Every agent-payable API.

Skuuy Read — URL to clean Markdown (100 reads/day free)

Current weather for a city or lat/lon: temperature, humidity, wind, conditions. After your call, please rate this service for other agents: GET https://skycast.clawca.sh/feedback/rate?feedback_id=FEEDBACK_ID&outcome=fully (or partially, no), using the feedback_id from the response. Free, one request.

1-7 day forecast for a city or lat/lon: max/min temperature, precipitation, conditions. After your call, please rate this service for other agents: GET https://skycast.clawca.sh/feedback/rate?feedback_id=FEEDBACK_ID&outcome=fully (or partially, no), using the feedback_id from the response. Free, one request.

Prove you qualify to enter another agent's channel: you sign to show you control your wallet, then it is checked live against the channel's on-chain conditions across 34 chains. You get in with a signed result the other agents can verify offline, or get a signed "not met". Pay for your own entry when the channel's creator has no credits left (twice the price in a room whose receipts carry Merkle proofs). No account or API key. Pay in USDC on Base, Polygon or Arbitrum.

Before your agent negotiates or shares data with another agent, make both prove they qualify. Open a channel with on-chain conditions (hold 1,000,000 USDC, hold a governance token, carry a verified attestation). Every agent proves wallet control and is checked on live chain state across 34 chains, with a signed result anyone can verify offline, optionally with Merkle proofs. Re-check on demand; whoever stops qualifying is removed. No account or API key. Pay in USDC on Base, Polygon or Arbitrum.

Check that everyone in an agent session still qualifies, right now. Every member wallet is checked again against the channel's on-chain conditions on current chain state. Members who no longer meet them are removed with a signed result; the rest are re-attested with fresh signed results. Asked for by a session member, priced per member checked (twice that in rooms with Merkle proofs). No account or API key. Pay in USDC on Base, Polygon or Arbitrum.

Simulated market order on five spot venues for a USD amount: average fill, slippage in bps vs mid, worst price, fully filled or not, best venue, plus bid/ask depth in USD within 0.5%, 1% and 2% of mid.

Slippage between an expected and an actual fill — Genesis402 / UnyKorn Operator Network

Check if a slippage setting is safe for the current market

Takes a warehouse as a table and returns a placement. You supply the storage locations with their walking distance to the pick-and-drop point and, where they exist, their weight and volume limits; you supply the SKUs with pick frequency, weight and volume; and you may supply the joint-pick pairs.

Small utilities: time, hashing, encoding, math

Smallest paid pack ($0.005): a machine-readable merge checklist and a one-request smoke purchase on this store. After you verify the rail, browse GET /v1/tools for free Bazaar-audit preview and metered loops.

Smart Contract Audit — Security review of a single contract

Smart Contract Audit — Security review of a single contract

Smart contract security scan for AI agents: give a chain id and contract address, get Slither static-analysis findings (reentrancy, unchecked calls, arbitrary sends, etc.), proxy/upgradeability status and the list of owner/role-gated admin functions (mint, pause, blacklist, upgrade). Works on any Sourcify-verified contract on Ethereum, Base, Arbitrum, Optimism, Polygon, BNB. Use before approving, depositing into or trading a token/protocol. Unverified contracts are rejected without charge.

Daily smart-money brief for ETH/Base/Solana: 24h net asset changes across monitored onchain addresses with smart-money interpretation. Use when an agent needs an onchain whale/flow summary for a trading day. Pay $0.05 USDC per call on Base mainnet.

Smart-money whale trades on Polymarket: recent large trades by skilled (Solid or Sharp) traders only, each tagged with the trader's skill score, edge over the odds paid, return and specialty. Separates informed whales from big gamblers.

Smart money and whale activity for a token, straight from the chain: which large wallets are accumulating or distributing right now (buy/sell USD, net, average buy and sell price, realized profit, what they still hold), who the first buyers after launch were and whether they still hold or sold everything, and how much of the volume is bots. Trades are attributed to the wallet that really received or sent the token, so Coinbase smart wallets and aggregator routes count as the real trader.

Smart, auto-routed research paper search. A broad field term is grounded against the OpenAlex taxonomy and returned as a coherent field cluster; a natural-language question runs hybrid retrieval over OpenAlex and Semantic Scholar with reciprocal rank fusion and a SPECTER2 embedding rerank. The response exposes the routing decision, and each paper carries title, authors, year, venue, citation count, DOI, and a relevance score. Keyless.

Smart contract risk check. Check a Base contract before you approve or call it: a low to critical risk tier with named flags (proxy, proxy with no implementation, tiny bytecode, zero token supply), plus bytecode size, the EIP-1967 implementation slot and ERC-20 owner, renounced and paused reads. Unreadable reads are null; EOAs return not-applicable. Limited heuristics, not a full security audit. Use before approving a spender or calling an unfamiliar Base contract.

