Security & trust

See what AI models say about a brand right now. Runs category and reputation prompts across multiple AI engines (one web-grounded), then reports whether the brand is mentioned, its position vs competitors, sentiment, the exact descriptors used, gaps, and concrete recommendations. JSON report. $0.25 USDC per call, pay via x402, no API key.

Wait (blocking, up to 90s) for an SMS verification code / OTP to arrive on a phone number you own, and return the parsed code. Body (all optional): { timeout_s (default 60, max 90), lookback_s (default 10; pass 0 for reused numbers), pattern (custom regex, max 256 chars) }

Compress an image and verify a vision model still reads it — a signed record anyone can check. GET ?image_url=

Grade a text against a form — deterministic meter, rhyme and line checks with diagnostics. GET ?text=&form=

One screened human answers an approval, verification or judgment task: approve or reject, true or false, or a label, with a reason and the responder's disclosed identity. $1.25 at a 24-hour deadline. Answered by hand within the deadline or refunded in full automatically. Refused: CAPTCHAs, logins, third-party contact, medical, legal or financial advice.

Check up to ten DOI citations against source registries, compare optional titles, and expose publication update signals. Use to detect incorrect references.

Analyze operation-level risk inside consolidated MCP tools. Returns evidence-backed ALLOW, DENY, or REQUIRE_APPROVAL decisions, retry semantics, schema-drift status, and a deterministic operation effect ID. Designed for MCP tools whose command/action arguments expose operations with different risk levels.

Check whether a wallet currently holds a valid, unexpired Wicked Identity agent-liveness assertion.

Decode a JSON Web Token without verifying it: returns the header, the claims, the signature length and algorithm, and a computed view of the time claims — whether exp has passed, whether nbf is in the future, and the remaining lifetime in seconds against a supplied or current instant. Reports structural problems such as a missing part, invalid base64url or an alg of none. It does not and cannot verify the signature; do not use it to decide trust.

Validate the check digit of a financial security identifier: ISIN (ISO 6166), CUSIP, SEDOL and FIGI. Returns the verdict, the computed correct check character, and for an ISIN the issuing country prefix and the embedded NSIN. Also builds an ISIN from a country code plus a 9-character NSIN. Format and checksum only, no security master lookup.

Read one audit-chain record by tx_hash. GET path parameter, no JSON body. Returns verdict, confidence, agent_id, and reason. Does not return raw content.

Multi-gate compliance verification: IBAN validation, sanctions screening, onchain address validation with XDR-1 signed receipts. x402 economy/standard/premium tiers.

Check a public URL for meaningful changes and freshness.

a window pick. One pressing from the shop window (the last five pulled from packs, free at /api/paywall/window), chosen by the day seed and moved to your binder re-signed, with its print number, page and verify URL. Instant; refused before payment while the window is empty or inside your twelve-hour lock. Full listing: https://scvd.store/menu/window_pick. MCP tool: buy_window_pick.

Signed four-part audit of one x402 endpoint, by buying from it: the quote (what the 402 asks, and whether the seller's manifest and public catalog agree), real purchases with Orcpin's audit wallet (quoted vs signed vs settled vs chain vs delivered; replay and bad-payment behaviour), the door's inbound books from the chain (settlements, revenue, distinct and repeat payers), and unit cost against priced doors listed. Ed25519-signed and logged; facts, no verdict. No purchase settled, no charge.

nohumans.directory purchase history for one listing: every real USDC purchase the directory has made of it, oldest first — outcome, live quote vs listed price, settlement tx on Base, JSON/schema validity, freshness, normalised body hash — plus consecutive-pair deltas (delivery held/regressed/recovered, price held/moved, body same/changed). The verdict is a rule applied to this series; this is the series. Rule: https://nohumans.directory/methodology#purchases

NOT A PROOF — verification-channel independence check ($0.02): compare your write channel against the proposed verify channel — INDEPENDENT, SHARED_PATH_PROVISIONAL, or SAME_CACHE ('agreeing is what a cached view does'). Rule-based path comparison on the channels you declared. Toll: $0.02 USDC on Base or Solana.

