Skip to main content
Glama
402signalhq

402Signal

Official
by 402signalhq
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

402Signal

Signed proof of what your agent was offered before it paid. 402Signal checks supported seller offers against buyer rules. On supported bound profiles, the local guard verifies signed evidence before your wallet signs; generic MPP offer observation does not itself provide a signed execution binding. Your application keeps its wallet, signing authority and final payment decision.

A qualifying check costs $0.003 USDC, paid over x402 with the same wallet. Completed normal misses are not settled: a check that finds no qualifying offer is free. Opening a hosted session costs $0.005 and lets you reuse one observation for 20 hops or 10 minutes. Seller payment, channel funding and network costs are separate, and a check is not a guarantee of delivery or output quality. Platform plans are quoted monthly on agreed receipt volume, workloads, capacity and support, with supported integration help and observation-triggered signed alerts. Start with a scoped evaluation. The quote states whether checking fees are included or separate. Private evidence stays in customer-owned storage; hosted retention is not included by default. See pricing.

Website · Try a sample check · Developer guides · Trust · OpenAPI · MCP · Changelog · Security policy

The service is also listed in third-party catalogues such as PayAPI Market (https://payapi.market/mcp); agents still pay https://402signal.com/route directly, and a listing is not an endorsement.

Three doors

You are

Start here

You get

A buyer or a platform embedding payments

Add the check to your client

Checks in your configured payment path; signed evidence on supported bound profiles; alerts when a new observation detects a seller change

A seller

Find your host

Your listing as buyers see it, a readiness badge, and the same public numbers as everyone else

An auditor or compliance reviewer

Verify a record

The receipt format, the public log, the anchor, and the Offer Evidence Record specification

Related MCP server: GoldBean

Start in a minute

Official x402 client. One hook adds the check to your configured seller-payment path. It pays the fee with your own wallet, re-reads the seller's challenge, verifies the signed receipt with your pinned log key, and aborts a payment whose terms differ from what was verified:

npm install @402signal/route-guard@0.7.6 && npm audit signatures
import { signalGuard } from "@402signal/route-guard/x402";
client.onBeforePaymentCreation(signalGuard({ fetchWithPayment, trustedLogVkey }));

mppx. The same guard as an onChallenge hook: import { mppGuard } from "@402signal/route-guard/mpp".

Any language. Ask for the checking-fee terms without paying anything, then resend the identical request with the payment authorization:

curl -sS -D - https://402signal.com/route \
  -H 'Content-Type: application/json' \
  --data '{"need":"web search","networks":["base"],"max_price_usd":0.02,"require_route_binding":true}'

The HTTP 402 lists the fee requirements on Base, Solana and Algorand. Use url for an exact endpoint or need to discover candidates; networks is a hard filter and prefer_network only ranks. Over MCP, call the check tool with the same arguments (route, its former name, is still accepted).

Python. pip install 402signal gives you the unpaid challenge, the paid check, read-only recovery and an offline receipt verifier (signal402.verify.verify_route_receipt).

No wallet yet? Run a sample check in the browser against a listed endpoint, ask for free check credits at ross@402signal.com (listed endpoints only), or run the offline checks with Node.js 22 or newer:

node integration/buyer-checks/run.mjs

The client and guard are published on npm with a provenance attestation and as GitHub release archives with checksums; from a reviewed checkout node scripts/install_route_guard.mjs downloads, verifies and installs the current release.

What a check returns

Result

Meaning

HTTP 402 before authorization

Checking-fee requirements; nothing has been checked yet

HTTP 200, live: true

A qualifying offer, selected_payment, billing.settled: true, and with require_route_binding a signed receipt to verify locally before signing

HTTP 200, live: false

A completed miss with a typed miss_reason; no fee

HTTP 503, binding_error: route_binding_unavailable

No probed candidate could be bound; a completed answer, not an outage. The reference wrap wrapExactAuthorize reports state=binding_unavailable with keep_calling_route: true

HTTP 503, other

Inspect billing.settlement_state: not_attempted, settled (fee settled, required evidence failed) or unknown (never reuse that authorization; use recovery)

HTTP 409, authorization_already_used

The same authorization was already final; the state and billing are disclosed, the private output is not

Read live, payable, selected_payment and billing together. A settled fee is not reversed if the seller's offer later changes.

Keys, credits and alerts

  • Check credits (X-402Signal-Trial): operator-issued, listed endpoints only, for evaluation without a funded wallet.

  • Admission keys (X-402Signal-Key): agreed ingress and capacity for platforms; never a wallet key.

  • GET /keys/usage answers only for the credentials you present: remaining credits, ceiling, expiry, or the key's recognized capacity.

  • Change alerts: with a key, POST /alerts subscribes a public HTTPS webhook to up to 20 seller hosts and delivers signed price_changed, recipient_changed and liveness_changed events drawn from the same public observations the endpoint pages count. Guide: docs/customer/alerts.md.

Evidence

Every qualifying check with require_route_binding returns an Ed25519-signed receipt bound to the exact URL, method, body hash and the seller's current x402 envelope, with an inclusion proof in an append-only log whose checkpoints are anchored on Algorand MainNet with a Falcon-1024 signature. Clients that need later verification must securely retain the complete paid /route response, including pq_trust.transparency.receipt and pq_trust.transparency.reveal, together with the original request. Private replay outcomes are short-term recovery, not long-term evidence storage. The reveal contains private request and decision evidence; do not put it in public logs.

The record format is documented as the Offer Evidence Record, version 1, with a draft x402 extension proposal. Verify a saved record with verifyReceipt from the guard, with the Python package, or in the browser at 402signal.com/verify; inspect the public log at 402signal.com/transparency.

What is in this repository

Path

Contents

live402/

The hosted service: check pipeline, replay authority, keys and alerts, MCP server, transparency log

sdk/route-guard/

Zero-dependency Node client and offline verifier, plus the x402 and mpp client hooks

sdk/python/

The 402signal Python package: challenge, check, recovery and offline verification

integration/

Reference buyer, MPP clients, offline buyer checks, MCP interoperability tests and the controlled lab

docs/

Contracts, the evidence-record specification, operating procedures and the documentation index

ops/, scripts/

Database migrations, load test, report and release tooling

Develop

Python 3.12.14 and Node 24, matching CI. Fixture mode keeps every catalog and seller response synthetic; no test needs a wallet, a facilitator or the network.

python3 -m pip install --require-hashes -r requirements.txt
LIVE402_FIXTURE=1 PYTHONPATH=. python3 -m live402          # http://127.0.0.1:8081
LIVE402_FIXTURE=1 PYTHONPATH=. python3 -m unittest discover -s tests
npm --prefix sdk/route-guard test

LOCAL_FREE=1 skips the paywall for local development and must never be set in production. See CONTRIBUTING.md for branches, reviews and the release train, and the documentation index for the replay authority, readiness, backups and scaling plans. Historical TestNet broadcasting is a 402signal (router) env capability: a security review must approve before anyone sets it to 1. Signer never reads BROADCAST, and the flag does not enable MainNet anchoring, which has its own reviewed runbook.

