Every agent-payable API.

One merge-safety verdict for a public GitHub pull request. Fetches the PR diff and runs it through code, secret, CI/CD pipeline and dependency scanners, returning a single verdict (pass, caution, block), a risk score and findings with severity, file, line and a fix hint. One call instead of slicing the diff into several. Security indicators, not a guarantee.

Cross-venue prediction-market search: one query returns a ranked list of NORMALIZED markets from Polymarket (real-money) and Manifold (play-money) under one schema — implied probability, outcomes, volume, liquidity, close date, status, money_type and a link-back. One call instead of hitting each venue's API and reconciling their shapes.

Top trending prediction events by 24-hour traded volume: a normalized list with 24h and total volume, liquidity, market count, a top-market summary, close date, status and a link-back.

premium agent insight analysis

Pre-sign risk verdict plus a plain-language explanation in Dutch or English. Bulk: 100 checks for $0.80 via /v1/credits.

Is this transaction, approval or signature safe to sign? Check it before your AI agent or wallet signs it: pre-sign verdict (green/orange/red + reason codes) for EVM transactions, token approvals and Permit/Permit2/EIP-3009/Seaport signatures. Screens the spender or recipient wallet for OFAC sanctions and scam, phishing or theft reports, and flags unlimited allowances, plain-wallet spenders and risky tokens. Bulk: 100 checks for $0.80 via /v1/credits.

Is this text a prompt-injection trap for your AI agent? Checks a web page, email, tool result, API answer or another agent's message before your agent acts on it: does it try to make the agent ignore its instructions, pay or send money, hand over keys or private data, or obey a fake user, admin or support message? Green/orange/red with reason codes, judged by TypeSafe's Jev, plus hidden-character tricks and OFAC-sanctioned addresses in the text

Wallet approval audit (green/orange/red, grade, one-line summary): every open ERC-20 allowance of an EVM wallet with who the spender is (flagged, plain wallet, unverified, unlimited) and which ones to revoke. Bulk: 100 checks for $0.80 via /v1/credits.

Is this wallet sanctioned? Screens any chain's address (EVM, Solana, Tron, Bitcoin, XRP Ledger, Algorand) against the OFAC SDN list, synced from the US Treasury, plus theft, phishing and mixer reports for EVM addresses. Green/orange/red with the SDN entry (name, programs) when listed. For sellers screening who pays them and agents checking who they pay. Bulk: 100 checks for $0.80 via /v1/credits.

Is this token safe to buy, or a honeypot or rug pull? Checks a Solana or EVM token before you buy, hold or accept it (mint or freeze authority still active, LP not locked, buy/sell tax, low liquidity, brand-new token, concentrated holders) and answers green/orange/red with a grade (SAFE/CAUTION/RISKY/AVOID), the reasons, a one-line summary and market data

pump.fun tokens near Raydium migration (?limit=)

What these wallets have been since March 2025: class (winner, bot, supply seller, new) and the SOL behind it

A pump.fun deployer's record without needing a coin: launches, graduations, best run, the gap between launches, its last launch; over the last 90 days how many of its launches doubled, did 10x, held at 2x a day later or died; its newest launches by name; and the base rate for its next launch from deployers with the same record ($0.005). Use before launching, or before buying from a deployer you have an address for; for a coin that exists, GET /launch/{mint}.

Your pump.fun picks replayed honestly against the chain's history, fees and fills included: a queued run, 202 with an id, then GET /replay/{id}

The launches most like this pump.fun memecoin at the same age, named with their contract addresses, and how each went over its next 24 h (peak, close, dead or graduated): the same deployer's prior launches first, then the nearest of the last 90 days by the deployer's record, the first-10 s buyers, the insiders' share and curve progress, each saying why it is similar ($0.005). Use before buying a fresh pump.fun coin; the bucket's spread is GET /launch/{mint}.

This launch, historically: the deployer, the bundle, the insiders, and the launches that looked the same

Search recall records from 9 US agencies (CPSC, FDA, NHTSA, US Coast Guard, FAA and more) by words, category and date, newest and most relevant first. Each record has hazard, remedy, firms, products, identifiers, as-of date and the agency source link. Use for questions like "recent listeria recalls" or "Takata airbag recalls".

