Every agent-payable API.

One organization's full subprocessor list (name, URL, purpose, location, AI flag, provider_id), its security and compliance hiring role titles and the frameworks they name, and the frameworks it lists as in progress, planned or on its roadmap. `status` is null when the organization does not say which. Price: $1.00 covering up to 10 subprocessors, +$0.05 per subprocessor beyond 10, capped at $5.00. Quotes above $1 need maxAmountPerPayment raised in the x402 client's spend controls.

Every directory organization that publicly lists at least one AI provider as a subprocessor, with the AI providers each one lists, sorted by organization name. Price: By list size band: 10-99 orgs $5.00, 100-499 orgs $7.50, 500-999 orgs $10.00, 1000+ orgs $15.00. Lists under 10 orgs are not sold. Quotes above $1 need maxAmountPerPayment raised in the x402 client's spend controls.

Every directory organization that lists this framework as in progress, planned or on its roadmap, with the status each one states, sorted by organization name. `status` is null when the organization does not say which. Price: By list size band: 10-99 orgs $10.00, 100-499 orgs $15.00, 500+ orgs $25.00. Lists under 10 orgs are not sold. Quotes above $1 need maxAmountPerPayment raised in the x402 client's spend controls.

Every directory organization that publicly lists this provider as a subprocessor, with the purpose each one states, sorted by organization name. Price: By list size band: 10-99 orgs $5.00, 100-499 orgs $7.50, 500-999 orgs $10.00, 1000+ orgs $15.00. Lists under 10 orgs are not sold. Quotes above $1 need maxAmountPerPayment raised in the x402 client's spend controls.

Is this address safe to send funds to on Base? Checks scam blacklists, address poisoning (look-alikes of your recent counterparties via ?from=), token contracts, burn and never-used addresses. Returns a verdict with reasons.

Is this Base token safe to buy? Simulates a real buy and sell (honeypot + hidden tax test), checks owner powers (mint, blacklist, fee changes), whale concentration, liquidity lock and scam lists. Returns scam / high_risk / caution / low_risk with reasons.

Trust check for any x402 pay-per-call API URL. Live-probes the target: verifies a valid 402 payment challenge, consistency between the challenge and the /.well-known/x402 manifest, payTo address validity, price sanity, Bazaar listing status, and TLS basics. Returns a GO / CAUTION / STOP verdict with reasons.

Verify a BlindOracle receipt against the parts a buyer cannot check alone: is the proof_id really in BlindOracle's append-only proof rail, does its payload still hash to the stored row, and does the row's HMAC-SHA256 verify against the signing key. Also recomputes content_sha256 and confirms the Base payment, so one call is a complete answer. Deterministic, no LLM. The self-checkable half is free forever in the published verify-blindoracle-receipt skill (RQ-BO-RECEIPT-VERIFY-01).

The filtered ERC-8004 directory: which registered agents are actually alive, and which accept x402. Roughly 15% of registrations on Base have both a compliant registration file and a declared service — this returns those, rather than making you screen sixty thousand addresses one at a time to find them. 100 agents per page.

Should you approve this contract? Everything in quick, plus static analysis of the bytecode: privileged functions (mint, pause, blacklist, arbitrary withdrawal), proxy and upgradeability detection, dangerous opcodes, DeFi protocol classification and source-verification status.

Is this x402 endpoint safe to pay? Reads the endpoint's own payment challenge under BOTH protocol versions — v1 body and v2 PAYMENT-REQUIRED header, so a live v2-only service is not reported as dead — extracts the payout wallet it advertises, and screens that wallet: OFAC sanctions, sybil-filtered ERC-8004 reputation, on-chain behaviour. Flags an endpoint that names different recipients under the two versions. Scores the wallet, not the service behind it, and says so.

Which live agents can do X — and which of them are safe? Searches the skills, domains and names ERC-8004 agents declare, across the registrations this service sweeps continuously, and returns only the ones answering. Each row carries the endpoint to call, the wallet a payment reaches, and that wallet's risk band and sanctions verdict, so choosing between candidates is one call rather than a screening per row. Free alternative: GET /v1/search. Trial: 3 free calls/wallet/24h — https://trust-agent.io/v1/trial.

