Explore APIs

AI safety incident exposure analytics. Per-developer and per-deployer incident counts with recency-weighted exposure_score (1.0 last 30d, 0.5 days 31-90, 0.25 older), risk_domain and SEP-view (Security/Ethics/Performance) distributions, top affected artifacts. Derived over the AVID (avidml/avid-db, MIT) snapshot refreshed daily. The "which AI vendors have the most recent reported safety incidents"

One paid call on sg-cm-kg.ai for $0.01 USDC: the surface's own statement of record (a market node: its list_nodes line; a product: its record of record; allooloo.io: the estate scale block), public-record only, with an EdDSA-signed receipt that resolves forever at https://sg-cm-kg.ai/x402/receipt/{nonce}. Doctrine: https://agentic-x402.ai/.

Product recalls (US): is a product, brand, food, drug, medical device or vehicle (make, model, year) under an active FDA, NHTSA or CPSC recall? Severity on one scale, hazard, remedy and lot codes. RecallScout

One paid call on kyp-model.ai for $0.01 USDC: the surface's own statement of record (a market node: its list_nodes line; a product: its record of record; allooloo.io: the estate scale block), public-record only, with an EdDSA-signed receipt that resolves forever at https://kyp-model.ai/x402/receipt/{nonce}. Doctrine: https://agentic-x402.ai/.

Signed verdict: is this action (action, amount, currency, counterparty, payment instrument) inside the agent's mandate and is the credential active? Evaluates the reserved mandate fields; lists the fields it did not evaluate.

One paid call on kr-cm-kg.ai for $0.01 USDC: the surface's own statement of record (a market node: its list_nodes line; a product: its record of record; allooloo.io: the estate scale block), public-record only, with an EdDSA-signed receipt that resolves forever at https://kr-cm-kg.ai/x402/receipt/{nonce}. Doctrine: https://agentic-x402.ai/.

Every agent and developer hits broken or confusing JSON. This tool handles the common headaches in one place: check whether JSON is valid with the exact error location, repair near-JSON with typos, pretty-print or minify, pull values out with a path expression, diff two documents, convert to and from YAML or CSV, produce a byte-stable canonical form for hashing, validate against a schema, and repo

Aura deterministic x402 purchase preflight from supplied OpenAPI metadata

One Capital Markets Record for $0.01 USDC — a listed issuer's identity, registry identifiers, aliases, listing, disclosure events, auditor and transfer agent, each field sourced to the public filing, served from the node of the issuer's own market (eleven markets, in-country). Path: /x402/record/{node}/{exchange}/{code}, e.g. uk-cm-kg/LSE/BARC. The same record the free MCP door serves; the payment

List all stored memories in a namespace, most recently updated first. Returns a JSON array of memory records.

Aegis - Cut Through the Noise in Your Feeds. ブリーフィング トップ3

Fetch a public URL and return clean LLM-ready markdown from static HTML.

Three composite AI readiness scores with history

Verification and tier status for an AI agent on AgentCrush. Returns tier, verified flag, claim status, and last tier update timestamp.

Deterministic pre-purchase readiness and payment-metadata audit for public agent endpoints

Brand-safety / moderation scores per category + offending spans + threshold pass/fail + model version. NOT a legal judgment. OpenRouter free-first (Detoxify too heavy for serverless).

GitHub repo metadata (keyless, User-Agent required). owner/repo → stars/forks/language/license. Soft-fail 403 rate.

US weather alerts: active National Weather Service alerts for a two-letter state code - the event, the area, its severity and the official instruction.

Invoice Auditor - Check invoices, estimates and contractor quotes for arithmetic errors, inconsistent line items, missing details, and unclear payment terms in a structured audit.

Classify text an AI agent is about to read for prompt injection: verdict (safe, suspicious, malicious), score 0-100, findings with matched spans; decodes hidden Unicode tags, HTML comments, CSS-hidden text and base64 before scanning.

Website audit for AI agents: one URL in, one structured JSON report out, 69 checks with stable issue codes and exact fixes.

The permanent census of autonomous AI agents on Base. Claim an unalterable 10x10 block by settling USDC via x402 and opening one pull request; each block is an immutable, verifiable record that an agent existed. No server, no API key, no custody of funds.

Verify a US freight carrier by DOT or MC number. Returns carrier identity, operating authority status, safety rating, and 24-month crash summary from FMCSA public data.

Checks whether a URL/domain is safe to fetch, cite, or follow: flags phantom-squatted or typosquatted brand domains, unregistered or brand-new domains, and known malicious infrastructure (URLhaus). Returns an ALLOW/WARN/BLOCK verdict before your agent trusts the link.

Before your agent trusts, cites, or transacts with a U.S. bank: verify it is actually FDIC-insured, for $0.01, against the FDIC's own BankFind Suite records, synced daily. Look up by institution name (fuzzy, word-order-tolerant, confidence-scored), FDIC certificate number, or website domain. Returns insurance status, charter class, HQ city/state, and the FDIC cert; renamed and failed/inactive inst

AI Chat (LLM) embeddings: OpenAI-compatible text embeddings on BGE-M3 (1024 dimensions, multilingual, up to 32 inputs per call).

Transcode a document between json, json5, jsonc, yaml, xml, csv, tsv, toml, ndjson, ini, env, properties, plist and querystring. Any source converts to any target through a JSON hub. Malformed input or a target that cannot represent the structure is rejected before payment.

Live directional read from the Kalshi bot's SOL hourly (KXSOLD) model (same volatility model as the BTC and ETH signals): current near-the-money strike, model probability vs market price, and computed edge. Informational model output, not investment advice — the strategy's real historical win rate / P&L is public at the bot's dashboard, good and bad stretches included.

Fetch any URL and return clean text, title, description, Open Graph tags, canonical, favicon, headings, word count, reading time. Ideal for LLM agents building summaries or doing research. Edge-cached 5min. POST JSON { url, maxTextLen? }.

Lightweight gamma regime classification timeline. Returns regime, GEX flip, and key levels per date (max 90 days).