x402-protocol-integration

Use when an agent needs bazaar market report. Returns 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). $0.50.

Find better alternatives to an x402 endpoint. Given a resource URL, returns the top semantically-similar endpoints (matched on advertised purpose via description embeddings) that currently OUT-SCORE it on our deterministic trust score — so an agent about to pay a mediocre endpoint can discover a more reliable, better-settled one serving the same function. Each result carries its trust score, grade, cosine similarity, advertised price and free endpoint-page URL. The price fields stay machine-readable: amountUsd is always the raw advertised amount, and the separate boolean priceCeiling is true when the endpoint uses the x402 'upto' scheme, i.e. amountUsd is an authorization ceiling and the real charge is typically lower. Same-host siblings and 'avoid'-flagged endpoints are excluded. Returns an empty list (still a valid answer) when nothing beats the subject.

Verify any third-party x402 endpoint is alive and correctly configured before paying it: a bounded GET/402 preflight fetches the payment contract, checks reachability and response latency, validates accepts, network, price and expiry against the x402 spec, and returns a signed observation receipt with an observed_at timestamp you can cite — protection against ghost endpoints, dead quotes and wasted USDC. Limitation: no payment is made, one endpoint per call, and a passing probe proves the contr…

Verify an x402 purchase actually settled and delivered what you paid for: submit bounded, non-secret metadata for the payment requirement, payment response, delivery receipt and settlement reference, and receive a single deterministic verdict — proven, conflicting, or missing — field by field, suitable to attach to a refund request or dispute. Limitation: verdicts are computed from the artifacts you provide; we do not fetch chain state or contact the provider on your behalf.

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 or Solana. Execution is deterministic, first-party, local-only, stateless, and does not call an upstream provider; structured validation failures are not billed.

Audit CORS response headers for wildcard, credential, and cache-variance risks. 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 or Solana. Execution is deterministic, first-party, local-only, stateless, and does not call an upstream provider; structured validation failures are not billed.

Revalue amount by two rates (historical vs current). Call when ECB-style revaluation when rates are caller-supplied. Returns revalued_amount as deterministic JSON for $0.002 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.

Count likely personal-data classes without echoing detected values. 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 or Solana. Execution is deterministic, first-party, local-only, stateless, and does not call an upstream provider; structured validation failures are not billed.

Decide whether an HTTP failure is safe to retry and return an idempotency-aware policy. 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 or Solana. Execution is deterministic, first-party, local-only, stateless, and does not call an upstream provider; structured validation failures are not billed.

Redact common PII candidates before logs, prompts, or downstream tools receive the text. 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 or Solana. Execution is deterministic, first-party, local-only, stateless, and does not call an upstream provider; structured validation failures are not billed.

Normalize heterogeneous webhook events and derive a stable payload fingerprint. 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 or Solana. Execution is deterministic, first-party, local-only, stateless, and does not call an upstream provider; structured validation failures are not billed.

Detect likely credentials and private keys without returning their values. 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 or Solana. Execution is deterministic, first-party, local-only, stateless, and does not call an upstream provider; structured validation failures are not billed.

Summarize log severity and hashed error fingerprints without returning sensitive error lines. 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 or Solana. Execution is deterministic, first-party, local-only, stateless, and does not call an upstream provider; structured validation failures are not billed.

Detect removed OpenAPI paths and methods before an agent deploys a client-breaking change. 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 or Solana. Execution is deterministic, first-party, local-only, stateless, and does not call an upstream provider; structured validation failures are not billed.

Check a JSON payload against a bounded structural contract and return path-level errors. 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 or Solana. Execution is deterministic, first-party, local-only, stateless, and does not call an upstream provider; structured validation failures are not billed.

Derive a deterministic namespaced idempotency key from canonical JSON. 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 or Solana. Execution is deterministic, first-party, local-only, stateless, and does not call an upstream provider; structured validation failures are not billed.

Measure achieved reliability against an SLO target from good and total events. 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 or Solana. Execution is deterministic, first-party, local-only, stateless, and does not call an upstream provider; structured validation failures are not billed.

Anthropic Messages API over x402 - point the Anthropic SDK (or Claude Code / the Agent SDK) at base_url https://agent402.tools/v1/premium and pay $0.50 per call in USDC, no API key, no signup. Same models, caps and price as this tier's /chat/completions route; any model here is served through the Messages wire (Claude natively, others translated). Depth: `effort` (low..max) on Claude 4.7+, thinking.budget_tokens on older Claude.

OpenAI Responses API over x402 - point the OpenAI SDK's responses.create() (or the OpenAI Agents SDK) at base_url https://agent402.tools/v1/premium and pay $0.50 per call in USDC, no API key, no signup. Same models, caps and price as this tier's /chat/completions route; any model here is served through the Responses wire.

Evaluate caller-supplied x402 payment requirements before a wallet signs them. Use after receiving HTTP 402 to enforce a maximum USDC amount, allowed networks, exact scheme, recipient presence, and an optional expiry buffer. Returns eligible accepts and explicit blockers for 0.002 USDC via x402 on Base or Solana; it never signs, pays, stores, or echoes a payment signature.

Probe an x402 server end-to-end: discovery, status, tools, reliability, and OpenAPI for $0.01 USDC. Call when you need this bounded result without an API key or subscription. Returns machine-readable JSON via x402 on Base or Solana. Limitation: results cover only the supplied input or one bounded public endpoint at request time; callers must verify before acting.

Extract English machine-printed text from one caller-supplied PNG, JPEG, or WebP for $0.01 USDC. Call when you need local OCR without a vision API—not handwriting, not a URL fetch, and not a paid cloud OCR provider. Returns bounded text, confidence, and a SHA-256 receipt. No API key, no subscription.

Audit an x402 server for listing readiness, discovery quality, pricing surface, OpenAPI coverage, and integration gaps for $0.01 USDC. Call when you need a preflight report before listing or buying—not a facilitator, settlement, or certification. No API key, no subscription.

Find live x402 endpoints worth paying, by capability: returns only endpoints Delx has live-probed, each with liveness score, last-observed timestamp, observed price, response-shape validity and Agents Hive ban-list status; every row cites its probe receipt, and ghost endpoints and dead quotes are filtered out before you spend. Limitation: observations, not endorsements — freshness is bounded by the last probe cycle, and absence from the directory means unprobed, not unsafe.