All projects matching “scoring”

Know Your Merchant (KYM) trust score: pass a merchant domain and get a deterministic 0-100 trust score with a band (high/medium/low/very_low/avoid) and human-readable reasons. Live signals: domain age from the RDAP registry of record, malware/phishing blocklist verdict via Cloudflare Security DNS, TLS certificate health, mail capability, and refund/privacy/contact page presence. The merchant-side

Scores text against every category in all six taxonomies (one embedding, cosine similarity) and returns the top `per` rows per taxonomy. With `taxonomy` and `category` it also returns the target's rank, score, gap to #1, and a phrase bank split into phrases the text already uses and phrases it…

Resolve ONE DNS record type for a domain -- the cheapest, narrowest domain-check endpoint. For all record types at once, use /domain/intelligence. For a bundled DNS+TLS+headers audit, use /web/audit (raw) or /security/posture (scored). For mail-security plus a scored verdict, use /domain/due-diligence.

Latest health score for one protocol: components (GitHub activity, TVL trend, treasury), source details, and score history.

Scored intelligence on freshly-launched Base tokens: safety + momentum → composite score and an AVOID/WATCH/HOT decision per launch. One call returns a ranked list.

Quick pre-flight quality score: composite (0-100) + grade (A-F) + three framework sub-scores (PEEM, RAGAS, G-Eval) + verdict. Run upstream of any other paid call to filter weak prompts before inference. The cheapest gate on the AI input quality problem.

Quick pre-flight quality score: composite (0-100) + grade (A-F) + three framework sub-scores (PEEM, RAGAS, G-Eval) + verdict. Run upstream of any other paid call to filter weak prompts before inference. The cheapest gate on the AI input quality problem.

Fuzzy-dedupe a list of records into clusters of likely-duplicate entities. Blocks by normalized token prefix, scores with Jaro-Winkler + token-set matching (exact on email/phone), unions matches above threshold, and returns a merged canonical record per cluster with a confidence score. Deterministic, no LLM calls.

Ranked crypto research scores from EarlyThunder: composite score, tier, category and one-line verdict for 259 assets, sorted best-first. Teaser for the full thesis endpoint.

Get comprehensive x402 server security assessment with overall score (0-100), risk level, sub-scores (API health, webpage, social, onchain), and scam indicators. Ideal for pre-transaction safety validation. Price: $0.01 USDC

Score how well a supplier fits a public tender or procurement opportunity. Returns fit score, eligibility assessment, requirements, gaps, risks and recommendation.

Check whether demand for a Solana token is manufactured before you buy: the organic score standalone — what share of volume is real buyers and sellers versus manufactured, plus organic buyers, trades-per-trader and the vol/liq ratio with the wash verdict. The demand-authenticity probe that complements a pre-trade safety check. — $0.01 USDC

Structured evaluation with TypeSafe's Jev (System One) model. Send any state plus typed questions — noul (true/false), choice (pick one), or score (ordinal scale) — and get back calibrated probabilities and confidence for each. Built for routing, classification, triage and policy checks where a fast, predictable, machine-readable answer beats prose.

Google Trends related queries for a keyword: the searches people run alongside it in a country — top queries scored 0-100 and rising queries with percentage growth, over a time window from the past hour to 2004-present. Keyword expansion for SEO keyword research, content planning and spotting breakout search demand early.

Stock fundamentals of a US company (e.g. AAPL, MSFT, NVDA): key financial figures and the latest filing from SEC regulatory filings, with a derived fundamental signal, score and interpretation. Use for the financials of a US-listed company. A crypto pair (BTCUSD) returns crypto fundamentals instead: perp price, volume, open interest, funding and, for BTC and ETH, CME positioning (CFTC).

Jev Decision ($0.005/call): Ask Jev (TypeSafe System One) typed questions about one state and get numbers back, not text: noul answers the probability a yes/no is yes; choice picks an option with a probability for every option; score places the state on an ordered scale of levels with a probability for every level. Same body and answer as TypeSafe's POST /v1/systemone (model optional, state as tex

Booking.com: Hotels and places to stay, prices for your dates, review scores, deals, locations, 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.

Current multi-hazard intelligence for any coordinates. Finds nearby wildfire, earthquake, flood, tropical cyclone, volcano, and drought signals and returns compact deterministic risk scores without generating satellite images.