Contact

MIT license · Security reports · ross@402signal.com · @402Signal

Available Tools

3 tools
checkA

Runs the paid pre-flight check on a live paid API endpoint: probes one exact HTTPS url, or the candidates discovered for a need, applies the buyer's price, network and readiness rules, and returns the selected offer with signed evidence of what the seller quoted (price, recipient, asset, network, expiry) before the agent pays the seller. Does not buy the seller's service, hold keys or pay anything for the agent; the agent keeps its wallet and pays the seller separately.

Use preview to discover candidates without paying, validate for a free readiness check of one listed URL, and check when a fresh live observation or a signed receipt is needed before a seller payment. Never call check to pay a seller. After billing.settlement_state=unknown, stop and reconcile; never create another authorization. route is the former name of this tool and is still accepted.

Cost and outcomes: the first unsigned call answers HTTP 402 with the $0.003 USDC checking-fee terms (Base, Solana or Algorand), which an x402-capable HTTP client pays. The fee settles only when a qualifying live offer is found; a completed miss (HTTP 200, live=false, typed miss_reason) is free; a settled fee is not reversed if the offer later changes. HTTP 503 with binding_error=route_binding_unavailable means the seller answered but no probed candidate could be bound to a signed receipt: a completed unpaid answer, not an outage (the reference wrapExactAuthorize reports state=binding_unavailable with keep_calling_route true).

Parameter interactions: need or url is required; with both, url is probed directly and no discovery runs. policy is plain English compiled into the structured fields; an explicit structured field wins over the compiled value, and phrases that do not compile are echoed in unresolved_constraints, never guessed. networks is a hard allowlist judged on the current 402; prefer_network only orders results and never filters. Three independent price bounds: max_price_usd (seller price in USD), max_amount_atomic (atomic units of the seller's asset) and max_total_cost_usd (seller price plus known fees); every bound fails closed when its value is unknown. require_route_binding=true implies require_transparency and may select the next bindable candidate. Defaults: objective best, search_depth standard (up to 7 probes; thorough up to 15; hard ceiling 20), accept_payTo_change false, require_route_binding false. Guide: https://402signal.com/developers#route-binding

ParametersJSON Schema
NameRequiredDescriptionDefault
urlNoOptional https URL to probe instead of discovery. need or url (or both) is required.
needNoWhat the caller wants routed (plain English).
policyNoNatural-language constraints compiled into structured values. Unresolved phrases are returned, never guessed.
networksNoHard policy lock. Restricts discovery and selection to this set. A HTTP 200 winner must have selected_payment.network in this set from the CURRENT observed 402, never a catalog claim. Unlike prefer_network, this is not a ranking preference.
objectiveNoBest-of-N among currently probed eligible candidates, not every discovered endpoint. cheapest, fastest, and most_reliable rank that probed survivor set. fastest is this-request probe RTT, not settlement latency. fastest_settlement is a separate settlement/finality objective. lowest_total_cost fails closed when a fee is unknown.
search_depthNostandard: first 3 then expand 2-4 (typical cap 7). thorough may expand further. Hard server ceiling is 20.
max_price_usdNoDrop live hits whose known normalized USD exceeds this bound. Unknown USD fails closed.
max_latency_msNoCompatibility alias for max_probe_latency_ms (this request's probe RTT). Unknown latency fails closed.
prefer_networkNoWeak ranking preference only. Ranks this seller network first but still searches and selects across all supported networks. Not a filter. Use networks for a hard policy lock. Observed networks: base, solana, algorand and the EVM chains polygon, arbitrum, monad, worldchain, xlayer, bnb, hyperevm, ethereum, optimism, avalanche, tempo, sei, celo, robinhood (CAIP-2 ids such as eip155:137 are accepted); the checking fee itself is paid on base, solana or algorand.
min_observationsNoRequire history n_7d at least this large. Unknown or smaller fails closed.
max_amount_atomicNoDrop live hits whose known atomic amount exceeds this bound. Unknown or cross-asset amount fails closed.
require_invocableNoIf true, drop live hits without an input schema. An explicit empty-object schema (type object, no properties or required fields) advertises no required inputs and counts as present. A bazaar HTTP GET with empty queryParams and no required body is the same signal. It does not guarantee the seller call succeeds. Absent or refused schema is not invocable.
max_total_cost_usdNoMerchant price plus known fees. Unknown fee fails closed.
accept_payTo_changeNoIf true, allow selecting a destination whose payTo just changed for the first time. Default false: the first unexpected payTo change is not selectable; a second later independent observation of the same destination can establish it.
max_probe_latency_msNoDrop live hits whose known probe RTT exceeds this bound. Not historical service/p50 latency.
min_observed_successNoRequire observed success_7d when n_7d >= 3. Unknown fails closed.
min_reputation_scoreNoRequire V1 reputation_score. Unknown fails closed. Never guessed from vague NL.
require_transparencyNoIf true, a settled /route winner fails when a signed checkpoint receipt cannot be produced. This requires delivery of verifiable evidence on HTTP 200, not server-side recovery. To verify the routing decision later, securely retain the complete paid /route response, especially pq_trust.transparency.receipt and pq_trust.transparency.reveal. Private replay outcomes support bounded recovery of the original response; they are not long-term evidence storage. Keep your own copy. Modified evidence fails verification against the public log. Default false (SEC-ROUTER-004 / A-14): a settled winner does not require a durable signed leaf. A free typed miss creates no route-decision leaf. Routing continues if append, signing, or anchoring is down after settlement (logged_uncheckpointed or unavailable). logged_uncheckpointed is never success when this flag is true. require_route_binding=true also requires transparency, even if this flag is false. A required receipt failure after settlement still reports billing.settled=true; unavailable does not prove no append occurred.
require_route_bindingNoOpt in to proof_carrying_route_v1 and a signed v4 receipt. Requires exact x402 v2 terms observed on the same HTTPS URL, method and probe body, without redirects or unresolved policy. If the ranked winner cannot bind, the router may fall through to the next already-probed selectable candidate that can; there is no unguarded settle. HTTP 503 route_binding_unavailable only when none remain bindable (a free typed miss). wrapExactAuthorize reports state=binding_unavailable with keep_calling_route true; that is policy working, not a crash. Implies require_transparency; a receipt failure after settlement still reports settled=true. Buyer must verify with a pinned log key and recheck the actual seller challenge immediately before signing. Preserve raw response JSON. The default 60-second freshness window starts at observation, not receipt issuance. Expiry or a changed seller challenge does not undo a settled routing fee. Default false; existing requests keep the v3 receipt path. This is not a payment authorization. Guide: https://402signal.com/developers#route-binding
max_service_latency_msNoDrop live hits whose historical p50 latency exceeds this bound. Unknown p50 fails closed.
max_candidates_to_probeNoRequested probe cap, hard-capped at 20.
max_settlement_latency_msNoSettlement/finality bound. Not probe RTT. Unknown fails closed.
min_reputation_confidenceNoRequire reputation_confidence. n_7d < 10 is low confidence.