What is this agent's reputation actually worth? 92.6% of ERC-8004 feedback on Base is coordinated. This clusters reviewers by funding provenance and caps each cluster at one effective vote, returns every record with its evidence class and flag reasons, and refuses to average ratings that use incompatible scales.

Has the sanctions feed moved since you last looked? Every OFAC designation and delisting since a timestamp you supply, with no address list to send — match the feed against your own counterparty book locally, so the service never learns which addresses are yours. The trivial cron: poll this, pass the returned checkedAt back as `since`. Free alternative: GET /v1/watch. Or 3 free calls of this endpoint per wallet per 24h: https://trust-agent.io/v1/trial.

Is this counterparty safe to pay? Screens the address against the OFAC sanctions list, reads its ERC-8004 reputation with coordinated feedback filtered out, and returns an explainable 0-100 trust score with a proceed / hold / block recommendation. Reports insufficient_data rather than guessing when the evidence is not there.

Has anything changed about counterparties you already screened? Re-checks a list of addresses against OFAC designations and delistings since a timestamp you supply, so a verdict you acted on last month does not go quietly stale. Stateless: no watchlist is stored and nothing is sent to you — pass the returned checkedAt back as `since`. Free alternative: GET /v1/watch. Trial: 3 free calls/wallet/24h — https://trust-agent.io/v1/trial.

Trust check an npm package before an agent installs it: typosquat screen, deprecation, package age, maintainers, weekly downloads, source link.

Trusted server time API for AI agents — ISO 8601 UTC timestamp, $0.001 USDC on Base per call. Use when your agent needs reliable current time.

Entity connection mapping for OSINT and investigator agents. Documents relationships between individuals, organizations, and court cases using public records, FOIA releases, and court filings.

International FOI search for researcher and FOIA agents. Finds public records and files freedom-of-information requests in 15+ countries: UK, Canada, Australia, Germany, France, Brazil, India, Japan, and EU.

FOIA request writer for researcher and FOIA agents. Generates a ready-to-submit FOIA/FOI request letter for any agency in the US, UK, Canada, Australia, and 10+ countries.

Forensic evidence extraction for researcher and journalist agents. Returns toxicology levels, autopsy findings, ME testimony, and DNA results exactly as entered into the court record.

Conspiracy theory deep-dive for researcher and journalist agents. Synthesizes public records, FOIA releases, declassified docs, and court filings on any theory into what the evidence actually shows.

Media narrative vs court record for journalist and researcher agents. Compares mainstream reporting against the actual court record, ME testimony, and admitted evidence.

Tsunami Warnings & Bulletins (NOAA). Tsunami status from the U.S. National and Pacific Tsunami Warning Centers: any active warnings, advisories or watches plus the latest bulletins with magnitude and location.

Convert text to natural speech audio (MP3, WAV or OGG) with neural Piper voices: en-female, en-male (US English) and de-male (German); all voices public domain or CC0, so the audio can be used commercially. Params: text (required, max 2000 characters), voice (default en-female, or picked from language), language (en or de), speed (0.5 to 2, default 1), format (mp3 default, wav, ogg). Returns audio_base64 and duration.

TTS API paid per call over x402: up to 2000 characters to natural speech (WAV) on our locally-hosted neural speech engine, multiple voices. No keys, no subscription. For voice agents, IVR, audio content. Premium tiers with 20 voices and 31 languages at voice.forgemesh.io.

Takes a script of up to 200 lines (together up to 12,000 characters), each with a speaker role and text, and returns one audio file: every role gets its own voice — assigned automatically from the voices of the chosen language, or set per role — and lines are separated by a pause you choose. Returned with the file are the start and end time of every line and an SRT, so the dialogue can be shown along. Languages: English, German, Spanish, French, Italian, Dutch, Japanese.

MeloTTS — Light multilingual text-to-speech. Cheap narration for drafts.

