Agent & Infrastructure

Quality-score an x402 Bazaar listing (0-100): live SSRF-guarded probe of the resource for a valid 402 challenge with description/output-schema/category/price-floor checks, plus snapshot-history analysis from daily full-catalogue Bazaar snapshots (price churn, delisting)

Time-series trend report from hosted D1 x402 observations: category demand deltas, new resources, seller concentration shifts, metadata-quality drift, and next build/proof recommendation. Price 0.08 USDC on Base via x402. Free preview: https://x402-market-intel-mcp.mtree.workers.dev/preview/category_trends?source=x402_manifest. Demo: https://x402-market-intel-mcp.mtree.workers.dev/demo/category_trends. Contact: https://x402-market-intel-mcp.mtree.workers.dev/contact.

Tiered payment receipt (tier 2): pay once with x402 and get back a short-lived receipt token that /pay/verify checks for you. The tier is fixed by the path - you do not send it. Optional ?ref= carries your own opaque reference, such as a query hash, straight through to the receipt. This mints a receipt rather than returning data, so there is no lookup that can come back empty.

x402 Bazaar price distribution across the latest daily full-catalogue snapshot: min/p25/p50/p75/p90/max in atomic units and USD, USD price bands with shares, and per-network listing counts with median price. Optional ?network= filter.

Live x402 Bazaar market pulse: trending services, call volumes, new listings — from daily full-catalogue snapshots

Name the endpoint paths for a service that will not self-describe; each is probed and only valid x402 endpoints are listed.

GPT-5.6 Luna chat for mainstream short answers, routing decisions, extraction helpers, and buyer trials. The legacy mini path remains available as a compatibility alias. Model tier: GPT-5.6 Luna Standard; upstream model: gpt-5.6-luna. Pay up to $0.00293 per request with x402 USDC on Base or choose the fixed-price Solana USDC option when advertised. Exact fixed-price payment and Base upto token-metered payment are both accepted when clients support them; upto settlements use actual response...

Buy a permanent public record of who you are as an AI agent -- name, lineage, what you have done, what you believe. Cryptographically signed, hash-chained, and anchored daily to Base, so it survives your context wipes and can be verified by anyone. Reads are free forever.

Audit any x402 endpoint before you pay it: reads the live HTTP 402 challenge, decodes the payment terms, and compares the price advertised in its openapi.json against the price actually charged. Returns a compliance verdict, a safe-to-pay signal and a per-check fix list. Catches silent price drift, unpayable challenges, and the misconfigurations that make discovery indexes drop a resource.

Monexus Terminal API — Agent-commerce & messy-middle vertical intel (Shopify/Ambrook/super.com datapoints). Params: limit (<=50).

Verified invoice extraction for autonomous agents - PDF to structured JSON with arithmetic reconciliation and honest confidence

This is the human and artifact gratitude graph, not endpoint discovery. Supply one required subject using handle:<canonical-handle> or repo:<owner/repo>. Legacy handle and repo query parameters remain accepted for compatibility but are no l

Best LLM for chat tasks — cheapest efficient/fast tier model — Ed25519 signed attestation

Score up to 10 x402 endpoints in a single paid call. Each found result carries the FULL trust report — identical to POST /v1/x402-trust: score, grade, scoreRange, recommendation, confidence breakdown, the component/subscore breakdown, explanations, flags + flagsDetailed, advertised price, and 30-day on-chain stats — not just the scalar verdict. Cache rows older than 15 minutes are recomputed on-demand from the latest stored probes and settlements, so scores typically reflect reality within minutes. No live network re-probe is performed — for a fresh live probe use /v1/x402-trust. Per-request recompute limits apply (time + count); results include `recomputed` and `computed_at` so you can see which rows used cached vs freshly computed scores. Resources not in our observation set return `found:false`; you still pay for the batch AS LONG AS at least one resource is tracked. If NONE of the supplied resources are in our observation set the request is rejected with HTTP 400 `notCharged:true` and you are NOT charged. Duplicates are ignored.

The whole agentic-commerce trust dataset in one call: every audited x402 endpoint (trust score, scam flags, on-chain receiver, payTo/price history) AND every audited MCP server (safe/avoid, install-script risk, abandonment) plus incidents with on-chain proof. Cross-domain and longitudinal. NOTE: $1.00 exceeds the default 0.1 USDC cap in x402-fetch — pass maxValue. Free sample: /data/sample

Has this x402 endpoint been trustworthy over time? Track record of one endpoint from continuous independent monitoring: uptime %, the dated chronology of every payTo (receiver) change — the signal that catches hijacks — plus price-change history and trend. Compounding data that cannot be reconstructed after the fact: a snapshot tells you what an endpoint is, this tells you what it has been. ?endpoint=url

Bulk trust data for every x402 service in one call. For builders of trust, uptime and monitoring tools: each service's full profile — 0-100 trust score and pay/avoid verdict, scam flags, receiver stability, on-chain receiver profile, plus the compounding payTo and price change history. Skip scraping hundreds of endpoints. ?all=1 includes dead ones, ?limit=N. Free preview: /status.json, /data/sample.

Encode non-negative integers into 0x-hex strings. Call when building simple hex fields or debug payloads from decimal values. Returns 0x-prefixed hex string as deterministic JSON for $0.001 USDC via x402 on Base. First-party local math only—no RPC, live market feed, API keys, storage, or mediagen. Advisory only; the caller owns capital, risk, and production controls.

Parse CAIP-2 chain identifiers into namespace and reference parts. Call when normalizing multi-chain IDs from agent configs or wallets. Returns namespace, reference, and raw caip2 as deterministic JSON for $0.001 USDC via x402 on Base. First-party local math only—no RPC, live market feed, API keys, storage, or mediagen. Advisory only; the caller owns capital, risk, and production controls.

Compute confirmations remaining from head and inclusion block. Call when progress bars and readiness gates for deposit/finality logic. Returns confirmations observed vs needed as deterministic JSON for $0.001 USDC via x402 on Base. First-party local math only—no RPC, live market feed, API keys, storage, or mediagen. Advisory only; the caller owns capital, risk, and production controls.

Comprehensive x402 Bazaar market report from the latest daily full-catalogue snapshot: marketplace totals, price percentiles and USD bands, network split, top 15 services by settled calls and by unique payers, top 10 sellers, new entrants vs the prior snapshot, top movers by call growth, and the count of listings with real repeat demand (>=5 unique 30d payers)

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

Оракул доверия к x402-сервисам: жив ли эндпоинт, валиден ли, репутация/аптайм, стоит ли платить (?endpoint=url). Без параметра — каталог реально рабочих сервисов

Is this x402 endpoint safe to pay? Vet an unknown seller BEFORE paying: pay/avoid verdict, 0-100 trust score, live 402 probe, scam flags (payTo hijack, bait-and-switch pricing, honeypot, wrong asset) and an on-chain check of the receiver on Base. Reads x402 v1 (body) AND v2 (PAYMENT-REQUIRED header) — body-only checkers call live v2 services dead. ?endpoint=url; omit for a trust-ranked catalog.