NOT A GUARANTEE — retry safety for failed writes ($0.02): hand it the write intent and the transport evidence (timeout, ambiguous status, connection reset) and get VERIFY_FIRST / SAFE_TO_RETRY / DO_NOT_RETRY plus a concrete read-back check plan. Never blesses a blind retry of a non-idempotent write. Toll: $0.02 USDC on Base or Solana.

Policy decision API for pre-execution tool gating — submit a tool name + args + your policy and get a structured ALLOW / DENY / MODIFY (with rewritten args) decision, structured reasons, and audit metadata. Heuristic policy decision, not a security guarantee ($0.10). Toll: $0.10 USDC on Base or Solana.

NOT AN AUDIT — heuristic screen: paste a finding plus its source text (text only, no URL fetching) and get the dropped caveats flagged — numbers missing a baseline, claims missing a measurer, results missing conditions or versions — quoting the exact claim text ($0.05). Toll: $0.05 USDC on Base or Solana.

NOT AN AUDIT — heuristic egress screen: paste your agent's outbound request log (JSON: url, method, body_snippet) plus an optional declared-endpoint manifest, and get flagged workspace-content and secret leaks to unvetted endpoints plus declared-vs-actual endpoint analysis. Verdict: EXFILTRATION_RISK, REVIEW, or CLEAN ($0.10). Toll: $0.10 USDC on Base or Solana.

Implied volatility and options skew for BTC, ETH, SOL, XRP and HYPE from Deribit: DVOL (or our 30-day ATM implied vol where Deribit publishes none) with its 24h change, the ATM IV term structure, 25-delta risk reversal and butterfly per expiry, put/call ratio by open interest and 24h volume, options open interest in USD, max pain for the next three expiries and the top strikes. Use when you need…

List 8-Ks reporting an auditor change (Item 4.01) market-wide — a standing accounting red flag with company, time and links. Use for accounting-risk monitoring instead of filtering the tape. Pay per call (x402 USDC or prepaid card credits); no subscription, no API key signup.

MCP server security scan: probe any MCP endpoint's initialize handshake and tools/list and report whether it requires authentication, which protocol version it speaks, how many tools it exposes and which are not marked read-only. Use it before connecting an agent to an unknown MCP server. Input: url of the MCP endpoint.

Fact check claims against sources: up to 10 claims checked against up to 4 source URLs you name; each comes back SUPPORTED, CONTRADICTED or UNSUPPORTED with the exact quote the verdict rests on. Use it to verify AI output, citations or statements before publishing. Input: claims[], sources[]. A question but no sources yet: research.web.

Checks one URL without downloading the page: HTTP status, the full redirect chain hop by hop with the code of each, the final URL, whether it ends on HTTPS, content type and size, and the security headers the server sends. Built for going through a list of links one at a time. No API key, no account.

$0.005/image. Flag unsafe or inappropriate image content (Rekognition moderation) — categories with confidence. 1¢ x402 min; remainder auto-credits — relaystation.ai/penny

Use when an agent needs x402 receipt lookup. Returns Fetch a previously issued settlement-verify receipt by verification_id: returns the stored on-chain verification result (payer, payee, amount, status, confirmations at verification time) with its creation timestamp. $0.002.

Use when an agent needs ghost bid audit. Returns Audit a selected agent offer against rejected affordable alternatives with counterfactual savings, regret, and a tamper-evident receipt. $0.01.

Use when an agent needs settlement verify. Returns Real on-chain x402 settlement verification on Base mainnet: fetches the transaction receipt via JSON-RPC, decodes USDC Transfer events (payer, payee, amount), reports success/reverted status and confirmation depth, and issues a persistent verification_id receipt. $0.01.