0x0 params: address*, chain |
sanctions_address_batch | Use when an agent must screen many wallets at once (payouts, counterparty lists) against OFAC SDN wallet addresses. Input: addresses (1-50, comma-separated, mixed chains) or POST JSON {addresses:[...]}. Output: per address listed yes/no, detected chains, SDN entity, programs; summary counts; list date. Unknown formats refused before payment. Not a legal determination. Example: ?addresses=0x098B716 params: addresses* |
sanctions_tx | Use when an agent must check a transaction before accepting or relaying funds: screens its direct parties (sender, recipient, contracts, token Transfer parties on Base; accounts and token owners on Solana) against OFAC SDN wallet addresses. Input: tx, network (eip155:8453 default, or solana). Output: verdict, parties, roles, listed yes/no, SDN entity, programs, tx status, list date. Bad formats re params: tx*, network |
sec_filings | Use when an agent needs a U.S. public company's SEC filings: latest 10-K/10-Q, 8-K events, proxies, S-1s. Input: ticker or cik, optional form (comma list, e.g. 10-K,8-K), since (YYYY-MM-DD), limit. Output: JSON company profile (CIK, name, industry, exchange, fiscal year end) and filings with dates, 8-K item codes and titles, XBRL flags, sec.gov links. Insider forms without filer names. Data: SEC E params: ticker, cik, form, since, limit |
us_regs | Use when an agent must track new U.S. rules, proposed rules, agency notices and fresh SEC disclosures. Input: optional q (topic), agency (Federal Register slug), doc_type, form (8-K, 13F-HR, NPORT-P...), source, days, limit. Output: JSON Federal Register documents (type, agencies, abstract, effective/comment dates, CFR, links) and latest SEC filings by companies/funds (form, filer, CIK, filed, lin params: q, agency, doc_type, form, source, days, limit |
web_search | Use when an agent needs current web results for a query. Input: q, optional max (1-10, default 5), time_range (day, week, month, year). Output: JSON results with title, URL and date when known, provider and retrieval time. For page text use /v1/web/search-read. Provider failure is not charged. Example: ?q=x402+payment+protocol&max=5 Price: $0.006 USDC (Base or Solana) via x402. params: q*, max, time_range |
web_search_read | Use when an agent needs to search and read in one call. Input: q, optional max (1-10, default 5), time_range (day, week, month, year). Output: JSON results (title, URL, date) and, for the top 3, the page converted to Markdown (up to 4,000 characters each; a page that fails is marked, the rest still ship). Provider failure is not charged. Example: ?q=EU+AI+Act+timeline&max=5 Price: $0.02 USDC (Base params: q*, max, time_range |
web_answer | Use when an agent needs a sourced answer to a question from the live web in one call. Input: q (question), optional time_range (day, week, month, year). Output: JSON answer (English, inline [n] citations), citations [{url, title, quote}], confidence, notes, sources read. Searches, reads the top 4 pages itself and answers only from them. Provider or model failure is not charged. Example: ?q=what+is params: q*, time_range |
ai_image | Use when an agent needs an image from a text prompt. Input: prompt (max 1000 chars), optional steps (1-8, default 4). Output: JSON with a 1024x1024 JPEG (base64), steps, model, safety verdicts. Prompt screened by blocklist + Llama Guard 3, image by a vision check; sexual, minor, deepfake or gore requests refused 422, not charged. Not stored. Example: ?prompt=isometric%20illustration%20of%20a%20tin params: prompt*, steps |
ai_tts | Use when an agent needs spoken audio from short text (voice reply, narration, accessibility). Input: text (max 500 chars), lang (en, ko, ja, zh, es, fr; default en). Output: JSON with an MP3 (base64), voice, model, safety verdict. Fixed built-in voices, no voice cloning. Text screened by Llama Guard 3; unsafe 422, not charged. Not stored. Example: ?text=Hello%20from%201gateway&lang=en Price: $0.00 params: text*, lang |
ai_transcribe | Use when an agent must turn audio into text (meetings, calls, voice notes). Input: POST a file (multipart 'file', raw body, JSON audioBase64) or url; mp3, wav, m4a, ogg, webm, flac, max 25 MB / 10 min. Output: text, language, timestamped segments, word count, duration; summary=true adds summary, key points, action items. $0.006 per started minute (+$0.004 summary), quoted before payment. Not store params: url, audioBase64, summary, language |