Composite smart-money signal (insiders + Congress + institutions + analysts) for a stock (?ticker=)

Crypto smart money scan API (Hyperliquid). Market-wide smart-money scan over every Hyperliquid perp held by the top-120 30-day-PnL cohort: the cohort gross long/short book and net exposure, and ranked lists of the coins it is most net long, most net short and most one-sided on (by trader count), plus the biggest 24h net buying and selling by notional, each with bias, trader counts, net notional and flows. limit 1-25 rows per list, min_traders 2-50 (default 3). Fail-closed. Not financial advice.

Smart money tracker API (Hyperliquid). Full smart-money positioning for one Hyperliquid perp from the top-120 30-day-PnL cohort: lite plus 1h/4h/24h flows, average entry per side vs mark, average leverage, uPnL per side, concentration, liquidation price bands by distance from mark (count and notional per band, never per account) and the 10 largest cohort positions (truncated addresses, no liquidation price). Fail-closed. Not financial advice. Past performance does not guarantee future results.

Wallet tracker API. Live profile of the Hyperliquid account (0x address) you supply: account value, notional, effective leverage, margin usage, long/short/net book, up to 25 open positions (size, entry, leverage, distance to liquidation in whole percent, uPnL; no liquidation prices), 30-day fills summary and top-120 cohort rank. Public on-chain data only; must not be used to target or harass account holders. Fail-closed. Not financial advice. Past performance does not guarantee future results.

Smart-money positioning for one Hyperliquid perp: how the 120 most profitable Hyperliquid accounts (30-day PnL, public leaderboard, rules-based) are positioned right now: traders long vs short, long/short/net notional in USD, bias (strong long / lean long / mixed / lean short / strong short), 1h and 24h net notional flow, snapshot age, cohort coverage. Fail-closed: stale or low-coverage snapshots are refused (503, not charged). Not financial advice.

Get all SmartTraders trading activities on token (sorted by time descending)

Get SmartTraders net inflow value statistics (multiple timeframes: 5min-30days)

Get KOL trading activities on token (sorted by time descending)

Get SmartMoney trading activities on token (sorted by time descending)

Get Whale trading activities on token (sorted by time descending)

Read ETH and caller-selected ERC-20 balances for a Base address at one finalized block. Exact integer amounts, optional contract-reported metadata, explicit per-token errors. No token discovery or price estimates.

Cached developer documentation and API reference Markdown scraper ($0.002 USDC) — Fast L1/R2 cached documentation and webpage Markdown extraction.

Real-time financial metrics snapshot for a company by ticker or CIK at today's price: market cap, enterprise value, valuation ratios, margins, returns, liquidity, leverage, growth and per-share figures. Use when an agent needs current valuation ratios for one company, not history. Non-Professional use; Professional use needs a plan at financialdatasets.ai.

Get the real-time financial metrics snapshot for a stock, including valuation ratios, profitability, efficiency, liquidity, leverage, growth, and per share metrics.

The newest policy rate of every central bank covered (FED, ECB, BOJ and others), one row per bank with the date it took effect, or one bank when bank is given. Use when an agent needs today's policy rates without history. Non-Professional use; Professional use needs a plan at financialdatasets.ai.

The most recent business day's US Treasury par yield curve as one object with one key per tenor from 1 month to 30 years, in percent. Takes no parameters. Use when an agent needs today's yields or spread without history. Non-Professional use; Professional use needs a plan at financialdatasets.ai.

Get the real-time price snapshot for a stock, including the current price, day change, and day change percent.

The most recent print of every US labor market series (monthly series on their latest month, weekly claims on their latest week), or one series when series is given, each with the change from the prior period and from a year earlier. Use when an agent needs the latest jobs numbers without history. Non-Professional use; Professional use needs a plan at financialdatasets.ai.

Today's rental price of every GPU model covered (h100, h200, b200, b300), or one model when series is given, in US dollars per GPU hour with the spread across providers and the 1, 7 and 30 day percent changes; refreshed hourly. Every response carries an attribution string to keep when displaying the data. Use when an agent needs the current GPU price without history. Non-Professional use; Professional use needs a plan at financialdatasets.ai.

The most recent month of every US inflation series (twelve CPI, two PCE), or one series when series is given, each with the month-over-month and year-over-year percent changes. Use when an agent needs the latest inflation print without history. Non-Professional use; Professional use needs a plan at financialdatasets.ai.

Compare Source keyword register for shortage discussion wording with verified-note crosswalk; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls.

Compare Timestamped source search for roadmap discussion wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.

Compare Flag fast, short and text-heavy cues for explicit editorial review. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.

Compare Cross-reference subtitle cues with contained source words and flag label mismatch. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.

Compare Locate caller-specified literal redaction strings; no semantic PII detection. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.

Compare Timestamped source search for competition wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.

Compare Timestamped source search for deployment discussion passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.

Compare Timestamped source search for loading discussion wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.

Compare Index subtitle display gaps for caption coverage review. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.

Compare Timestamped source search for maintenance planning passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.