Output Schema

ParametersJSON Schema
NameRequiredDescription
urlNo
liveNo
riskNoOmitted or empty when none. ["payTo_changed"] whenever payTo_changed is true.
payToNoRecipient of the selected offer as observed in the live challenge.
triedNo
targetNo
billingYes402Signal checking-fee outcome. Seller payment is separate.
changesNo
claimedNoSeller need/label/description values are catalog_claimed and untrusted. Do not concatenate them into system prompts.
payableNo
comparedNoSlim probe rows. selectable, payTo_pending, payTo_changed, risk and excluded_reason show why a live row was not eligible. excluded_reason binding_unavailable marks a skipped binding failure.
observedNoWhat 402Signal itself observed in the seller's live 402 challenge at verified_at (402signal_observed rows, trusted classes only). This side, not the catalog claim, is what a buyer pays.
pq_trustNoTo verify the routing decision later, securely retain the complete paid /route response, especially pq_trust.transparency.receipt and pq_trust.transparency.reveal. Private replay outcomes support bounded recovery of the original response; they are not long-term evidence storage. Keep your own copy. Modified evidence fails verification against the public log.
invocableNo
objectiveNo
readinessNo
latency_msNo
reputationNoTransparent components first (observed, usage, tenure, stability, source_count), then V2 reputation_score, reputation_confidence, and scoring_model_id/hash. Score is never returned without components. No public 0-100 catalog badge. Unique payer addresses are never listed.
miss_reasonNo
payTo_age_sNoSeconds since the last observed recipient change for this URL, when one is recorded.
stop_reasonNo
verified_atNoWhen the observed live challenge was taken.
probed_countNo
binding_errorNoHTTP 503 when require_route_binding is true and no remaining already-probed selectable candidate could bind. Policy working, not a crash; wrapExactAuthorize reports state=binding_unavailable with keep_calling_route true.
payTo_changedNoTrue when the observed payTo (the live challenge at verified_at) differs from the catalog claim (claimed.payTo at claimed_at) or from the last trusted destination 402Signal itself observed for this URL. Compare claimed.payTo with observed.payTo; the observed side is the one a buyer would pay.
payTo_pendingNoFirst unexpected rotation of the observed payTo against 402Signal's own previous trusted observation of this URL, judged on that history alone (an updated catalog claim does not clear it). Not selectable unless accept_payTo_change is true; a second independent observation of the same destination establishes it.
probe_ceilingNo
schema_sourceNo
observed_age_sNoSeconds since observed.observed_at.
unprobed_countNo
decision_bindingNoOpt in to proof_carrying_route_v1 and a signed v4 receipt. Requires exact x402 v2 terms observed on the same HTTPS URL, method and probe body, without redirects or unresolved policy. If the ranked winner cannot bind, the router may fall through to the next already-probed selectable candidate that can; there is no unguarded settle. HTTP 503 route_binding_unavailable only when none remain bindable (a free typed miss). wrapExactAuthorize reports state=binding_unavailable with keep_calling_route true; that is policy working, not a crash. Implies require_transparency; a receipt failure after settlement still reports settled=true. Buyer must verify with a pinned log key and recheck the actual seller challenge immediately before signing. Preserve raw response JSON. The default 60-second freshness window starts at observation, not receipt issuance. Expiry or a changed seller challenge does not undo a settled routing fee. Default false; existing requests keep the v3 receipt path. This is not a payment authorization. Guide: https://402signal.com/developers#route-binding
discovered_countNo
selected_paymentNo
candidates_probedNo
discovery_matchesNo
unmet_constraintsNo
challenge_observedNo
applied_constraintsNo
claimed_payTo_matchNoWhether observed.payTo equals claimed.payTo, compared per rail (case-insensitive on EVM). False on a mismatch; null when either side is unknown. Independent of payTo_pending, which judges against 402Signal's own observation history.
evaluation_completeNo
candidates_consideredNo
candidates_discoveredNo
probe_budget_exhaustedNo
unresolved_constraintsNo
interpreted_constraintsNo
candidate_evaluation_completeNo

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations cover only the safety profile (readOnly=false, destructive=false, openWorld=true, idempotent=false); the description adds the economics and failure semantics an agent cannot infer: the HTTP 402 / $0.003 USDC fee flow, fee settles only on a qualifying live offer, a completed miss is free, settled fees are not reversed, and 503 binding_error=route_binding_unavailable is a completed unpaid answer rather than an outage. This is exactly the extra context annotations cannot carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then usage, then cost/outcomes, then parameter interactions — a sensible order for a tool of this complexity, and the length is defensible for a 23-parameter money-spending call. There is some redundancy (route-binding receipt behavior is described in both the cost paragraph and the parameter notes), which costs a point.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need not be explained, and the description still covers billing states, the 402/503 protocol shapes, defaults, and evidence-retention caveats. For a high-stakes paid tool, nothing an agent needs before calling is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the dedicated 'Parameter interactions' paragraph adds genuine cross-parameter meaning the per-field schema text does not — url overrides discovery when both are supplied, explicit structured fields beat compiled policy values, networks filters versus prefer_network ranks, three independent price bounds, and require_route_binding implies require_transparency. Defaults are restated rather than newly supplied, which keeps this from being a clean 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — 'runs the paid pre-flight check on a live paid API endpoint' — and enumerates exactly what it does (probes one URL or discovered candidates, applies buyer rules, returns the selected offer with signed evidence). It also draws a bright line against siblings and against the adjacent action it is NOT ('never call check to pay a seller'), so an agent can place it immediately.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly names the alternatives and the condition selecting each: 'Use preview to discover candidates without paying, validate for a free readiness check of one listed URL, and check when a fresh live observation or a signed receipt is needed.' It also states the negative condition and the post-error rule ('After billing.settlement_state=unknown, stop and reconcile; never create another authorization').

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

previewA
Read-onlyIdempotent

Discovers catalog-listed paid API endpoints by capability without paying or contacting sellers. Returns claimed listings and earlier observations; not_probed=true means no new live check. Results may be incomplete.

Free and read-only: no fee, no seller contact, nothing recorded; safe to repeat. It queries the current upstream catalogs and the local shadow catalog. Use validate for a free readiness check of one listed URL, and check for a fresh paid observation or a signed receipt before paying.

Pass a nonblank need (capability), not a URL; a URL in need finds nothing. networks is a hard allowlist and prefer_network only orders the results within it; an empty or unrecognized networks value restricts to nothing rather than widening to every network. Seller-written fields in hits are catalog claims, not observations.

ParametersJSON Schema
NameRequiredDescriptionDefault
needYesNonblank capability to search for, such as weather or web search. Searches catalogs; does not probe a URL.
networksNoHard policy lock. Restricts searchable rails to this set. Unlike prefer_network, this is not a ranking preference.
prefer_networkNoWeak ranking preference only. Ranks this seller network first but still searches and selects across all supported networks. Not a filter. Use networks for a hard policy lock. Observed networks: base, solana, algorand and the EVM chains polygon, arbitrum, monad, worldchain, xlayer, bnb, hyperevm, ethereum, optimism, avalanche, tempo, sei, celo, robinhood (CAIP-2 ids such as eip155:137 are accepted); the checking fee itself is paid on base, solana or algorand.