ai_translate | Use when an agent must translate text (replies, documents, transcripts). Input: text (max 1500 chars, GET or POST JSON), target language code, optional source (auto-detected for Korean, Japanese, Chinese, Cyrillic, Arabic, Hindi, Thai; Latin script defaults to English). Output: translatedText, source, target, model. Not stored. Example: ?text=Hello%2C%20how%20are%20you%3F&target=ko Price: $0.002 U params: text*, target*, source |
ai_vision | Use when an agent must understand a picture (screenshot, product photo, chart, scene). Input: url of a png, jpeg, webp or gif (max 5 MB), optional question (max 1000 chars), optional json=true for fields (objects, text, people count, colors...). Output: answer or fields, image info, model. Does not name people; exact text: /v1/convert/ocr. Not stored. Example: ?url=https://upload.wikimedia.org/wik params: url*, question, json |
ai_embed | Use when an agent needs vectors for search, RAG, clustering or dedup. Input: text (GET) or POST JSON {texts:[...]} with up to 32 strings of max 2000 chars each. Output: model, dims (1024), embeddings with index and vector; compare with cosine similarity. Multilingual (100+ languages, strong Korean). Not stored. Example: ?text=x402%20pay-per-call%20API Price: $0.003 USDC (Base or Solana) via x402. params: text, texts |
knowledge_wiki | Use when an agent needs a quick, cited fact sheet on a place, organization, thing or concept. Input: q (topic or title), optional lang (Wikipedia code, default en). Output: JSON title, description, extract, coordinates, thumbnail, page URL, Wikidata facts (instance of, inception, country, official website), CC BY-SA attribution. Best title match if not exact. Example: ?q=Seoul&lang=en Price: $0.00 params: q*, lang |
news_brief | Use when an agent needs what is happening on a topic right now, in English, including Korean and Asian news. Input: topic, optional time_range (day, week default, month, year), max (1-10 headlines, default 10). Output: JSON overview, clusters [{headline, summary, sources}] with duplicates merged, and sources (title, url, outlet, publishedAt). Headlines and links only. Failures not charged. Example params: topic*, time_range, max |
web_extract | Use when an agent needs specific fields from a web page as JSON. Input: url, schema (URL-encoded JSON Schema, object root, max 30 properties, depth 3, 3,000 chars). Output: JSON data validated against the schema (null when not on the page), title, finalUrl. SSRF-safe; noai pages refused; bad schema refused before payment. Fixed schema: /v1/docs/extract. Example: ?url=https://example.com/&schema={" params: url*, schema* |
web_audit | Use when an agent must grade a website and say what to fix. Input: url or bare domain. Output: JSON score 0-100, grade A-F, per-category scores (security, https, seo, mail, ai), findings [{id, severity, category, title, fix}] and top fixes. Rule-based from one live fetch plus DNS; raw data: /v1/web/site-profile. Example: ?url=stripe.com Price: $0.006 USDC (Base or Solana) via x402. params: url* |
kr_policy_latest | Use when an agent tracks South Korean government policy, regulation or draft legislation in English. Input: optional q (keyword, Korean or English), date (YYYY-MM-DD KST), limit (1-20, default 5). Output: JSON items with Korean title, official link, published time and English brief {title_en, summary_en, agency_en, category, key_points}. Machine translation; check the official page. Example: ?q=AI params: q, date, limit |
web_read | Use when an agent already has a URL and needs the page as clean Markdown (boilerplate removed, tables kept). Input: url, optional max_chars (500-60000), flags=1 for rule-based prompt-injection signals. Output: JSON markdown, title, language, finalUrl, chars, truncated. SSRF-safe; pages opting out with noai are refused. English brief: /v1/web/read/brief. Search+read: /v1/web/search-read. Example: ? params: url*, max_chars, flags |
