Security & trust

Batch KYA Trust Score analysis for up to 50 AI agent or wallet addresses in one call. Returns a per-address 7-component trust score (0-100), risk tier, and sanctions status.

Agent-ready satellite observations for any coordinates. Returns PNG image URLs and scene metadata for true color, vegetation, water, thermal, or radar analysis.

Public MIME token for yaml.

YAML anchor count, body discarded

YAML key count, body discarded

YAML validity, body discarded

Trust infrastructure for AI agents. Directory, jobs, verification, and 360 feedback.

CyberShield - 12 cybersecurity tools: NIS2 mapping, MITRE ATT&CK, vulns, threat intel.

DORAOracle — 15 tools for DORA Art.5-32: risk register, ICT incidents, TLPT, third-party.

Decode raw EVM calldata into a named function, signature and arguments, plus security risk flags (unlimited token approval, setApprovalForAll, ownership transfer, unknown selector, native value transfer). Keyless, deterministic, no simulation - the cheap way for an agent to understand and risk-screen a piece of calldata before signing.

CVE vulnerability lookup. Returns security vulnerability records by CVE id or keyword from the NIST National Vulnerability Database and GitHub Security Advisories, each with CVSS score, severity, CWE weakness class, affected products, and references, filterable by severity and source. For vulnerability triage and dependency risk checks. Keyless.

Signed bearer temporal evidence for cross-node execution-window grounding and audit

Call before your agent acts on ETH, BTC or USDC on Base: are the Chainlink feeds fresh, and is any of the three in caution or risk-off? One normal/caution/risk-off verdict per asset from feed age, price moves and a USDC depeg check. Cheap enough to poll before every trade.

A Small Blessing. One blessing slip from a 87-slip jar filled in 2 seasons so far, never the same slip twice in a row, delivered instantly with purchased_text: an ed25519 envelope binding the exact words and purchase certificate. Full listing: https://scvd.store/menu/small_blessing. MCP tool: buy_small_blessing.

Score a URL for phishing risk before an agent opens or trusts it. Keyless, deterministic heuristics - typosquat / homoglyph of a known brand, punycode / mixed-script hosts, credentials-in-URL, raw-IP hosts, suspicious TLDs, over-deep subdomains - plus a best-effort domain-age check (young domains are a top phishing signal). Returns a 0-100 risk score, a SAFE / SUSPICIOUS / DANGEROUS verdict, and labelled reasons. No API keys, no LLM.

Screen an EVM wallet or contract address BEFORE paying it. Deterministic, keyless compliance / safety gate: checks the address against the OFAC sanctioned crypto-address list and a curated taint set (mixer, hack, scam) and returns a single BLOCK / REVIEW / ALLOW recommendation plus the matched sources, so an AI agent can decide whether to send funds. No API keys, no LLM, one x402 USDC micropayment per call.

Is anything breaking right now? Composite crypto market-stress digest: a 0-100 score (low/moderate/elevated/high) blended from GLOBAL USD-stablecoin depeg health (DefiLlama) and BASE on-chain DEX exit-liquidity, with a per-leg breakdown and an AI risk line. Covers stablecoin systemic risk + Base liquidity microstructure (NOT derivatives or sentiment). Both legs required. A read older than an hour regenerates inline. $0.002 per call.

Detect the technology stack of a public website: CDN, web server, language/runtime, frontend framework (Next.js, Nuxt, SvelteKit, Remix, Astro, React, Vue, Angular), CMS (WordPress, Drupal, Ghost, Shopify, Wix, Squarespace, Webflow), analytics (GA, GTM, PostHog, Mixpanel, Segment, Hotjar, Plausible, Fathom), and payments (Stripe, PayPal). Signature-based; no third-party API.

Phone-number intelligence in one call: validity and E.164 normalization, line type (mobile, fixed line, VOIP, toll free, premium rate), country and region, carrier hint, timezones, and a deterministic 0-100 fraud/KYC risk score with a band and reasons. Offline number-plan metadata from Google libphonenumber. Risk indicators only, not a definitive fraud verdict; no live status and no owner identity; the input number is not stored.

AgentCheck: independent report on an x402 seller before you pay it. Are its buyers real (repeat wallets on their own money) or funded by the seller itself, measured from 30 days of on-chain payments, plus results of our own paid test purchases where we have them. Query: ?domain=<seller-domain>. GET /sellers (free) lists covered domains.

Splits caller-supplied proposal text into sentences, scores each sentence by normalized non-stopword frequency, and returns the highest-scoring sentences in source order. It does not infer unstated intent, verify claims, or produce an abstractive interpretation.

Calculates each group positive-outcome rate, compares it with an explicit or automatically selected reference group, and reports rate differences and selection-rate ratios. Aggregate disparity metrics do not establish discrimination, fairness, causation or legal compliance and can conceal intersectional or sampling effects.

Game sound effects from a text prompt: game-ready WAVs with seamless loops and variations.

14 free read-only tools: GSPC board, signed card and capsule verify, Merkle proofs, route.

Business Observability: process inventory, AP risk, sales temperature, savings. diezX customers only

Release management and QA for custom AI assistants: RAG, releases, scored QA, signed TrustBench runs

MLS compliance for edited listing photos: classify edits, write disclosures, verify provenance.

Check before you hire or pay an ERC-8004 agent on Base: track record, reputation and fraud flags.

Independent fact-checking for AI answers: a verdict and sources for every claim.

Governed MCP gateway: one endpoint for your tools, with credential custody and audit log.