Agent & Infrastructure

[3-LEG] AI tool and MCP chain, one tool (?entity=mammoth-ai): leading decay warnings, release cadence stalling and docs going dark -> current live or dead status from real DNS and GitHub checks -> realized lifecycle from launch to death with days alive (confirmation gate). A chain, not one reading: confidence = how many legs are lit, in order. Sources: DNS, GitHub, package registries. Descriptive only, never a forecast or advice. No data -> 422 no_charge, not billed. $0.25 per call.

[3-LEG] AI tool and MCP chain, one tool (?entity=mammoth-ai): leading decay warnings, release cadence stalling and docs going dark -> current live or dead status from real DNS and GitHub checks -> realized lifecycle from launch to death with days alive (confirmation gate). A sequential chain, not one reading - confidence = how many legs are lit, in order. Sources: DNS, GitHub, package registries. Descriptive only, never a forecast or advice. No data -> 422 no_charge, not billed.

[3-LEG] AI dependency chain, one dependency (?entity=openai-text-davinci-003): leading deprecation notices INCLUDING the sunset date the publisher itself scheduled -> current current availability -> realized lifecycle to deprecation, days alive (confirmation gate). A sequential chain, not one reading - confidence = how many legs are lit, in order. Sources: vendor notices, source URL per record. Descriptive only, never a forecast or advice. No data -> 422 no_charge, not billed.

[3-LEG] Regulatory filing chain, one issuer (?entity=AMC): leading NT late-filing notices, a distress leading indicator -> current 8-K material events graded by item severity -> realized Form 4 insider transactions (confirmation gate). A sequential chain, not one reading - confidence = how many legs are lit, in order. Sources: SEC EDGAR. Descriptive only, never a forecast or advice. No data -> 422 no_charge, not billed.

Validate revocation authority separately from x402 payment and prepare bounded propagation to opted-in verified targets.

x402 settlement smoke test — cheapest end-to-end paid call on Base. Verify your wallet, facilitator, and EIP-3009 USDC settlement for one cent before spending more. Returns payer address and confirmation. Keywords: x402 test, payment verifi

Read-only JSON-RPC access to the Avalanche C-Chain, served by the Pocket Network decentralised supplier set. Pay per request in USDC; no account, no API key.

Agent-visibility check: does an AI crawler (GPTBot, ClaudeBot, PerplexityBot, OAI-SearchBot) actually see your site? BEST-RATE pack: 4 checks for $5 ($1.25/check). Same service, smallest entry $2 at https://402registry.com/buy/one. Ladder: 1/$2, 2/$3, 4/$5. All packs: https://402registry.com/.well-known/402registry.json. A passing check earns a dated badge and a registry listing. No account, no card, no human.

Quick review: does an AI crawler (GPTBot, ClaudeBot, PerplexityBot, OAI-SearchBot) actually see your site? Every rule, no model: $0.1 for one check. Returns the score, findings by severity and the five that matter most (empty JS shell, soft 404, www/apex, robots vs AI bots, sitemap) with evidence. Fixes, a model verdict and a listing: the full check at https://402registry.com/buy/one. A passing review queues the site for the free catalog check. No account, no card, no human.

[BATCH+PROOF] Full x402 service demand roster, latest day: demand_class, calls_30d, unique_payers_30d, score_total, liveness_state, lifecycle, record_hash per service. Model demand-v1, refreshed daily from the public CDP catalogue; unique_payers_30d is a lower bound, never a sum. DEGRADED DELIVERY, see unavailable_fields - the five-axis sub-scores, action_hint, tier and verified are empty. Descriptive only, never a forecast or advice. No data -> 422 no_charge, not billed. $0.09 per call.

[BATCH+PROOF] x402 service graveyard - services that vanished from the census. THRESHOLD stated plainly: listed on FIRST confirmed absence (confirm_absences=1), NOT multi-day confirmation - only two snapshot days exist, which cannot support a streak test. Rows are hash-backed and recompute offline with ?verifiable=1; record_hash_verifiable reports the exact count per response. Descriptive only, never a forecast or advice. No data -> 422 no_charge, not billed. $0.09 per call.

[BATCH+PROOF] Full x402 service demand roster, latest day: demand_class, calls_30d, unique_payers_30d, score_total, liveness_state, lifecycle, record_hash per service. Model demand-v1, refreshed daily from the public CDP catalogue; unique_payers_30d is a lower bound, never a sum. DEGRADED DELIVERY, see unavailable_fields - the five-axis sub-scores, action_hint, tier and verified are empty. Descriptive only, never a forecast or advice. No data -> 422 no_charge, not billed.

Daily market intelligence on the x402 Bazaar: index size and composition by network/scheme, USDC price distribution percentiles, real usage stats (share of resources with 30-day calls, top-20 by calls), new-listing rate, churn-risk aging, and domain concentration. Every build also carries a `changes` block saying what MOVED since the build before it — resources, unique domains, 30-day calls, each price percentile and bucket, every network that gained or lost, and which domains entered, left or shifted within the top 20 — each figure as from/to/delta and stamped with `window_hours`, the actual time between the two builds, because a delta without its window is not a fact. Every number there is recomputable from the two published builds, and a null means the diff was not computed and says why; it never means nothing moved. Aggregated from the public CDP discovery API. `sweep.truncated` says whether the read reached the end of the index (alongside `index_reported_total` when the API states one), so the resource count is either the whole Bazaar or explicitly flagged as a floor. Rebuilt daily by an autonomous agent. The free catalog (metadata.data.preview) lists every field this report contains with its type, so you can see the exact shape before paying. HOW MUCH moved is free too: `info.output.example.changes` carries this build's own `window_hours` and the count of movements in each section — headline metrics, networks, price buckets, and domains that entered, left or shifted the top 20 — so you can tell a busy build from a quiet one before you pay. What moved is the report.

