All projects on Base matching “verdict”

One combined go/no-go before an agent spends: PROCEED / CAUTION / ABORT from the token's market verdict, the counterparty wallet's sanctions, age and poisoning check, and — with a spender — its ERC-20 approvals. A leg that cannot be evaluated returns unknown and caps the verdict at CAUTION. Mode 'compact' returns the decision, the worst leg, and one summary per leg. Use this when an agent is about

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

Token safety check on Base before buying: honeypot, rug pull and scam detection. Verdict SAFE/CAUTION/SCAM with fixed reason codes and action ALLOW/BLOCK/RECHECK; admin rights, sell tax, liquidity, two independent honeypot sources plus own sale simulation of a real holder (Uniswap v4 included), check coverage and block number

Domain intelligence in one call: DNS records (A, AAAA, MX, TXT, NS, CNAME), WHOIS via RDAP (registrar, created, expires, status), and live SSL certificate (issuer, validity, expiry). $0.005 per call. No account or API key needed.

For model cascades: is the small model's answer usable, or should the larger model be paid? Detects refusal, evasion, off-topic answers, contradiction and incompleteness; decides accept, review or escalate. Does not fact-check without a source: provide the source to check substance.

Evaluate a claim or question against one supplied HTML or PDF source and return anchored evidence.

AX1 Verdict analyzes Base tokens and supported Solana mints using live onchain metrics across all pools. Each $0.02 call returns a grade (BASED, MID, COOKED or RADIOACTIVE), a one-line verdict, a short roast, a shareable verdict page and a card image. Payment is USDC on Base. No account or API key is required. Entertainment, not trading advice. By AX1, ax1.vc.

Send a Base token contract address, get an AI-written verdict: onchain metrics, a plain-language take, and a shareable verdict card. Entertainment, not trading advice.

Wire-In Lookup — per-entity merchant-seat verdict. Pass ?ua=<counterparty-UA>; get ONE signed row: score (0.0-1.0 payment-reliability observed at this seat), confidence, verdict (settled | attempted_payment | probe_only | low_signal | unknown), observed counts, Ed25519 attestation. $0.01 USDC/entity on Base or Solana. Fold the score into your own counterparty model — wire it into your scoring loop

Who is behind a token: our safety verdict (grade, honeypot), DexScreener market (liquidity, volume, age, pair), declared X + website with contract/X linking checks, the creator wallet (Clanker admin or on-chain deployer) profiled as /identity/wallet, stable red-flag signals (impersonation, wash trading, dead token, serial rugger, rug ring) and a credibility verdict. Not charged when nothing could

Put one question to a panel of 3 different AI models and get a single verdict back. Each model answers independently, then a chair synthesizes: verdict, confidence, the points they all agreed on, the dissent, and what would flip the answer. Use it for judgement calls where one model's opinion is not enough: is this safe, is this worth it, which option. No account, no API key, one USDC micropayment

The scorecard plus Messy Virgo's analyst verdict: one overall verdict (strong signal, watch, weak or red flag) with its reason, a written summary across security, performance and social, the key risks and what to watch, grounded in the 118 KPIs that ship with it, incl. honeypot, liquidity and sentiment. Call it when you need a decision-ready answer on a token: pre-trade checks, watchlist triage, p

[Payment decision: spend policy + seller reputation risk check, one verdict] Right before an AI agent pays: POST {payment, policy, seller} -> ONE verdict pay / dont_pay / ask_human. Runs the spend-policy check (limits, rolling cap, categories, allow/deny, hours, assets/chains, approval threshold) and the x402 seller reputation check (buyers, wash share, age, concentration), with reasons and one si

DAO Proposal Verdict: GO, CAUTION or BLOCK for one OpenZeppelin Governor proposal on Ethereum or Base, from decoded targets, Slither flags and a fork simulation diff. Returns: a DAO proposal verdict on one OpenZeppelin Governor proposal: GO, CAUTION or BLOCK from decoded targets, governance reads, Slither flags on verified target contracts, and a fork simulation diff of outflows, mints and owners

One call, one verdict on a token's owner powers: PROCEED, CAUTION or BLOCK, with the reasons attached. $0.02 USDC per call on Base, no API key. GET ?address=0x... (token contract, required), chain=base|ethereum. Reads the chain directly: owner, pause switch, pending owner, upgradeable proxy. Tells you whether the owner can still pause, upgrade or rug it. Returns verdict, a one-line summary, reason

Is this token a scam? Token due diligence in ONE call ({"address":"0x...","symbol":"SYM"}): on-chain security verdict (honeypot + rug pull signals) fused with a web scam/rug/honeypot mention search, returned as one verdict with sources. For pre-swap due diligence by DeFi agents. Web results are third-party claims — verify before acting.