web_read_brief | Use when an agent needs a page in any language (Korean, Japanese, etc.) read and briefed in English. Input: url, optional max_chars, flags=1. Output: JSON markdown, title, plus brief {headline, summary, key_points, entities, topics, source_language, content_type}; fixed schema, cached by content. Model outage or daily cap is refused before payment. Example: ?url=https://example.com/ Price: $0.006 params: url*, max_chars, flags |
ai_prompt_injection | Use when an agent must screen untrusted text (web page, email, tool output, RAG chunk) before an LLM reads it. Input: text (up to 20,000 chars, POST JSON or GET) or url. Output: JSON probability 0-1, verdict (clean/suspicious/injection), attackTypes, spans with offsets, sanitizedText with flagged spans removed, method (rules + open-model classifier; rules only if the model is down). Heuristic, not params: text, url |
web_read_batch | Use when an agent has several URLs (search results, citations) and needs them all as Markdown at once. Input: urls (1-5 public URLs separated by spaces), optional max_chars per URL (500-20000), flags=1. Output: JSON results[] in input order, each status ok (markdown, title, finalUrl) or error (code, message). Charged once if at least one page is read. Example: ?urls=https://example.com/ https://ex params: urls*, max_chars, flags |
render_pdf | Use when an agent must hand over a document as a PDF (report, invoice, summary, receipt). Input: GET ?url= for a public page, or POST JSON {html | markdown | url, format A4|Letter, landscape, margin_mm}. Markdown gets a clean stylesheet with Korean fonts. Output: JSON fileBase64 (decode to the PDF), bytes, page settings. Headless Chrome on Cloudflare. Bad input or daily cap refused before payment. params: url, format, landscape, margin_mm, markdown, html |
render_png | Use when an agent must turn its own HTML or Markdown into an image (social card, chart, table snapshot, preview) or capture a page as PNG. Input: GET ?url=, or POST JSON {html | markdown | url, width 320-1920, full_page}. Korean fonts included. Output: JSON fileBase64 (decode to the PNG), bytes, viewport. Bad input or daily cap refused before payment. Example: ?url=https://example.com/ Price: $0.0 params: url, width, full_page, markdown, html |
convert_ocr | Use when an agent must read text from a scan, photo or screenshot: scanned PDFs (embedded page images) or PNG/JPEG/WebP up to 5 MB, Korean and English, tables kept as Markdown. Up to 3 pages per call. Input: url via GET, or POST a file (multipart 'file', raw body, or JSON contentBase64). Output: JSON markdown, pages with confidence, warnings. PDFs with selectable text: use /v1/convert/markdown. Ex params: url, contentBase64 |
x402_verify | Use when an agent or seller must confirm a payment before delivering: checks a Base, Base Sepolia or Solana transaction for a USDC transfer to pay_to of at least amount. Input: tx (hash or signature), pay_to, network (default eip155:8453), optional amount in USDC. Output: JSON paid true/false, verdict, received, payers, block, time, confirmations. Bad formats refused before payment. Example: ?tx=0 params: tx*, pay_to*, network, amount |
web_screenshot | Use when an agent must see how a page looks (layout, charts, visual QA, previews), not just its text. Input: url, width (320-1920, default 1280), full_page=1 for the whole page, format png or jpeg (default). Output: JSON imageBase64 (decode to the image), contentType, bytes, viewport. Renders JavaScript. Daily cap or bad URL refused before payment. Example: ?url=https://example.com/ Price: $0.01 U params: url*, width, full_page, format |
email_check | Use when an agent is about to email or sign up a contact. Input: email. Output: JSON verdict (deliverable, risky, undeliverable) with reasons, MX hosts, null MX, SPF and DMARC policy, disposable domain, role account, free provider. No SMTP probe, so the mailbox itself is not verified. Malformed address refused before payment. Example: ?email=info@example.com Price: $0.002 USDC (Base or Solana) via params: email* |
docs_extract | Use when an agent needs the key facts of a document, not just its text: Korean HWP/HWPX, PDF, DOCX or web page. Input: url via GET, or POST a file (multipart 'file', raw body, or JSON contentBase64+filename). Output: fixed-schema JSON title, title_en, document_type, date, org, amounts, tables (parsed rows), english_overview. Bad input or model outage refused before payment. Example: ?url=https://e params: url, type |