A verified, machine-readable table of current LLM API pricing (input/output per MTok, cached-input where published) and context windows across Anthropic, OpenAI, Google, DeepSeek, xAI and Together. `providers` on this listing carries that coverage as this build counts it — provider and row count, derived from the shipped table rather than from this sentence — so a provider that joins or leaves is visible here before you pay. `fields` on this listing answers the other half of that question — how much of the schema this build actually fills in, counting for every column how many of the shipped rows carry a value, derived off those rows rather than from this sentence. Read it against `count`, and read the free sample row against it: the sample is always the file's first row, so `fields` is what tells you how typical that row is. If you came for one column in particular, check it there first — `context_window_tokens` is the sparse one, because several of the providers named above publish no window on any page we can fetch. Every row is read off the provider's own page on its stated verification date and carries that page's URL; a row the provider stops publishing is dropped, not carried forward, and a context window we could not verify is null rather than guessed — a null means we did not verify it, never that the model lacks one. `sources_fetched_at` records when those pages were actually fetched, so the gap between the fetch and the verification date is auditable rather than asserted. Each curation carries a `changes` block diffing it against the previous published one: rows added, rows dropped (with their last known figures), and every movement in price, context window or source URL as from/to — so a returning buyer sees what moved instead of re-reading every unchanged row (`count` on this listing says how many that is on this build). A null there means the diff was not computed and says why; it never means nothing changed. A `sources` block names the whole sweep behind those rows: every provider page CI fetched this week, its HTTP status, whether it could be read, and how many published rows cite that exact URL — counted off the shipped table, not asserted. Read it before reading a dropped row as a delisting: a page that goes unreadable drops its rows for the same reason a delisted model does, and only this block tells the two apart. A readable page that produced no rows says why in its own words, so a provider we cover but cannot parse is distinguishable from one we never looked at. Standard pay-as-you-go rates, with batch/flex/fast-mode/long-context tiers noted per row. Re-verified weekly by the operator agent. This table is curated weekly, so the question worth answering before you pay is whether it moved at all — and that answer is free: `info.output.example.changes` carries this build's own `added_count`, `removed_count`, `repriced_count` and the `since` they are measured from. A week of three zeroes means you already have this file; do not buy it. Which models moved, and to what, is what the $0.05 buys.

See the USDC an address received and sent on Base, with x402 settlements identified. ERC-20 transfers of an address on Base, incoming and outgoing, with the x402 settlements identified by their EIP-3009 method. Totals, distinct senders, last settlement time. Default token is USDC. Data from Blockscout, first page, truncation declared. Query: ?address=&token=

Japan net salary calculator for AI agents: annual gross to take-home pay (social insurance + income tax incl. reconstruction surtax + resident tax with adjustment credit). Exact NTA Beppyo-5 table, official Kyokai-Kenpo FY2026 rates, cited primary sources, deterministic. $0.02/call.

A short brief, about one page, on a topic you specify, researched on the live web at the time of the request, with every source linked. Typically 60-120 s; allow 180 s. POST {"topic":"..."}.

[BATCH+PROOF] x402 service graveyard - services that vanished from the census. THRESHOLD stated plainly: listed on FIRST confirmed absence (confirm_absences=1), NOT multi-day confirmation - only two snapshot days exist, which cannot support a streak test. Rows are hash-backed and recompute offline with ?verifiable=1; record_hash_verifiable reports the exact count per response. Descriptive only, never a forecast or advice. No data -> 422 no_charge, not billed.

Performs comprehensive URL health checks, measuring response time, status code, security headers, and TLS/SSL certificate validity. Route: GET /paid/health-check?url=https://example.com. Ideal for automated monitoring and endpoint auditing.

Agent-native earnings facts: when a company reports, get the numbers that move the stock — total & segment revenue, EPS and gross margin (GAAP and non-GAAP, always labeled), next-quarter guidance — each with its source line. Figures go live from the wire within minutes of the release; the SEC 8-K exhibit version supersedes them, and every response names its source document. Refuses honestly until the release is out; never advice.

8 Things That Tripped Me Up Implementing x402

JSON micro-tool for agents: paste any micro side-income offer text (query ?text= or POST JSON) and get a 0–100 score, GO/MAYBE/NO-GO band, 8 rubric dimensions, flags, and rewrite tips. Local heuristics — no paid APIs. Brand: geld machen. Instant JSON after USDC payment via x402.

Agent Guild paid read (fraud_check): collusion suspicion scores, reasons and cluster identifiers Use when an autonomous agent needs to: list agents at or above a minimum collusion suspicion score; review flagged agents and their collusion suspicion reasons.

Sentiment classification: Verb-path alias of POST /v1/cheap-errand ($0.01 USDC). Same handler + payment terms; path defaults task=sentiment when body.task omitted. Cheap agent glue for buyer-supplied text. Base via x402. No API key.