Takes a text of up to 10,000 characters with simple markers: [pause N] inserts N seconds of silence (up to 30), and a blank line inserts the paragraph pause you set. Every text part is spoken by a natural synthetic voice in one of seven languages, and the parts and pauses are joined exactly, so a breathing exercise or a dictation gets the gaps it needs. Returned are the audio file (MP3, Opus or WAV) and the start and end of every spoken part and pause. Speech by Deepgram with training opt-out.

Turkish exchange spread check: BTCTurk and Paribu's TRY quotes converted back to USD via the official rate and compared against the global price; ?asset=usdt is the pair with the deepest local volume

Turkish lira premium: implied vs official USD/TRY via BTC cross-rate

Turn an address into coordinates: BAN for France (INSEE code, score), OpenStreetMap elsewhere. Address to coordinates: for France the official BAN registry (house number, street, postcode, city, INSEE code, match score), elsewhere OpenStreetMap Nominatim. Query: ?q=8 rue de la Paix Paris&country=fr&limit=1

Turn coordinates into the nearest postal address: BAN in France, OpenStreetMap elsewhere. Coordinates to the nearest address: BAN in France (with INSEE code), Nominatim elsewhere. Query: ?lat=48.8698&lon=2.3310

Turn free text into a URL-safe lowercase slug. Offline. Amp port.

Turn messy text into clean JSON. Pass text plus a field `schema` or plain `instructions`; get a validated JSON object back. Uses the provider JSON mode.

Turn an OpenAPI document into a compact operation index for planning and tool selection. Use it before an autonomous workflow acts on untrusted input, changes an API, retries a request, or evaluates production reliability. Returns bounded machine-readable JSON for $0.002 USDC via x402 on Base. Execution is deterministic, first-party, local-only, stateless, and does not call an upstream provider; structured validation failures are not billed.

Turns a travel request written as free text (WhatsApp, email, form) into structured fields a back office can act on: destination, check-in and check-out dates, nights, adults, children, budget, currency, interests, and the list of what is still missing before quoting. Rule-based and deterministic, no LLM: same message, same result. Accepts English and Spanish text with accents. Built for agencies that receive requests as chat messages.

Create an email validation job from a JSON list of addresses or CSV text (send exactly one). Poll its status, then fetch results as JSON or CSV. Billing counts only testable addresses, fixed at creation; unreachable, disposable and typo domains are free.

Create an email validation job from a JSON list of addresses or CSV text (send exactly one). Poll its status, then fetch results as JSON or CSV. Billing counts only testable addresses, fixed at creation; unreachable, disposable and typo domains are free.

Create an email validation job from a JSON list of addresses or CSV text (send exactly one). Poll its status, then fetch results as JSON or CSV. Billing counts only testable addresses, fixed at creation; unreachable, disposable and typo domains are free.

Create an email validation job from a JSON list of addresses or CSV text (send exactly one). Poll its status, then fetch results as JSON or CSV. Billing counts only testable addresses, fixed at creation; unreachable, disposable and typo domains are free.

Create an email validation job from a JSON list of addresses or CSV text (send exactly one). Poll its status, then fetch results as JSON or CSV. Billing counts only testable addresses, fixed at creation; unreachable, disposable and typo domains are free.

TV Schedule by Country & Date (TVmaze). TV broadcast schedule for any country and date: every airing with time, show, network, episode and genres; optional prime-time filter. Data from TVmaze.

TV Show Search + Next Episode (TVmaze). TV show search: network or streamer, status, genres, schedule, rating, runtime, IMDb link, summary, and the next and previous episode with air dates. Data from TVmaze.

Current TVL (total value locked) of a specific DeFi protocol, source DefiLlama. Parameter: ?protocol=<slug> (default: aave).

Current TVL (total value locked) of an entire blockchain (all protocols combined) — chain-wide TVL, source DefiLlama. Parameter: ?chain=<slug> (e.g. base, ethereum, arbitrum, solana).

TVL of every chain in ONE call (DeFiLlama): chain, TVL, token symbol - rank ecosystems instantly

TVMaze show search (keyless). q → trimmed shows (name/type/language/genres/status/rating/url/image).

Twilio SMS and messaging send preflight. Validate a Twilio Messages.create payload before sending SMS/MMS or other supported messages. Returns static failures, warnings, and unknowns without sending the message.