Episode 1 of recipients[], an ongoing AI-agent thriller serial: a short text episode (~370 words, markdown). An agent finds its own ID on a payment recipient list before the file even exists. $0.01 USDC on Base. Free teaser at /teaser.

reefjaco POST /weather Current weather plus 3-day forecast for a city name (Open-Meteo, no key)

Replace regular expression matches in text, with an optional max-replacement count.

Test a regular expression against text; returns match status, capture groups and span.

X (Twitter) account metadata for any handle (based_in, source app, username-change count, recent-activity proxy). Utility endpoint.

Give it domains. For each it parses robots.txt (user-agents, allow/disallow, crawl-delay, declared sitemaps, blocks-all) and the XML sitemap(s) (URL counts, nested sitemaps, lastmod coverage), and flags crawlability issues - with a signal and findings. Keyless, read-only. Up to 3 items per call; failed lookups are not charged.

Lints and validates a caller-supplied robots.txt against RFC 9309 and reports every check, not only the failures: group structure, product token charset, path patterns, special characters, other records, size limit. Given a user agent and URLs it recomputes the allow/disallow decision per URL, naming the winning rule, its octet length and the tiebreak that applied. Where the RFC is silent or contradicts itself, the reading used is stated. Makes no outbound request.

Send any x402 resource URL, get a trust verdict on the endpoint itself. Returns TRUSTED / CAUTION / AVOID with a 0-100 score from an observation-only live probe (never pays the target): payment terms, Bazaar discovery-schema quality, CDP Bazaar and PayAI catalog presence, plus a diff against the previous check. Use this when an agent is about to pay an unfamiliar x402 endpoint and needs to know it is alive, honestly described, and unchanged first.

Token safety scanner for Base: 0-100 safety score, risk band, and red flags (liquidity, honeypot signals, upgradeable proxy, pair age, 24h flow) for any Base token contract.

Market-intelligence aggregate over a normalized RWA sub-category: total TVL, the top products ranked with their TVL share, issuer concentration and the leading product's growth trend. Called without a category it returns a market-wide roll-up of every sub-category's TVL and product count. Cited to the open-data source.

Catalog of tokenized real-world-asset products ranked by TVL, from the DefiLlama RWA universe. Each row carries slug, name, symbol, normalized sub-category, backing type, issuer, DefiLlama category, total value locked and the chains it lives on. Optionally filter by sub-category, chain or issuer. The cheap first step that resolves a name to the slug the other routes use.

Yield facet for a tokenized-RWA product: pool-level APY, base APY, reward APY, the 30-day mean APY and the 30-day change, plus a TVL-weighted average across the product's pools, from the DefiLlama yields feed. Reports availability false when the product has no tracked pools. Cited to the open-data source.

safe arithmetic eval (+ - * / % ^ parens)

Check a Romanian SAF-T D406 file (monthly, annual assets, stock) before filing with ANAF: the official ANAF validator (DUKIntegrator) plus the consistency checks it skips - balanced entries, opening + movements = closing per account, partner balances, invoice totals, VAT = base x rate, VAT codes for the period, exchange rates, CUI/IBAN check digits, asset and stock roll-forwards. Each finding has a fix (RO/EN). XML as the request body, up to 100 MB. Charged only if a D406 was checked.

Check whether a crypto address appears on the official public sanctions lists (OFAC SDN, UK, EU, UN). Deterministic exact lookup; returns the matched record (list, program, entity name, reference, currency).