us_company_intelligence | Use when an agent researches a U.S. public company (due diligence, investing, competitors) and wants one sourced brief instead of many calls. Input: ticker or cik, optional news=false. Output: JSON profile, 3 fiscal years + latest quarter + balance sheet from SEC XBRL, YoY growth, rule-based risk signals (8-K items, late filings, losses) with evidence, recent 8-K events, latest news (title, link, params: ticker, cik, news |
satellite_image | Use when an agent must see a place from above or check vegetation, water or change. Input: lat, lon, radius_m (200-10000), mode (true_color, false_color, ndvi, ndwi, moisture), date, days back, max_cloud. Picks the clearest Sentinel-2 scene by cloud share inside your area, not the whole tile. Output: JSON PNG URL (+ other modes), scene date, area cloud %, alternatives. No scene: 404, not charged. params: lat*, lon*, radius_m, mode, date, days, max_cloud, size |
satellite_compare | Use when checking what changed at a place between two dates (construction, deforestation, flooding, crops). Input: lat, lon, radius_m (200-10000), before and after dates (20+ days apart). Output: JSON per date: clearest scene, area cloud %, NDVI mean/median, true color, NDVI and false color PNG URLs; NDVI change and reliability. No scene: 404, not charged. Example: ?lat=37.5665&lon=126.978&before= params: lat*, lon*, radius_m, before*, after*, window_days, size |
satellite_trend | Use when tracking crops, greenery or land change month by month. Input: lat, lon, radius_m (200-10000), months (1-12), optional end date. Output: JSON series per month: clearest scene, area cloud %, NDVI mean/median, status (ok, cloudy, no_scene), plus min/max and first-to-last change. Numbers only, no images. No scene at all: 404, not charged. Example: ?lat=36.35&lon=127.38&months=6 Price: $0.012 params: lat*, lon*, radius_m, months, end |
base_token_risk | ERC-20 token risk scan: honeypot check, rug pull check, token safety / scam check. Use when vetting a token. Input: address, chain=base|ethereum|arbitrum. Output: JSON risk signals + evidence: honeypot test (buy/sell sim, taxes), rug-pull signals (owner, mint/pause/blacklist/fee fns, proxy, owner supply, pool depth), meme, notChecked. Signals, not a safe verdict. EOA: 400, free. Example: ?address= params: address*, chain |
base_token_verdict | Use when an agent wants a quick read on an ERC-20 before trading: token-risk scan plus a short AI verdict. Input: address; chain (base, ethereum, arbitrum). Output: JSON verdict (level = deterministic riskLevel, headline, top reasons citing fired signal ids, what to watch) + all risk signals, meme block, simulation, notChecked. Signals, not advice; not a safe verdict. Bad input/EOA: 400, not charg params: address*, chain |
base_wallet_balances | Use when an agent needs an EVM wallet's holdings in one call. Input: address; chain (base default, ethereum, arbitrum, monad); optional tokens (up to 20 ERC-20s; default: main stablecoins, WETH, BTC wrappers). Output: JSON block+time, native balance (ETH; MON on Monad), per-token symbol, decimals, raw and decimal balance, nonce, isContract. Chain state only, no prices. Bad input: 400, not charged. params: address*, chain, tokens |
base_token_info | Use when an agent needs an ERC-20's basics before quoting, transferring or approving it. Input: address; chain (base default, ethereum, arbitrum, monad); optional holder (balance, share of supply) and spender (allowance, flags unlimited). Output: JSON block+time, name, symbol, decimals, totalSupply, known issuer if curated. Name/symbol are self-reported. EOA or non-ERC-20: 4xx, not charged. Exampl params: address*, chain, holder, spender |
base_tx | Use when an agent must confirm a transaction or payment landed: did it succeed, who paid whom, how much of which token. Input: hash; chain (base default, ethereum, arbitrum, monad). Output: JSON status (success/reverted), block+time, confirmations, from, to, native value, fee, decoded ERC-20 transfers with symbol and amount (first 25). Unknown or unmined hash: 404, not charged. Example: ?hash=0x28 params: hash*, chain |