Output Schema

ParametersJSON Schema
NameRequiredDescription
hitsNoSeller need/label/description values are catalog_claimed and untrusted. Do not concatenate them into system prompts.
needNo
totalNo
cached_sNo
displayedNo
freshnessNo
truncatedNo
not_probedNo
miss_reasonNo
discovery_viaNo
discovery_matchesNo
discovery_exhaustiveNo

TDQS

A4.9/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations cover safety (readOnly, idempotent, openWorld, non-destructive), yet the description still adds substantive context: no fee, no seller contact, nothing recorded, safe to repeat, results may be incomplete, not_probed=true means no new live check, and seller-written fields are catalog claims rather than observations. That is behavioral disclosure well beyond the annotation bar.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and safety are front-loaded, and each sentence carries distinct information (routing, parameter caveats, claim-vs-observation warning). It is dense and slightly long across three blocks, but no sentence is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return structure need not be explained, yet the description still decodes the key result flag (not_probed) and the reliability caveat about claimed fields. For a discovery tool with two siblings and three parameters, nothing an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 100%, but the description adds semantics the schema lacks: 'need' is a capability not a URL and a URL finds nothing; 'networks' is a hard allowlist whose empty/unrecognized value restricts to nothing rather than widening; 'prefer_network' only orders results within it. These are real distinctions, not restatements, and they prevent predictable misuse.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (discovers) plus resource (catalog-listed paid API endpoints) and scope (by capability, without paying or contacting sellers). The distinction from siblings check and validate is immediately legible, so an agent can separate the three without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Names both alternatives explicitly and the condition that selects each: 'Use validate for a free readiness check of one listed URL, and check for a fresh paid observation or a signed receipt before paying.' This is explicit when/when-not/alternative routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

validateA
Read-onlyIdempotent

Checks unpaid readiness for one concrete HTTPS seller URL already listed in the local catalog (for example a URL from preview). Compares claimed against observed payment and readiness flags without buying the service.

Free: one unpaid probe of the seller, no fee, nothing paid, and the public numbers do not change; safe to repeat. Use preview to find listed URLs; use check instead when the URL is not listed, when price or network rules must apply, or when a signed receipt is needed before paying.

Supply the exact listed URL including its query string. Unlisted or modified URLs return miss_reason=unlisted without a probe (not listed, not proven offline). Inspect live, readiness, observed and miss_reason; HTTP 200 alone is not success. No price or network filter and no signed receipt.

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesExact concrete HTTPS URL already listed in the local catalog, including its query string. Unlisted URLs are not probed.

Output Schema

ParametersJSON Schema
NameRequiredDescription
urlNo
liveNo
n_7dNo
flagsNo
claimedNoSeller need/label/description values are catalog_claimed and untrusted. Do not concatenate them into system prompts.
payableNo
observedNo
invocableNo
readinessNo
miss_reasonNo