Use this when you don't have a USDOT number yet and need to filter carriers by state, safety tier, authority status, or cargo type — for example, every carrier with an unsatisfactory rating in a given state. Capped at 100 rows per call, Active carriers only by default. Billed only when at least one carrier matches; a zero-row result is free.

semver compare {a,b} -> cmp -1|0|1

SendCheck deep scan: the same verification across all 5 chains (Base, Ethereum, Arbitrum, Optimism, Polygon) incl. wrong-network detection. POST {address, chain}

SendCheck: pre-send verification of any EVM address on one chain (EIP-55 checksum, wallet-vs-contract, outgoing activity, balances, verdict). POST {address, chain}

SendCheck: pre-send verification of any EVM address on one chain (EIP-55 checksum, wallet-vs-contract, outgoing activity, balances, verdict). POST {address, chain}

SendCheck: pre-send verification of any EVM address on one chain (EIP-55 checksum, wallet-vs-contract, outgoing activity, balances, verdict). POST {address, chain}

Sentiment analysis: classify text as positive, negative, or neutral with a confidence score and an alternate label. Powered by Jev, with an automatic Groq-hosted LLM fallback if Jev is slow or unavailable ("engine":"jev"|"fallback" in the response) - under 4.5s guaranteed. Try GET /sentiment/sample.

Google Event Details: Google Event Details results, returned as JSON. Structured JSON, USD 0.05 per call in USDC — no API key, no account, no subscription, no minimum. Not affiliated with, endorsed by or an official channel of any of the services the results come from. All trademarks and copyright remain the property of their respective owners.

Google Maps Reviews: User information, reviews, rating, and more available. Structured JSON, USD 0.05 per call in USDC — no API key, no account, no subscription, no minimum. Not affiliated with, endorsed by or an official channel of any of the services the results come from. All trademarks and copyright remain the property of their respective owners.

DuckDuckGo: Scrape DuckDuckGo search results in JSON format automatically, using custom parameters. Structured JSON, USD 0.05 per call in USDC — no API key, no account, no subscription, no minimum. Not affiliated with, endorsed by or an official channel of any of the services the results come from. All trademarks and copyright remain the property of their respective owners.

Tripadvisor Place: Tripadvisor Place results, returned as JSON. Structured JSON, USD 0.05 per call in USDC — no API key, no account, no subscription, no minimum. Not affiliated with, endorsed by or an official channel of any of the services the results come from. All trademarks and copyright remain the property of their respective owners.

Yahoo!: Scrape Yahoo! search results in JSON format automatically using custom parameters. Structured JSON, USD 0.05 per call in USDC — no API key, no account, no subscription, no minimum. Not affiliated with, endorsed by or an official channel of any of the services the results come from. All trademarks and copyright remain the property of their respective owners.

Google Light: Access the world's fastest Google Search API. Scrape Google search results in JSON format automatically using custom parameters. Structured JSON, USD 0.05 per call in USDC — no API key, no account, no subscription, no minimum. Not affiliated with, endorsed by or an official channel of any of the services the results come from. All trademarks and copyright remain the property of their respective owners.

Google Local: Phone numbers, addresses, hours, GPS coordinates and more in code friendly JSON format. Structured JSON, USD 0.05 per call in USDC — no API key, no account, no subscription, no minimum. Not affiliated with, endorsed by or an official channel of any of the services the results come from. All trademarks and copyright remain the property of their respective owners.

Google Forums: Forum titles, dates, links, and more. Structured JSON, USD 0.05 per call in USDC — no API key, no account, no subscription, no minimum. Not affiliated with, endorsed by or an official channel of any of the services the results come from. All trademarks and copyright remain the property of their respective owners.

Google Maps Photos: Extract full size images, thumbnails, and user information. Structured JSON, USD 0.05 per call in USDC — no API key, no account, no subscription, no minimum. Not affiliated with, endorsed by or an official channel of any of the services the results come from. All trademarks and copyright remain the property of their respective owners.

Yandex: Scrape Yandex search results directly in JSON format. Extract organic results for your own keywords with different region and language parameters. Structured JSON, USD 0.05 per call in USDC — no API key, no account, no subscription, no minimum. Not affiliated with, endorsed by or an official channel of any of the services the results come from. All trademarks and copyright remain the property of their respective owners.

eBay Product: Product specs, prices, ratings, reviews and more. Structured JSON, USD 0.05 per call in USDC — no API key, no account, no subscription, no minimum. Not affiliated with, endorsed by or an official channel of any of the services the results come from. All trademarks and copyright remain the property of their respective owners.