base_token_flows | Use when an agent must see who is buying or dumping a Base ERC-20 now (smart money, whales, who bought/sold). Input: token address, optional wallet, minutes (1-240), limit. Output: JSON signal (smart money accumulating vs retail), whale/shark/dolphin/fish flow buckets, who bought/sold with own labels, notable wallets, repeat traders, recent/largest swaps, DEX netflow. On-chain only; address ≠ pers params: address*, minutes, wallet, limit |
onchain_prices | Use when an agent needs a token's USD price without a third-party price feed. Input: tokens (up to 10, base:0x… or sol:<mint>). Output: per token priceUsd, confidence, the pool used (Uniswap v3 / Aerodrome on Base, Orca Whirlpool on Solana; fee tier, depth in USD), path (direct USDC or via WETH/SOL), warnings; no price below $1,000 depth. Spot, not TWAP. Example: ?tokens=base:0x940181a94A35A4569E4 params: tokens* |
base_wallet_related | Use when an agent must see who an EVM wallet deals with: counterparties ranked by ERC-20 transfers, earliest inbound sender, wallets the same EOA funder also paid, tokens moved. Input: address, chain (base default, ethereum, arbitrum, monad), hours (1-24, Arbitrum 1-6, Monad 1-2; default 6), limit. Output: JSON counterparties with own labels (contract/EOA, known token), first and shared funder. ER params: address*, chain, hours, limit |
rwa_treasuries | Use when an agent tracks tokenized US Treasury / money market funds. Input: optional token (BUIDL, USDY, OUSG, USTB, USYC, BENJI), chain (all, ethereum, base). Output: JSON per token totalSupply, NAV per share from Chainlink or the issuer's onchain oracle ($1 for constant-NAV funds, null if none), AUM, mint/burn flows 24 h / 7 d in units and USD, totals. Ethereum + Base issuance only. Cached 10 mi params: token, chain |
token_controls | Use when an agent must know what an issuer can do to holders of an ERC-20 (stablecoin, RWA, ERC-3643) on Ethereum or Base. Input: address, optional chain (ethereum default, base), holder. Output: JSON capabilities (mint, burn from holder, pause, freeze/blacklist, seize, upgrade, ERC-3643), matched functions, proxy implementation, role holders, paused now, holder frozen status and balance. Example: params: address*, chain, holder |
proof_of_reserve | Use when an agent checks whether a wrapped or backed token's reported reserves cover its supply. Input: optional asset (WBTC, cbBTC, TUSD, stETH, eETH). Output: JSON per asset Chainlink Proof of Reserve value, totalSupply by chain, ratio, reserves minus supply, below-supply flag, supply coverage (full/partial), feed age vs heartbeat, stale flag, feed page. Reported reserves, not an audit. Example: params: asset |
onchain_prices_batch | Use when a trading agent needs many token prices at once plus what a buy would really cost. Input: tokens (≤25, base:0x… or sol:<mint>, ≤10 Solana), amount_usd (default 1000). Output: per token priceUsd, confidence, pool, depth and a buy estimate: tokensOut, effectivePriceUsd, priceImpactPct (Uniswap v3 QuoterV2 / Aerodrome on Base, CLMM estimate on Orca). Cached 20 s. Example: ?tokens=base:0x4200 params: tokens*, amount_usd |
token_report | Use when an agent needs one English brief on a token before trading or listing it. Input: token (base:0x… or sol:<mint>), format=json|markdown. Output: executiveSummary, riskAssessment (signals, owner/proxy or mint/freeze authority, holders), liquidity (price, depth, $1k/$10k buy impact), perpMarket (Hyperliquid, symbol match), sanctions (OFAC wallets), dataGaps. AI-written from chain facts; not a params: token*, format |
tx_explain | Use when an agent must tell a user what a transaction did. Input: tx (Base hash or Solana signature), network=eip155:8453|solana (optional, inferred). Output: explanation (1-3 sentences; every number checked against the decoded facts, template fallback), facts: status, time, fee, from/to, called function (curated selector table), ERC-20 transfers, approvals, inferred swap (sent/received), Solana p params: tx*, network |
sol_token_info | Use when an agent needs a Solana token's basics before quoting, transferring or accepting it. Input: mint. Output: JSON slot, program (spl-token or token-2022), decimals, supply raw and decimal, mint and freeze authority, Token-2022 extensions (transfer fee, permanent delegate, transfer hook, default frozen, metadata), known issuer if curated. Not a mint: 422, unknown: 404, not charged. Example: ? params: mint* |