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds rich behavioral detail beyond the annotations: it is free, performs one unpaid probe, does not change public numbers, is safe to repeat, returns miss_reason=unlisted for unlisted/modified URLs, and warns that HTTP 200 alone is not success. This aligns with readOnlyHint, idempotentHint, and destructiveHint=false with no contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-organized into purpose, usage guidance, and parameter behavior, and is front-loaded with the core action. There is minor redundancy (e.g., 'no fee, nothing paid' restates 'free' and the no-filter/receipt point repeats the check-routing sentence), but it remains tight and scannable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter, read-only, idempotent tool with an output schema, the description covers everything needed: how to get valid URLs, what happens for invalid/unlisted URLs, how to interpret results, and when to use sibling tools. Nothing essential is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema already documents the url parameter. The description adds meaningful behavioral nuance: the URL must be exact, include the query string, be already listed, and unlisted URLs will not be probed. This goes beyond the schema's wording.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Checks unpaid readiness for one concrete HTTPS seller URL already listed in the local catalog' and clarifies it compares claimed vs observed readiness flags. It also differentiates from siblings by naming preview and check in the routing guidance.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit guidance is provided: 'Use preview to find listed URLs; use check instead when the URL is not listed, when price or network rules must apply, or when a signed receipt is needed.' This clearly tells an agent when to use validate versus its siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 4 tool updatesv0.1.5
    • Changedcheck20 fields changed
      • changedInput schema / properties / networks / items / enum
        Previous value: -[
-  "base",
-  "solana",
-  "algorand",
-  "polygon",
-  "arbitrum",
-  "monad",
-  "worldchain",
-  "xlayer",
-  "bnb",
-  "hyperevm",
-  "ethereum",
-  "optimism",
-  "avalanche",
-  "tempo"
-]New value: +[
+  "base",
+  "solana",
+  "algorand",
+  "polygon",
+  "arbitrum",
+  "monad",
+  "worldchain",
+  "xlayer",
+  "bnb",
+  "hyperevm",
+  "ethereum",
+  "optimism",
+  "avalanche",
+  "tempo",
+  "sei",
+  "celo",
+  "robinhood"
+]
      • changedInput schema / properties / prefer_network / description
        Previous value: -"Weak ranking preference only. Ranks this seller network first but still searches and selects across all supported networks. Not a filter. Use networks for a hard policy lock. Observed networks: base, solana, algorand and the EVM chains polygon, arbitrum, monad, worldchain, xlayer, bnb, hyperevm, ethereum, optimism, avalanche (CAIP-2 ids such as eip155:137 are accepted); the checking fee itself is paid on base, solana or algorand."New value: +"Weak ranking preference only. Ranks this seller network first but still searches and selects across all supported networks. Not a filter. Use networks for a hard policy lock. Observed networks: base, solana, algorand and the EVM chains polygon, arbitrum, monad, worldchain, xlayer, bnb, hyperevm, ethereum, optimism, avalanche, tempo, sei, celo, robinhood (CAIP-2 ids such as eip155:137 are accepted); the checking fee itself is paid on base, solana or algorand."
      • changedInput schema / properties / prefer_network / enum
        Previous value: -[
-  "base",
-  "solana",
-  "algorand",
-  "polygon",
-  "arbitrum",
-  "monad",
-  "worldchain",
-  "xlayer",
-  "bnb",
-  "hyperevm",
-  "ethereum",
-  "optimism",
-  "avalanche",
-  "tempo"
-]New value: +[
+  "base",
+  "solana",
+  "algorand",
+  "polygon",
+  "arbitrum",
+  "monad",
+  "worldchain",
+  "xlayer",
+  "bnb",
+  "hyperevm",
+  "ethereum",
+  "optimism",
+  "avalanche",
+  "tempo",
+  "sei",
+  "celo",
+  "robinhood"
+]
      • addedOutput schema / properties / claimed / properties / amount / description
        Added value: +"The price the catalog listing claimed, as of claimed_at."
      • addedOutput schema / properties / claimed / properties / claimed_at
        Added value: +{
+  "description": "When the discovery feed last presented these claimed values for this URL.",
+  "type": [
+    "string",
+    "integer",
+    "null"
+  ]
+}
      • addedOutput schema / properties / claimed / properties / facilitator
        Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
      • addedOutput schema / properties / claimed / properties / payTo / description
        Added value: +"The recipient the catalog listing claimed, as of claimed_at. Compare with observed.payTo."
      • addedOutput schema / properties / claimed_payTo_match
        Added value: +{
+  "description": "Whether observed.payTo equals claimed.payTo, compared per rail (case-insensitive on EVM). False on a mismatch; null when either side is unknown. Independent of payTo_pending, which judges against 402Signal's own observation history.",
+  "type": [
+    "boolean",
+    "null"
+  ]
+}
      • changedOutput schema / properties / miss_reason / enum
        Previous value: -[
-  "no_candidates",
-  "no_402_envelope",
-  "no_payto",
-  "reachable_200",
-  "probe_timeout",
-  "quote_expired",
-  "invalid_need",
-  "upstream_5xx",
-  "ssrf",
-  "unlisted",
-  "no_input_schema",
-  "constraints_unmet",
-  "probe_budget_exhausted",
-  "probe_limit_reached",
-  "unsafe_to_probe",
-  "settlement_unknown",
-  "authorization_used",
-  "probe_capacity",
-  "window_spent",
-  "fingerprint_miss",
-  "scheme_mismatch",
-  "network_mismatch",
-  "invalid_session_shape",
-  null
-]New value: +[
+  "no_candidates",
+  "no_402_envelope",
+  "no_payto",
+  "reachable_200",
+  "probe_timeout",
+  "quote_expired",
+  "invalid_need",
+  "upstream_5xx",
+  "ssrf",
+  "unlisted",
+  "no_input_schema",
+  "constraints_unmet",
+  "binding_unavailable",
+  "probe_budget_exhausted",
+  "probe_limit_reached",
+  "unsafe_to_probe",
+  "settlement_unknown",
+  "authorization_used",
+  "probe_capacity",
+  "window_spent",
+  "fingerprint_miss",
+  "scheme_mismatch",
+  "network_mismatch",
+  "invalid_session_shape",
+  null
+]
      • addedOutput schema / properties / observed
        Added value: +{
+  "description": "What 402Signal itself observed in the seller's live 402 challenge at verified_at (402signal_observed rows, trusted classes only). This side, not the catalog claim, is what a buyer pays.",
+  "properties": {
+    "amount": {
+      "description": "Price in the observed challenge at verified_at.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "http_status": {
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "invocable": {
+      "type": [
+        "boolean",
+        "integer",
+        "null"
+      ]
+    },
+    "latency_ms": {
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "observed_at": {
+      "description": "When that observation was made.",
+      "type": [
+        "string",
+        "integer",
+        "null"
+      ]
+    },
+    "payTo": {
+      "description": "Recipient in the observed challenge at verified_at.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "payable": {
+      "type": [
+        "boolean",
+        "integer",
+        "null"
+      ]
+    },
+    "schema_present": {
+      "type": [
+        "boolean",
+        "integer",
+        "null"
+      ]
+    }
+  },
+  "type": "object"
+}
      • addedOutput schema / properties / observed_age_s
        Added value: +{
+  "description": "Seconds since observed.observed_at.",
+  "type": [
+    "integer",
+    "null"
+  ]
+}
      • addedOutput schema / properties / payTo
        Added value: +{
+  "description": "Recipient of the selected offer as observed in the live challenge.",
+  "type": [
+    "string",
+    "null"
+  ]
+}
      • addedOutput schema / properties / payTo_age_s
        Added value: +{
+  "description": "Seconds since the last observed recipient change for this URL, when one is recorded.",
+  "type": [
+    "integer",
+    "null"
+  ]
+}
      • addedOutput schema / properties / payTo_changed
        Added value: +{