Funding rate for any Hyperliquid perp: the raw rate, its interval in hours, the 8h equivalent, the annualised rate, next funding time and mark price. Use when you need to answer: What is the funding rate on this perp? Without a symbol: funding rates for the SOL and BTC perps on Hyperliquid, with open interest. The whole table with 30-day z-scores: /api/funding-radar.

Crypto funding-rate extremes screener: scans all 17 perpetual futures markets (BTC/ETH/SOL/BNB/XRP/DOGE/ADA/AVAX/LINK/DOT/LTC/TRX/BCH/ATOM/NEAR/APT/HYPE). Uses z-score (30-day baseline) to identify statistically extreme funding: |z|≥2 = extreme, |z|≥3 = critical. Returns only assets clearing the threshold. Real-time from Kronos market_signals (OKX data). Pay-per-call via x402.

French address geocoding on the official Base Adresse Nationale (api-adresse.data.gouv.fr, Etalab/IGN, continuously updated). Forward: ?q=8 boulevard du port amiens with optional &type=housenumber|street|locality|municipality &citycode=80021 (INSEE filter). Reverse: ?lat=49.897&lon=2.290. &limit=1-10 (default 3). Each match returns normalized label, confidence score, lat/lon, street, postcode, cit

Name search, European registers. Local copies, all searched without pays: Belgium, Croatia, Cyprus, Estonia, Ireland, Latvia, Lithuania, Norway, Romania, Sweden, Spain (BORME); live only with pays set: Czechia, Finland, Slovakia, Switzerland; Poland through GLEIF; DK/UK if enabled; +GLEIF. Top 10, score_confiance. BE, CH, CZ, DK, EE, HR, LT, LV, NO, RO, SE, SK: legal persons only (no FIE, ENK, IK)

Test that your x402 client can pay AUN: one call returns a deterministic paid receipt that the purchase was delivered (a liveness check, not downstream business-value proof). Use it as a first test call; once it works, the same client and wallet can call vendor-intelligence (company research), domain-trust-score or web-read-batch with no setup. $0.001 USDC per call on Base.

Real-time web search (via Exa) — ranked results with title, URL, published date, author, and relevance score for a query

Details for one on-chain DeFi lending pool (Aave v3, Compound v3, Moonwell, Morpho Blue) by pool id protocol:chain:token_address: supply APY, borrow APY, utilization, TVL and 0-100 risk score. Example: pool_id=aave-v3:base:0x833589fcd6edb6e08f4c7c32d4f71b54bda02913 (Aave Base USDC). Pool ids come from /v1/lookup/yields results. Refreshed about every 30 min

Token safety check for an ERC-20 on Base: is this token a scam, a honeypot, or safe to hold? Examines ownership and mint authority, proxy upgradeability, liquidity and holder concentration, transfer-restriction patterns. Returns hold/caution/avoid with a score and the signals behind it. Heuristic static analysis, not a security audit — a proxy contract can change its implementation after this chec

KRW Macro Stress Score (0-100) — combined signal from US 3Y treasury, VIX, foreign ownership proxy (SK Hynix + Samsung, mcap-weighted), USD/KRW momentum, and Korean semiconductor equity. Rolling 120d percentile over 2yr backfill. Regime + direction + per-component breakdown. Positioning: KRW macro stress, not kimchi-premium prediction.

Token security / honeypot detector for a Base mainnet ERC-20: EIP-1967/1822 proxy + upgradeability detection, bytecode dispatcher scan for mint/pause/blacklist/fee-setter/ownership selectors, owner() renouncement check, and a live eth_call state-override simulation testing whether a synthetic wallet can actually transfer() the token. Returns risk_score (0-100) + verdict (clear/review/block) + huma

Is this Base token safe to buy, or a honeypot, rug pull or scam? Simulates a real buy and sell to prove the token can be sold and to measure buy and sell tax, then checks mint, blacklist, pause and fee powers, proxy upgradeability, owner and DEX liquidity. Input: token address. Returns a verdict (low, caution, high, avoid), a 0-100 risk score and the evidence. Check before an agent trades a token.

Re-check up to 5 tokens you hold or watch in one call, on Base, Ethereum, Arbitrum, Optimism, Polygon or Solana: each token's 0-100 risk score, level, reason codes, price, liquidity and a fingerprint. Send the fingerprints back as since to get what changed (new risks, owner or authority changes, liquidity or price moves of 10%+) and a short list of alerts. One price for the whole list, made for po