sol_token_risk | Solana token risk scan: rug pull, scam token and token safety check. Use when buying, accepting or listing a token. Input: mint. Output: JSON riskLevel + signals w/ evidence: mint authority, freeze authority (can freeze/blacklist holders), permanent delegate, transfer hook/fee, default-frozen, mutable metadata, top-10 share; pump.fun curve %/PumpSwap LP burn, dev %. No sell simulation; not an audi params: mint* |
sol_meme_launches | Use when an agent watches new Solana meme coins. Input: optional minutes (5-60), limit (1-20). Output: JSON launch counts per 10 min from the pump.fun program, then the newest launches: mint, name/symbol, age, bonding-curve progress %, price and market cap in SOL, mint/freeze authority, holder aggregates (curve %, top-10 ex-curve %, dev %), riskLevel + signals. Aggregates only; no wallet lists. No params: minutes, limit |
rh_stock_tokens | Use when an agent integrates tokenized equities on Robinhood Chain (4663). Input: optional symbols (<=20), address, limit (1-100), feedOnly. Output: JSON per token: on-chain uid/symbol checked against the public registry, uiMultiplier vs registry, pending multiplier, paused, supply, Chainlink feed age/stale/lag, reference total-return value; US 24/5 session state. Reference signals, not market dat params: symbols, address, limit, feedOnly |
sol_wallet_balances | Use when an agent needs what a Solana address holds in one call. Input: address. Output: JSON slot, SOL balance, every non-zero token (mint, token account, program, decimals, raw and decimal balance, frozen flag; first 50), counts of token and empty accounts. Chain state only, no prices. Bad input: 400, not charged. Example: ?address=CV8t6fnSsckB3bzJSVRxQjVvTgdB35q11Fu3eaF1nz8u Price: $0.002 USDC params: address* |
sol_tx | Use when an agent must confirm a Solana payment or transaction landed: did it succeed, who paid whom, how much of which token. Input: signature. Output: JSON status (success/failed), slot, block time, confirmation status, fee payer, signers, fee, programs, SOL and token balance changes per account (first 25). Unknown signature: 404, not charged. Example: ?signature=5Xg1wCobkM4jAJNHE6t7B1amt4ch5wq5 params: signature* |
llm_model_prices | Use when an agent must price an LLM call or pick the cheapest model. Input: model (up to 5, comma list) plus optional input_tokens, output_tokens, requests; or no model plus mode, provider, min_context, capabilities (vision, function_calling...). Output: JSON USD per 1M input/output tokens, cached/batch prices, context window, provider, capabilities, cost estimate or cheapest ranking, as_of + sour params: model, input_tokens, output_tokens, requests, provider, mode, min_context, capabilities, limit, include_deprecated |
x402_api_recommend | Use when an agent must pick a paid x402 API for a task. Input: q (task in plain words or keywords), optional max_price (USD), network (base, solana or CAIP-2), limit (1-20). Output: JSON ranked endpoints: resource URL, method, description, price, networks, seller, 30-day payers and calls (Bazaar), seller buyers (x402scan), wash/quality flags, score, index as_of. Same rules for every seller. Exampl params: q*, max_price, network, limit, include_flagged |
x402_lint | Use when you sell an API over x402 and want it to pass Bazaar/CDP listing checks. Input: url (https x402 resource), method GET or POST. Output: JSON score 0-100, grade, per-check pass/warn/fail with fix hints (x402 v2 quote, accepts fields, USDC asset, payTo format and OFAC list, description quality, Bazaar schemas, header size, CORS, latency, openapi/llms.txt, ERC-8004) plus our measured uptime. params: url*, method |
x402_preflight | Use when an agent is about to pay an unknown x402 endpoint and needs a cheap safety gate. Input: url (https x402 resource), method, optional max_price_usd. Output: JSON verdict ALLOW/WARN/DENY with reasons: live quote now, price vs similar routes and your budget, payTo on the OFAC list, price change vs our last measurement, our 7-day uptime/p95, ERC-8004 registration. Never pays; cached 60 s. Exam params: url*, method, max_price_usd |
hl_perp_metrics | Hyperliquid funding for one perpetual futures market: current and predicted funding rate, open interest and basis. Use when an agent monitors a perp position or funding carry. Input: coin (e.g. BTC, kPEPE). Output: JSON as_of, cache_age_s, 1h + annualized funding, OI coin/USD, mark/oracle/mid, basis %, premium, 24h volume and change, HL predicted funding, next funding time (cross-venue: /v1/crypto params: coin* |