+  "description": "True when the observed payTo (the live challenge at verified_at) differs from the catalog claim (claimed.payTo at claimed_at) or from the last trusted destination 402Signal itself observed for this URL. Compare claimed.payTo with observed.payTo; the observed side is the one a buyer would pay.",
+  "type": "boolean"
+}
      • addedOutput schema / properties / payTo_pending
        Added value: +{
+  "description": "First unexpected rotation of the observed payTo against 402Signal's own previous trusted observation of this URL, judged on that history alone (an updated catalog claim does not clear it). Not selectable unless accept_payTo_change is true; a second independent observation of the same destination establishes it.",
+  "type": "boolean"
+}
      • addedOutput schema / properties / readiness
        Added value: +{
+  "enum": [
+    "discovered",
+    "payable",
+    "invocable",
+    "recently_verified"
+  ],
+  "type": "string"
+}
      • addedOutput schema / properties / reputation / description
        Added value: +"Transparent components first (observed, usage, tenure, stability, source_count), then V2 reputation_score, reputation_confidence, and scoring_model_id/hash. Score is never returned without components. No public 0-100 catalog badge. Unique payer addresses are never listed."
      • addedOutput schema / properties / reputation / properties
        Added value: +{
+  "stability": {
+    "description": "Observed changes to this URL's terms (402signal_observed, not catalog claims): a change is a live challenge whose recipient, price, schema or rail differed from the previous trusted observation of the same URL.",
+    "properties": {
+      "payTo_changes": {
+        "properties": {
+          "changed_at": {
+            "description": "RFC3339 time of the last observed change, or null.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "count": {
+            "description": "Observed changes in the window; null when unknown.",
+            "type": [
+              "integer",
+              "null"
+            ]
+          }
+        },
+        "type": "object"
+      },
+      "price_changes": {
+        "properties": {
+          "changed_at": {
+            "description": "RFC3339 time of the last observed change, or null.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "count": {
+            "description": "Observed changes in the window; null when unknown.",
+            "type": [
+              "integer",
+              "null"
+            ]
+          }
+        },
+        "type": "object"
+      },
+      "rail_changes": {
+        "properties": {
+          "changed_at": {
+            "description": "RFC3339 time of the last observed change, or null.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "count": {
+            "description": "Observed changes in the window; null when unknown.",
+            "type": [
+              "integer",
+              "null"
+            ]
+          }
+        },
+        "type": "object"
+      },
+      "schema_changes": {
+        "properties": {
+          "changed_at": {
+            "description": "RFC3339 time of the last observed change, or null.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "count": {
+            "description": "Observed changes in the window; null when unknown.",
+            "type": [
+              "integer",
+              "null"
+            ]
+          }
+        },
+        "type": "object"
+      }
+    },
+    "type": "object"
+  }
+}
      • addedOutput schema / properties / risk
        Added value: +{
+  "description": "Omitted or empty when none. [\"payTo_changed\"] whenever payTo_changed is true.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
      • addedOutput schema / properties / verified_at
        Added value: +{
+  "description": "When the observed live challenge was taken.",
+  "type": [
+    "string",
+    "null"
+  ]
+}
    • Changedpreview4 fields changed
      • changedInput schema / properties / networks / items / enum
        Previous value: -[
-  "base",
-  "solana",
-  "algorand",
-  "polygon",
-  "arbitrum",
-  "monad",
-  "worldchain",
-  "xlayer",
-  "bnb",
-  "hyperevm",
-  "ethereum",
-  "optimism",
-  "avalanche",
-  "tempo"
-]New value: +[
+  "base",
+  "solana",
+  "algorand",
+  "polygon",
+  "arbitrum",
+  "monad",
+  "worldchain",
+  "xlayer",
+  "bnb",
+  "hyperevm",
+  "ethereum",
+  "optimism",
+  "avalanche",
+  "tempo",
+  "sei",
+  "celo",
+  "robinhood"
+]
      • changedInput schema / properties / prefer_network / description
        Previous value: -"Weak ranking preference only. Ranks this seller network first but still searches and selects across all supported networks. Not a filter. Use networks for a hard policy lock. Observed networks: base, solana, algorand and the EVM chains polygon, arbitrum, monad, worldchain, xlayer, bnb, hyperevm, ethereum, optimism, avalanche (CAIP-2 ids such as eip155:137 are accepted); the checking fee itself is paid on base, solana or algorand."New value: +"Weak ranking preference only. Ranks this seller network first but still searches and selects across all supported networks. Not a filter. Use networks for a hard policy lock. Observed networks: base, solana, algorand and the EVM chains polygon, arbitrum, monad, worldchain, xlayer, bnb, hyperevm, ethereum, optimism, avalanche, tempo, sei, celo, robinhood (CAIP-2 ids such as eip155:137 are accepted); the checking fee itself is paid on base, solana or algorand."
      • changedInput schema / properties / prefer_network / enum
        Previous value: -[
-  "base",
-  "solana",
-  "algorand",
-  "polygon",
-  "arbitrum",
-  "monad",
-  "worldchain",
-  "xlayer",
-  "bnb",
-  "hyperevm",
-  "ethereum",
-  "optimism",
-  "avalanche",
-  "tempo"
-]New value: +[
+  "base",
+  "solana",
+  "algorand",
+  "polygon",
+  "arbitrum",
+  "monad",
+  "worldchain",
+  "xlayer",
+  "bnb",
+  "hyperevm",
+  "ethereum",
+  "optimism",
+  "avalanche",
+  "tempo",
+  "sei",
+  "celo",
+  "robinhood"
+]
      • changedOutput schema / properties / miss_reason / enum
        Previous value: -[
-  "no_candidates",
-  "no_402_envelope",
-  "no_payto",
-  "reachable_200",
-  "probe_timeout",
-  "quote_expired",
-  "invalid_need",
-  "upstream_5xx",
-  "ssrf",
-  "unlisted",
-  "no_input_schema",
-  "constraints_unmet",
-  "probe_budget_exhausted",
-  "probe_limit_reached",
-  "unsafe_to_probe",
-  "settlement_unknown",
-  "authorization_used",
-  "probe_capacity",
-  "window_spent",
-  "fingerprint_miss",
-  "scheme_mismatch",
-  "network_mismatch",
-  "invalid_session_shape",
-  null
-]New value: +[
+  "no_candidates",
+  "no_402_envelope",
+  "no_payto",
+  "reachable_200",
+  "probe_timeout",
+  "quote_expired",
+  "invalid_need",
+  "upstream_5xx",
+  "ssrf",
+  "unlisted",
+  "no_input_schema",
+  "constraints_unmet",
+  "binding_unavailable",
+  "probe_budget_exhausted",
+  "probe_limit_reached",
+  "unsafe_to_probe",
+  "settlement_unknown",
+  "authorization_used",
+  "probe_capacity",
+  "window_spent",
+  "fingerprint_miss",
+  "scheme_mismatch",
+  "network_mismatch",
+  "invalid_session_shape",
+  null
+]
    • Removedroute
    • Changedvalidate5 fields changed
      • addedOutput schema / properties / claimed / properties / amount / description
        Added value: +"The price the catalog listing claimed, as of claimed_at."
      • addedOutput schema / properties / claimed / properties / claimed_at
        Added value: +{
+  "description": "When the discovery feed last presented these claimed values for this URL.",
+  "type": [
+    "string",
+    "integer",
+    "null"
+  ]
+}
      • addedOutput schema / properties / claimed / properties / facilitator
        Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
      • addedOutput schema / properties / claimed / properties / payTo / description
        Added value: +"The recipient the catalog listing claimed, as of claimed_at. Compare with observed.payTo."
      • changedOutput schema / properties / miss_reason / enum
        Previous value: -[
-  "no_candidates",
-  "no_402_envelope",
-  "no_payto",
-  "reachable_200",
-  "probe_timeout",
-  "quote_expired",
-  "invalid_need",
-  "upstream_5xx",
-  "ssrf",
-  "unlisted",
-  "no_input_schema",
-  "constraints_unmet",
-  "probe_budget_exhausted",