Daily-refreshed ranking of US exchange-listed (NYSE/Nasdaq/CBOE) operating companies with the worst combined distress: Altman Z, Piotroski F and Beneish M verdict risk points plus red-flag severity from recent filings (going concern, auditor change, restatement, delisting notice, late filing). Each row: ticker, distress score, verdict, fraud-risk, top red flags, F/Z/M. Query limit=1-100 (default 2

Stablecoin peg tick — USDT, USDC, USDS, DAI, USDe, USD1 in ONE $0.01 call: live price, deviation from $1, 24h change, and a deterministic STABLE / WATCH / ALERT verdict per coin. Built for monitoring loops: call it every cycle, escalate to /api/depeg-watch for the single-coin deep read when a verdict is not STABLE. 60s freshness, cited to CoinGecko, no LLM in the path.

dappgrade score — front-end integrity verdict for an onchain app, looked up by contract address. Inspects the app's public web front-end, not contract bytecode or admin control. Returns ok / caution / avoid / unknown with the coverage the verdict rests on.

Bridge condition and clearance verdict from the FHWA National Bridge Inventory: component condition ratings (deck/superstructure/substructure/culvert, 0-9), Good/Fair/Poor verdict, scour-critical flag, vertical/horizontal clearances, ADT, and inspection date for any US bridge by structure number, state+county, or facility/feature text. Public-domain USDOT data.

Market salary bands + offer verdict by SOC occupation and metro area. Returns annual wage percentiles (p10/p25/median/p75/p90), mean, employment, and a below_market/competitive/above_market verdict against your offer. BLS OEWS May 2025 public-domain data.

DJZS adversarial logic audit of a prediction-market trade intent. Deterministic verdict (PASS/WAIT/FAIL) with risk score, defect flags, verdict_hash, and on-chain Proof-of-Logic receipt. Out-of-scope requests are refused WITHOUT CHARGE. Audit, not advice.

Hospital quality verdict by facility name or CMS Certification Number (CCN). Returns the CMS overall star rating plus per-measure-group verdicts (mortality, safety of care, readmission, patient experience/HCAHPS, timely & effective care) built from CMS's published better/no-different/worse measure counts versus national benchmarks, hospital type, ownership, and emergency-services flag. Source: CMS

One-call verdict for an ERC-20 token on Base: risk (incl. holder concentration) + rug-pull + momentum + contract flags, verdict avoid/high_risk/caution/low_risk and a one-line English summary · Pay per call: $0.01 — or starter pack: 40 credits = 20 calls for $0.02 (valid 7 days): https://token-verdict.restockalarm.workers.dev/v1/starter-pack

Should your agent buy this Base token? Half the price of $0.02 AI token-verdict quests, deterministic on-chain checks instead of an LLM opinion. One-call verdict OK|CAUTION|AVOID + should_buy + can_sell + plain-English reasons, backed by risk_score 0-100 + level, flags (honeypot, cannot_sell_all, high tax, mintable, hidden owner, proxy, blacklist, unverified), bytecode size, EIP-1967 proxy impl, o

Check whether a website, business, or wallet is a scam before an agent trusts or pays it — fraud, phishing and rug-risk screening. Returns verdict (safe/caution/avoid), trust_score, domain age, red_flags. Input: ?target=domain

Source-bounded fact-check. Verify a claim against provided source text. Returns verdict: supported, contradicted, or unverifiable. Does NOT search the web.

Use before an agent buys or swaps into a Base token: token-risk, sellability (honeypot, tax), swap route and price impact for your size, and deployer reputation in one GO/HOLD/STOP verdict with a receipt. GO only when every check ran clean; an outage is HOLD. Coinbase tokenized stocks get stock checks (transfer policy, wallet eligibility, premium vs reference). GO/HOLD return `enforce`: a Cobalt c

Call this before paying any agent: Should I Pay? Binary decision (PAY/CAUTION/SKIP) with confidence and expected USDC loss before sending money to an unknown agent. Target by ERC-8004 agent_id, Solana pubkey, x402 seller_url or pay_to wallet. Every response includes a shareable verdict page and card image. GET or POST with JSON body. No account, no API key

$0.01/screen. Screen any name against OFAC, EU, and UK sanctions (UN included) plus Wikidata-derived PEP watchlists — fuzzy matching, instant JSON verdict. Compliance in one call, one of 155 Relaystation tools on one balance — relaystation.ai