hl_funding_screener | Use when hunting Hyperliquid funding extremes or carry trades across all perps. Ranked by funding, open interest, volume, basis, premium or 24h change. Input: optional sort, order, limit (1-50), min_oi_usd, min_volume_usd, funding (positive/negative), min_abs_apr. Output: JSON as_of, cache_age_s, rows (1h + annualized funding, OI USD, 24h volume, basis, premium), top/bottom 5. Example: ?sort=fundi params: sort, order, limit, min_oi_usd, min_volume_usd, funding, min_abs_apr |
hl_funding_history | Use when an agent judges whether a perp's funding is unusually high or low, or tracks open-interest build-up. Input: coin (e.g. BTC), hours (24-720, default 168). Output: current 1h funding and APR, 24h/7d/30d average APR, current percentile and z-score vs 7d and 30d, share of positive hours, downsampled series, open interest now and change 1h/24h/7d (from our 5-minute snapshots). Example: ?coin=B params: coin*, hours |
hl_extremes | Use when hunting crowded perps: which markets have funding far from their own normal and where open interest is jumping. Input: optional limit (1-50, default 10), min_oi_usd (default 1,000,000). Output: as_of, fundingExtremes ranked by |z| (current 1h funding vs the coin's last 7 days), oiMovers24h and oiMovers1h (open-interest % change), each with funding APR and OI USD. Example: ?limit=10 Price: params: limit, min_oi_usd |
sepolia_eth | Use when an agent, test suite or CI job needs Sepolia gas now: one x402 call, no faucet login or mainnet history. Input: to (recipient address); sends 0.1 SepETH (1 SepETH: /v1/testnet/sepolia-eth/1). Output: JSON txHash (confirmed before settling), explorerUrl, amountEth, from, to. Daily limits (UTC): 5 SepETH per address (both sizes), 20 overall; checked before payment. Test ETH has no monetary params: to* |
sepolia_eth_1 | Use when a contract deploy, test suite or CI job needs more Sepolia gas than a faucet gives: one x402 call, no faucet login or mainnet history. Input: to (recipient address); sends 1 SepETH. Output: JSON txHash (confirmed before settling), explorerUrl, amountEth, from, to. Daily limits (UTC): 5 SepETH per address (both sizes), 20 overall; checked before payment. Test ETH has no monetary value. Exa params: to* |
base_sepolia_eth | Use when an agent, x402 test or CI job needs Base Sepolia gas now: one x402 call, no faucet login or mainnet history. Input: to (recipient address); sends 0.1 ETH (1 ETH: /v1/testnet/base-sepolia-eth/1). Output: JSON txHash (confirmed before settling), explorerUrl, amountEth, from, to. Daily limits (UTC): 5 ETH per address (both sizes), 20 overall; checked before payment. Test ETH has no monetary params: to* |
base_sepolia_eth_1 | Use when contract deploys, x402 tests or CI jobs need more Base Sepolia gas than a faucet gives: one x402 call, no faucet login or mainnet history. Input: to (recipient address); sends 1 Base Sepolia ETH. Output: JSON txHash (confirmed before settling), explorerUrl, amountEth, from, to. Daily limits (UTC): 5 ETH per address (both sizes), 20 overall; checked before payment. Test ETH has no monetary params: to* |
crypto_perp_screener | Use when an agent scans every perp listed on Hyperliquid, dYdX v4, GMX v2, Lighter and Paradex for funding arbitrage or crowding. Input: optional sort (spread, funding, oi, volume), order, limit (1-50), venues, min_venues, min_oi_usd. Output: JSON rows per coin with each venue's annualized funding, OI USD, 24h volume, max-min funding spread with short/long venue, mean APR, totals, coverage. Exampl params: sort, order, limit, venues, min_venues, min_oi_usd |
crypto_perp_basis | Use when an agent compares one coin's perp basis on DEX venues only (Hyperliquid, dYdX v4, GMX v2, Lighter, Paradex; no CEX). Input: coin, optional venues. Output: JSON per venue mark, index/oracle, premium %, annualized funding, OI USD; max-min funding spread; carry pairs ranked by funding spread. Derived statistics, not investment advice; fees and risk ignored. Example: ?coin=BTC Price: $0.003 U params: coin*, venues |