-  "probe_limit_reached",
-  "unsafe_to_probe",
-  "settlement_unknown",
-  "authorization_used",
-  "probe_capacity",
-  "window_spent",
-  "fingerprint_miss",
-  "scheme_mismatch",
-  "network_mismatch",
-  "invalid_session_shape",
-  null
-]New value: +[
+  "no_candidates",
+  "no_402_envelope",
+  "no_payto",
+  "reachable_200",
+  "probe_timeout",
+  "quote_expired",
+  "invalid_need",
+  "upstream_5xx",
+  "ssrf",
+  "unlisted",
+  "no_input_schema",
+  "constraints_unmet",
+  "binding_unavailable",
+  "probe_budget_exhausted",
+  "probe_limit_reached",
+  "unsafe_to_probe",
+  "settlement_unknown",
+  "authorization_used",
+  "probe_capacity",
+  "window_spent",
+  "fingerprint_miss",
+  "scheme_mismatch",
+  "network_mismatch",
+  "invalid_session_shape",
+  null
+]
  2. 4 tool updatesv0.1.4
    • Addedcheck
    • Changedpreview4 fields changed
      • changedInput schema / properties / networks / items / enum
        Previous value: -[
-  "base",
-  "solana",
-  "algorand"
-]New value: +[
+  "base",
+  "solana",
+  "algorand",
+  "polygon",
+  "arbitrum",
+  "monad",
+  "worldchain",
+  "xlayer",
+  "bnb",
+  "hyperevm",
+  "ethereum",
+  "optimism",
+  "avalanche",
+  "tempo"
+]
      • changedInput schema / properties / prefer_network / description
        Previous value: -"Weak ranking preference only. Ranks this pay-in rail first but still searches and selects across all supported rails. Not a filter. Use networks for a hard policy lock."New value: +"Weak ranking preference only. Ranks this seller network first but still searches and selects across all supported networks. Not a filter. Use networks for a hard policy lock. Observed networks: base, solana, algorand and the EVM chains polygon, arbitrum, monad, worldchain, xlayer, bnb, hyperevm, ethereum, optimism, avalanche (CAIP-2 ids such as eip155:137 are accepted); the checking fee itself is paid on base, solana or algorand."
      • changedInput schema / properties / prefer_network / enum
        Previous value: -[
-  "base",
-  "solana",
-  "algorand"
-]New value: +[
+  "base",
+  "solana",
+  "algorand",
+  "polygon",
+  "arbitrum",
+  "monad",
+  "worldchain",
+  "xlayer",
+  "bnb",
+  "hyperevm",
+  "ethereum",
+  "optimism",
+  "avalanche",
+  "tempo"
+]
      • changedOutput schema / properties / miss_reason / enum
        Previous value: -[
-  "no_candidates",
-  "no_402_envelope",
-  "no_payto",
-  "reachable_200",
-  "probe_timeout",
-  "quote_expired",
-  "invalid_need",
-  "upstream_5xx",
-  "ssrf",
-  "no_input_schema",
-  "constraints_unmet",
-  "probe_budget_exhausted",
-  "probe_limit_reached",
-  "unsafe_to_probe",
-  "settlement_unknown",
-  "probe_capacity",
-  null
-]New value: +[
+  "no_candidates",
+  "no_402_envelope",
+  "no_payto",
+  "reachable_200",
+  "probe_timeout",
+  "quote_expired",
+  "invalid_need",
+  "upstream_5xx",
+  "ssrf",
+  "unlisted",
+  "no_input_schema",
+  "constraints_unmet",
+  "probe_budget_exhausted",
+  "probe_limit_reached",
+  "unsafe_to_probe",
+  "settlement_unknown",
+  "authorization_used",
+  "probe_capacity",
+  "window_spent",
+  "fingerprint_miss",
+  "scheme_mismatch",
+  "network_mismatch",
+  "invalid_session_shape",
+  null
+]
    • Changedroute14 fields changed
      • changedInput schema / properties / networks / items / enum
        Previous value: -[
-  "base",
-  "solana",
-  "algorand"
-]New value: +[
+  "base",
+  "solana",
+  "algorand",
+  "polygon",
+  "arbitrum",
+  "monad",
+  "worldchain",
+  "xlayer",
+  "bnb",
+  "hyperevm",
+  "ethereum",
+  "optimism",
+  "avalanche",
+  "tempo"
+]
      • changedInput schema / properties / prefer_network / description
        Previous value: -"Weak ranking preference only. Ranks this pay-in rail first but still searches and selects across all supported rails. Not a filter. Use networks for a hard policy lock."New value: +"Weak ranking preference only. Ranks this seller network first but still searches and selects across all supported networks. Not a filter. Use networks for a hard policy lock. Observed networks: base, solana, algorand and the EVM chains polygon, arbitrum, monad, worldchain, xlayer, bnb, hyperevm, ethereum, optimism, avalanche (CAIP-2 ids such as eip155:137 are accepted); the checking fee itself is paid on base, solana or algorand."
      • changedInput schema / properties / prefer_network / enum
        Previous value: -[
-  "base",
-  "solana",
-  "algorand"
-]New value: +[
+  "base",
+  "solana",
+  "algorand",
+  "polygon",
+  "arbitrum",
+  "monad",
+  "worldchain",
+  "xlayer",
+  "bnb",
+  "hyperevm",
+  "ethereum",
+  "optimism",
+  "avalanche",
+  "tempo"
+]
      • changedInput schema / properties / require_route_binding / description
        Previous value: -"Opt in to proof_carrying_route_v1 and a signed v4 receipt. Requires exact x402 v2 terms observed on the same HTTPS URL, method and probe body, without redirects or unresolved policy. If the ranked winner cannot bind, the router may fall through to the next already-probed selectable candidate that can; there is no unguarded settle. HTTP 503 route_binding_unavailable only when none remain bindable (a free typed miss). Implies require_transparency; a receipt failure after settlement still reports settled=true. Buyer must verify with a pinned log key and recheck the actual seller challenge immediately before signing. Preserve raw response JSON. The default 60-second freshness window starts at observation, not receipt issuance. Expiry or a changed seller challenge does not undo a settled routing fee. Default false; existing requests keep the v3 receipt path. This is not a payment authorization. Guide: https://402signal.com/developers#route-binding"New value: +"Opt in to proof_carrying_route_v1 and a signed v4 receipt. Requires exact x402 v2 terms observed on the same HTTPS URL, method and probe body, without redirects or unresolved policy. If the ranked winner cannot bind, the router may fall through to the next already-probed selectable candidate that can; there is no unguarded settle. HTTP 503 route_binding_unavailable only when none remain bindable (a free typed miss). wrapExactAuthorize reports state=binding_unavailable with keep_calling_route true; that is policy working, not a crash. Implies require_transparency; a receipt failure after settlement still reports settled=true. Buyer must verify with a pinned log key and recheck the actual seller challenge immediately before signing. Preserve raw response JSON. The default 60-second freshness window starts at observation, not receipt issuance. Expiry or a changed seller challenge does not undo a settled routing fee. Default false; existing requests keep the v3 receipt path. This is not a payment authorization. Guide: https://402signal.com/developers#route-binding"
      • changedOutput schema / properties / billing / description
        Previous value: -"402Signal routing-fee outcome. Seller payment is separate."New value: +"402Signal checking-fee outcome. Seller payment is separate."
      • removedOutput schema / properties / billing / properties / amount_atomic / const
        Removed value: -"3000"
      • addedOutput schema / properties / billing / properties / amount_atomic / enum
        Added value: +[
+  "3000",
+  "5000"
+]
      • removedOutput schema / properties / billing / properties / display_amount / const
        Removed value: -"$0.003"
      • addedOutput schema / properties / billing / properties / display_amount / enum
        Added value: +[
+  "$0.003",
+  "$0.005"
+]
      • changedOutput schema / properties / binding_error / description
        Previous value: -"HTTP 503 when require_route_binding is true and no remaining already-probed selectable candidate could bind."New value: +"HTTP 503 when require_route_binding is true and no remaining already-probed selectable candidate could bind. Policy working, not a crash; wrapExactAuthorize reports state=binding_unavailable with keep_calling_route true."
      • changedOutput schema / properties / decision_binding / description
