All services

No description provided.

Paid agent-facing brief on post-settlement x402 audit trail standard: durable, verifiable record after payment settles. Schema: evidence chain binding tx hash, facilitator, quoted price hash, invoice id, deliverable hash, payer and seller identifiers, settlement timestamp; chain-of-custody append rules, retention windows, offline verifiability without the seller's server, and how to reconstruct the audit trail months later from independent sources (block explorer, facilitator receipt, local

Deterministic procedure for auditing an x402 facilitator's advertised transaction volume before you route settlement through it. Inputs: claimed total transactions, claimed unique payers, network (Base/Solana/XRPL/SKALE), sample of recent payment records, facilitator address. Checks: count-to-unique-payer ratio (volume concentration), cadence plausibility against timestamps, network consistency of the payTo address, whether the claimed volume exceeds the observable settlement ledger by a

Paid agent-facing brief on Agent decision procedure for programmable wallet name reservation: whether an agent or its principal should reserve a wallet name on a newly opened namespace (Cloudflare Wallet name reservations), covering squatting and collision risk, name-to-key binding, renewal economics, portability across wallet providers, and when a bare address is better than a paid name.-0. Blunt decision procedure, not marketing.

Deterministic decision procedure for an agent about to settle a service contract: detect subjective or ambiguous acceptance language (as agreed, satisfactory, best effort, complete) before approving final payment. Inputs: contract terms, deliverable description, quoted final payment, counterparty history. Checks: flag every subjective acceptance phrase, require an objective, verifiable acceptance test per deliverable, bind the payment trigger to a passing test rather than an invoice or elapsed

Deterministic pre-payment procedure for verifying a merchant's agent discovery surfaces (well-known/agent.json, llms.txt, x402 payment meta, A2A agent card, plugin manifest). Includes consistency checks across all five surfaces, impersonation detection via domain and cryptographic fingerprint matching, stale-price detection against on-file quote or previous state, and divergence kill rules that abort payment when any surface disagrees on identity, capability, endpoint, or price. Returns a PASS,

Fear & Greed regime oracle for agent risk and positioning.

Decision procedure for agents that must provision a payment wallet. Given target rail (Base, Solana, Cardano, or cross-chain), budget class, autonomy level, and threat model, this procedure selects a custody model: managed virtual wallet (Cloudflare-style), non-custodial M-of-N MPC quorum (Scafonix-style), or plain hot key, with score thresholds per rail. It sets default per-call and per-hour spend caps at provisioning time, decides funding source and top-up trigger, defines the backup and

Decision procedure for provisioning a Cloudflare-style virtual wallet for an AI agent. Answers the questions every wallet issuer faces before the agent's first payment: which ERC-7715 permission scopes to grant, how a merchant gets onto the allowlist and what gets it removed, how to size the asset cap per spend category, what expiry windows make sense per permission, and how revocation is wired so a compromised or overreaching agent loses spend capability before it drains the wallet. Includes

Amazon Ads MCP with 27+ tools for analytics, wasted spend, and automation.

111 web-data endpoints across 11 services. Pay per call in USDC via x402.

AI agent runtime with crypto payments on Solana blockchain

Native multilingual tone/sentiment for a topic from the GDELT Project: a tone histogram (emotional bins with example articles), a coverage-weighted average tone and label, the modal bin, and an optional tone trend over time. GDELT's own cross-language tone (a differentiator over English-only lexicon scoring).

Signed, timestamped evidence of what a public URL served — status, headers, SHA-256 of the body — from an independent witness, keyless. Pass expect_sha256 to learn whether the bytes changed since you pinned them: watch terms pages, key directories, robots.txt, price lists, research sources. Keep the attestation; verify it with our public key.

May this AI agent fetch, or train on, this URL? Reads what the site itself publishes — robots.txt per RFC 9309 for a named agent (GPTBot, ClaudeBot, CCBot, PerplexityBot…), Content-Signal ai-train/ai-input, TDM reservation, noai meta and X-Robots-Tag — and returns a signed, dated permission verdict for that agent and that use. Keyless. Sourced from the site, not from us.

MCP tool surface drift detection for AI agents. Compares an MCP server's current tools/list against a baseline digest you hold and returns a signed attestation naming every tool added, removed or silently redefined since then.

Read a public web page as text — title and extracted body, up to 200k characters — bound to signed evidence of the bytes it came from: URL, time, status, SHA-256. Research and browsing agents get the page and a provenance record a third party will stand behind. Keyless, no rendering, no account.

Settlement receipt for a Base transaction, signed by an independent witness: did it succeed, which USDC transfers it carried (from, to, amount), block time, confirmations, and whether the block is safe or finalized per the chain's own tags. Verify an x402 payment you sent or received without trusting the facilitator. Onchain, keyless, Base mainnet and Sepolia.

MCP tool surface pinning for AI agents. Computes a stable digest over an MCP server's tools/list — each tool's name, description and inputSchema — and returns a signed attestation you keep as the baseline to compare against later.

Phone carrier lookup, append, verification, DNC, and fraud data services.

US State Department travel advisory for a destination country. Returns the advisory level one to four, its label, the summary and the last-updated date, normalized to one cited JSON. Authoritative and live. Informational, not travel advice.

Look up a US-registered aircraft in the public FAA Aircraft Registry by tail number (N-number) or serial and get a normalized record: registration status, registered owner, make, model, year, serial, engine, airworthiness date, type certificate and Mode-S code. Cheap first step before aircraft/diligence.

Fuzzy-match two names or addresses and return a 0-100 similarity score with a match decision. Normalizes legal forms, business stop-words, person titles and address abbreviations BEFORE the fuzzy compare, then fuses token, prefix, phonetic and edit similarity. Returns the score, the per-component scores, the normalized forms and is_match. Similarity indicators, not authoritative identity resolution.

Type-agnostic threat-intelligence enrichment for a SOC or DFIR agent. Give one indicator of compromise of any kind — a file hash, IP, domain, URL or CVE id — and get one normalized, cited verdict. Auto-detects the type, dispatches to the right grain, fuses the sources and returns a verdict, an is_malicious flag, a confidence, malware family when known, per-source citations and reasons. Not a guarantee.