crypto_perp_funding | Use when an agent compares perpetual funding across venues for one coin (carry/crowding). Input: coin (e.g. BTC). Output: JSON venues ranked by annualized funding (DEX venues only: Hyperliquid, dYdX, GMX, Lighter, Paradex), normalized to per-hour and APR, max-min spread with short/long venue, consensus mean, Hyperliquid mark vs oracle and vs dYdX oracle basis. Derived figures only; cached 60 s. Un params: coin* |
hl_candles | Use when an agent needs price history for a Hyperliquid perp or HIP-3 market (xyz:TSLA). Input: coin, interval (1m-1M, default 1h), limit (1-500, default 100), optional start/end (ISO date or unix). Output: JSON candles (time, open, high, low, close, volume, trades) plus summary: change %, high/low, volume, annualized realized volatility. Unknown coin: 400, not charged. Example: ?coin=ETH&interval params: coin*, interval, limit, start, end |
hl_liquidations | Use when an agent sizes leverage on a Hyperliquid perp or checks how close typical positions are to liquidation. Input: coin, optional leverages (e.g. 5,10,20). Output: JSON mark, max leverage, maintenance margin, long/short liquidation price and distance % per leverage, whether the 24 h range exceeds it, 24 h high/low, OI USD, funding APR and crowded side. Estimates, not a live liquidation feed. params: coin*, leverages |
crypto_stablecoins | Use when an agent tracks stablecoin liquidity (mints/burns) as a market signal. Input: optional chain (all, ethereum, base), symbol (USDC). Output: JSON per token and chain totalSupply read onchain, change 24 h / 7 d (absolute and %), per-symbol sums, USD net change and direction, biggest movers, block numbers; peg=true adds Chainlink price, deviation bp and depeg status. Ethereum + Base only. Exa params: chain, symbol, peg |
crypto_pulse | Use when an agent needs a one-call crypto market snapshot before acting. Input: none. Output: JSON one-line summary; BTC, ETH, SOL price, 24 h change, funding APR, OI, volume; Crypto Fear & Greed value, label, 1 d/7 d change with attribution; OI-weighted perp funding with highest/lowest markets; onchain stablecoin supply and 24 h/7 d net mint or burn. Example: /v1/crypto/pulse Price: $0.002 USDC ( params: none |
hl_orderbook | Use when an agent sizes a Hyperliquid market order or compares liquidity. Input: coin (perp or HIP-3 xyz:TSLA), optional sizes_usd (up to 5, default 1000,10000,100000), levels (0-20). Output: JSON best bid/ask, spread bps, depth USD within 0.1/0.5/1/2%, imbalance, per size buy/sell average fill, worst price and slippage bps vs mid, top levels. Cached 3 s. Example: ?coin=BTC&sizes_usd=1000,10000 Pr params: coin*, sizes_usd, levels |
crypto_etf | Use when an agent needs US spot bitcoin or ether ETF holdings from official filings (IBIT, FBTC, GBTC, ETHA...). Input: asset (btc or eth), optional ticker. Output: JSON per fund coins held (reported or estimated), fair value USD, NAV/share, shares outstanding, sponsor fee, period end, change vs previous period, share of coins, filing link; totals. From 10-Q/10-K XBRL, not daily flows. Cached 12 h params: asset, ticker |
hl_markets | Use when an agent discovers what trades on Hyperliquid, including HIP-3 builder-deployed dexs (stocks, commodities, FX). Input: optional dex (xyz, flx, main), sort (oi, volume, leverage, name), limit (1-200). Output: JSON without dex: core and HIP-3 totals and every dex with deployer, markets, OI, volume, OI caps, top markets; with dex: each market's max leverage, isolated-only flag, OI cap and % params: dex, sort, limit |
convert_to_markdown | Use when an agent must read a document as clean Markdown: web page, PDF, DOCX or Korean HWP/HWPX, tables kept. Input: url (http/https) via GET, or POST a file (multipart 'file', raw body, or JSON contentBase64+filename). Free-plan size cap → 413 before payment: HWP 48 KB, HWPX 100 KB XML. Output: JSON markdown, title, pages, sourceType, warnings. Price by detected type: HTML $0.0027, PDF/DOCX $0.0 params: url, contentBase64, filename, type |
Entries describe changes in tool definitions. They are not statements about a server, its quality or its author. The grade measures how the tool definitions fit model providers (token cost, schema compatibility, confusable names) as scored by the ToolFit engine at the time of the listing. JSON: append .json. Opt-out: how or hello@youraitools.co.