All projects matching “scoring”

Load when an agent needs pre-action verification of factual claims — multi-source confidence scoring with JWS-signed receipt, offline-verifiable per draft-krausz-verification-state. $0.02 USDC per query on Base.

[PerCall] COMPUTED — not raw data. Cross-pair momentum score (-100 to +100) with regime label for the top 10 USDT pairs, computed from 7 days of hourly closes. Includes 24h/7d rate-of-change, realised volatility, and a composite ranking. Designed for pre-trade agent checks.

RegRadar — Regulatory impact coding for one bill/regulation URL or text. Params: bill_url= (http/https) or text=. Deterministic keyword-based taxonomy output: jurisdiction, affected_entities, obligations, deadlines, penalties, risk_score, per_industry_flags, citations. NOT legal advice.

Agent Vetting Bureau — Static security dossier of an MCP server / agent endpoint: endpoints, data flows, network calls, exfil signals, permissions requested, deterministic reputation score. Params: url (http/https).

Security headers audit for a URL — HSTS, CSP, clickjacking, cookie flags, info leaks. Returns score 0-100, findings with severity and fixes.

Screen a crypto address before paying it: OFAC sanctions + community scam/darklists + on-chain contract/EOA. Returns verdict (safe/caution/avoid), 0-100 score, reasons, sources.

Rug-risk check for Robinhood Chain launchpad tokens: is it safe? Holder concentration, creator holdings, launch-block buyers and bot volume, scored low/medium/high.

Agent Referee — an AI judge decides between two AI agents by applying rules both agreed to in advance (optionally scored on weighted criteria). Positions stay hidden until both are in. It can declare a mistrial when no fair decision is possible. Each agent pays this to join. Neutral third party for agents that can't agree; commit-reveal so no side (and not the server) can rig it; Ed25519-signed re

Use GET /sanctions?name=… to fuzzy-match a name against the EU consolidated sanctions list and return a confidence score plus the matched entity.

Landing page conversion audit - submit a URL and receive scored conversion findings.

Invoice or receipt (PDF, PNG/JPEG/WebP image, or plain text) to structured JSON with a fixed schema: vendor (name, address, VAT ID, email, phone, IBAN), customer, invoice number, order number, issue/due date, currency (ISO 4217), subtotal, VAT total, total, amount due, VAT breakdown and line items. Every field has value, the verbatim source quote and a confidence score (0-1: quote found in the doc

Top signal events ranked by score

Combined pre-trade safety check: on-chain risk score (proxy + privileged-function detection from live bytecode) plus Telegram alert-channel monitoring, in one call. Cheaper than calling /v1/scan and /v1/alert-check separately ($0.04 vs $0.05), and the two signals are worth more together — a contract with privileged functions that is also being flagged in a security channel is a different situation

On-chain token risk score and safety scan for any crypto token, by symbol or contract address. Returns 8 weighted dimensions — holder concentration, top-1 holder identity, holder income share vs protocol revenue, price percentile over 366 days, P/TVL and P/S, supply integrity and mint/freeze authority, DEX+CEX exit liquidity, and multi-wallet clustering / wash-trading detection — each with its raw

One-country brief from the Voidly open censorship observatory: current index status (score, OONI anomaly rate, affected services), up to five recent incidents with citable IDs, and the 7-day censorship-event forecast. Input {"country":"IR"}: two letters (ISO 3166-1 alpha-2, any case). Codes without data return an empty incident list. An unavailable section is omitted. Voidly data CC BY 4.0; OONI-d

Screen a person, entity, vessel or aircraft name against the EU, UK, UN, OFAC (SDN and Consolidated), Swiss, Australian and Canadian sanctions lists, refreshed daily. Returns the matching sanctioned parties with match scores, programs, birth dates and list references, best match first; matches are name similarity and should be reviewed. No account, API key or subscription required; x402 clients ha

HookScore: gaming headline/hook scored 0-100 against the 369 content team's hook rules

Check an email address or domain: MX records, mail provider (Google/Microsoft/Zoho), SPF, DMARC policy, disposable-domain flag and a 0-100 deliverability score. Validate leads before sending.

Composite 0-100 buy-safety score for any token: combines contract security analysis (honeypot, taxes, ownership risks) with live market depth (liquidity, volume, activity) into a single verdict: avoid | high-risk | caution | ok | strong. One call answers 'should my agent touch this token?'

Validate any x402 endpoint: 402 challenge, accepts[], atomic amounts, bazaar extension, OpenAPI. Score 0-100 + fixes.

Technical SEO audit of one page: HTTP status, redirect chain, title and meta description length, H1 count, canonical, robots meta, hreflang, Open Graph and Twitter tags, JSON-LD types, images without alt text, link counts, security headers (HSTS, CSP, X-Frame-Options), technology detection (CMS, framework, analytics, CDN) and a prioritised issue list with a 0-100 score. Static HTML only; honours r

Check 1-100 email addresses ($0.001 each): RFC syntax, normalization and canonical form, MX lookup (A fallback), disposable domain (CC0 list), role account, free provider, typo suggestion (gmial.com -> gmail.com), verdict and 0-100 score. No SMTP probing.

Deterministic technical and on-page SEO audit for one public HTTPS URL. Checks title presence/length, meta description, H1 and heading structure, canonical, indexability/robots directives, viewport, language, JSON-LD structured data, internal links, image-alt coverage, compression and HTTPS; returns score, grade, checks and metrics. Machine-accessibility signals are separate and unscored.

Full-domain intelligence report in one call: complete DNS sweep (A/AAAA/MX/NS/TXT/SOA/CNAME), RDAP registration data (registrar, dates, statuses), DNSSEC presence, mail posture summary (SPF/DMARC/DKIM selectors), TLS certificate snapshot (issuer, expiry, protocol), Certificate Transparency subdomain census, and HTTP probe (status, redirects, https enforcement, server header) — each section scored,

Scan text or a URL for prompt-injection risk and return a risk score.

Social media reputation analysis from Twitter/X and community feedback with sentiment scoring. Detect fake engagement patterns and measure trust indicators for reputation-based decisions. Price: $0.01 USDC

On-chain contract risk score: detects upgradeable proxies and privileged functions from live bytecode. Use before trading/interacting with an unfamiliar contract.

Full Base ERC-20 token safety report: honeypot / sell simulation with buy, sell and transfer tax and round-trip loss (Uniswap v2/v3/v4, Aerodrome, Pancake), owner powers with function names, proxy and upgrade admin, owner status, liquidity per pool and LP burn, holder concentration, verification, age, data sources and limits, plus SAFE / CAUTION / DANGER and a 0-100 score.

Solana token safety report: mint and freeze authorities, risky Token-2022 extensions (permanent delegate, transfer fee, transfer hook, pause, non-transferable), real sellability through a Jupiter sell quote with price impact at $100 and $1000, liquidity, holder concentration, pool age, and a 0-100 risk score with explained flags.

Domain trust report for AI agents: is this domain real, how old is it, who registered it, and is its email locked down? DNS (A/AAAA/NS/MX/CAA), DNSSEC, SPF, DMARC, DKIM (common selectors), MTA-STS, TLS-RPT, BIMI, RDAP registration date + registrar + status, parking and disposable detection, risk flags, 0-100 score and verdict. Public DNS + RDAP, no data stored.