        Previous value: -"Opt in to proof_carrying_route_v1 and a signed v4 receipt. Requires exact x402 v2 terms observed on the same HTTPS URL, method and probe body, without redirects or unresolved policy. If the ranked winner cannot bind, the router may fall through to the next already-probed selectable candidate that can; there is no unguarded settle. HTTP 503 route_binding_unavailable only when none remain bindable (a free typed miss). Implies require_transparency; a receipt failure after settlement still reports settled=true. Buyer must verify with a pinned log key and recheck the actual seller challenge immediately before signing. Preserve raw response JSON. The default 60-second freshness window starts at observation, not receipt issuance. Expiry or a changed seller challenge does not undo a settled routing fee. Default false; existing requests keep the v3 receipt path. This is not a payment authorization. Guide: https://402signal.com/developers#route-binding"New value: +"Opt in to proof_carrying_route_v1 and a signed v4 receipt. Requires exact x402 v2 terms observed on the same HTTPS URL, method and probe body, without redirects or unresolved policy. If the ranked winner cannot bind, the router may fall through to the next already-probed selectable candidate that can; there is no unguarded settle. HTTP 503 route_binding_unavailable only when none remain bindable (a free typed miss). wrapExactAuthorize reports state=binding_unavailable with keep_calling_route true; that is policy working, not a crash. Implies require_transparency; a receipt failure after settlement still reports settled=true. Buyer must verify with a pinned log key and recheck the actual seller challenge immediately before signing. Preserve raw response JSON. The default 60-second freshness window starts at observation, not receipt issuance. Expiry or a changed seller challenge does not undo a settled routing fee. Default false; existing requests keep the v3 receipt path. This is not a payment authorization. Guide: https://402signal.com/developers#route-binding"
      • changedOutput schema / properties / miss_reason / enum
        Previous value: -[
-  "no_candidates",
-  "no_402_envelope",
-  "no_payto",
-  "reachable_200",
-  "probe_timeout",
-  "quote_expired",
-  "invalid_need",
-  "upstream_5xx",
-  "ssrf",
-  "no_input_schema",
-  "constraints_unmet",
-  "probe_budget_exhausted",
-  "probe_limit_reached",
-  "unsafe_to_probe",
-  "settlement_unknown",
-  "probe_capacity",
-  null
-]New value: +[
+  "no_candidates",
+  "no_402_envelope",
+  "no_payto",
+  "reachable_200",
+  "probe_timeout",
+  "quote_expired",
+  "invalid_need",
+  "upstream_5xx",
+  "ssrf",
+  "unlisted",
+  "no_input_schema",
+  "constraints_unmet",
+  "probe_budget_exhausted",
+  "probe_limit_reached",
+  "unsafe_to_probe",
+  "settlement_unknown",
+  "authorization_used",
+  "probe_capacity",
+  "window_spent",
+  "fingerprint_miss",
+  "scheme_mismatch",
+  "network_mismatch",
+  "invalid_session_shape",
+  null
+]
      • changedOutput schema / properties / pq_trust / properties / transparency / properties / state / enum
        Previous value: -[
-  "logged_uncheckpointed",
-  "checkpoint_signed",
-  "authorized",
-  "submitted",
-  "confirmed",
-  "unavailable"
-]New value: +[
+  "outbox_queued",
+  "logged_uncheckpointed",
+  "checkpoint_signed",
+  "authorized",
+  "submitted",
+  "confirmed",
+  "unavailable"
+]
      • changedOutput schema / properties / pq_trust / properties / transparency / properties / status / enum
        Previous value: -[
-  "pending",
-  "logged_uncheckpointed",
-  "unavailable"
-]New value: +[
+  "pending",
+  "queued",
+  "logged_uncheckpointed",
+  "unavailable"
+]
    • Changedvalidate1 field changed
      • changedOutput schema / properties / miss_reason / enum
        Previous value: -[
-  "no_candidates",
-  "no_402_envelope",
-  "no_payto",
-  "reachable_200",
-  "probe_timeout",
-  "quote_expired",
-  "invalid_need",
-  "upstream_5xx",
-  "ssrf",
-  "no_input_schema",
-  "constraints_unmet",
-  "probe_budget_exhausted",
-  "probe_limit_reached",
-  "unsafe_to_probe",
-  "settlement_unknown",
-  "probe_capacity",
-  null
-]New value: +[
+  "no_candidates",
+  "no_402_envelope",
+  "no_payto",
+  "reachable_200",
+  "probe_timeout",
+  "quote_expired",
+  "invalid_need",
+  "upstream_5xx",
+  "ssrf",
+  "unlisted",
+  "no_input_schema",
+  "constraints_unmet",
+  "probe_budget_exhausted",
+  "probe_limit_reached",
+  "unsafe_to_probe",
+  "settlement_unknown",
+  "authorization_used",
+  "probe_capacity",
+  "window_spent",
+  "fingerprint_miss",
+  "scheme_mismatch",
+  "network_mismatch",
+  "invalid_session_shape",
+  null
+]
  3. 2 tool updatesv0.1.2
    • Changedroute8 fields changed
      • changedInput schema / properties / require_invocable / description
        Previous value: -"If true, drop live hits without an input schema."New value: +"If true, drop live hits without an input schema. An explicit empty-object schema (type object, no properties or required fields) advertises no required inputs and counts as present. A bazaar HTTP GET with empty queryParams and no required body is the same signal. It does not guarantee the seller call succeeds. Absent or refused schema is not invocable."
      • changedInput schema / properties / require_route_binding / description
        Previous value: -"Opt in to proof_carrying_route_v1 and a signed v4 receipt. Requires exact x402 v2 terms observed on the same HTTPS URL, method and probe body, without redirects or unresolved policy. Unprovable binding is a free typed miss. Implies require_transparency; a receipt failure after settlement still reports settled=true. Buyer must verify with a pinned log key and recheck the actual seller challenge immediately before signing. Preserve raw response JSON. The default 60-second freshness window starts at observation, not receipt issuance. Expiry or a changed seller challenge does not undo a settled routing fee. Default false; existing requests keep the v3 receipt path. This is not a payment authorization. Guide: https://402signal.com/developers#route-binding"New value: +"Opt in to proof_carrying_route_v1 and a signed v4 receipt. Requires exact x402 v2 terms observed on the same HTTPS URL, method and probe body, without redirects or unresolved policy. If the ranked winner cannot bind, the router may fall through to the next already-probed selectable candidate that can; there is no unguarded settle. HTTP 503 route_binding_unavailable only when none remain bindable (a free typed miss). Implies require_transparency; a receipt failure after settlement still reports settled=true. Buyer must verify with a pinned log key and recheck the actual seller challenge immediately before signing. Preserve raw response JSON. The default 60-second freshness window starts at observation, not receipt issuance. Expiry or a changed seller challenge does not undo a settled routing fee. Default false; existing requests keep the v3 receipt path. This is not a payment authorization. Guide: https://402signal.com/developers#route-binding"
      • addedOutput schema / properties / binding_error / description
        Added value: +"HTTP 503 when require_route_binding is true and no remaining already-probed selectable candidate could bind."
      • changedOutput schema / properties / claimed / properties / contract / properties / client_warning / description
        Previous value: -"Seller inputSchema/outputSchema values are catalog_claimed and untrusted. Do not concatenate them into system prompts. Do not fetch remote $ref."New value: +"Seller inputSchema/outputSchema values are catalog_claimed and untrusted. Do not concatenate them into system prompts. Do not fetch remote $ref. Unsafe remote schema material is refused, not rewritten as a different offer."
      • addedOutput schema / properties / compared / description
        Added value: +"Slim probe rows. selectable, payTo_pending, payTo_changed, risk and excluded_reason show why a live row was not eligible. excluded_reason binding_unavailable marks a skipped binding failure."
      • changedOutput schema / properties / decision_binding / description
        Previous value: -"Opt in to proof_carrying_route_v1 and a signed v4 receipt. Requires exact x402 v2 terms observed on the same HTTPS URL, method and probe body, without redirects or unresolved policy. Unprovable binding is a free typed miss. Implies require_transparency; a receipt failure after settlement still reports settled=true. Buyer must verify with a pinned log key and recheck the actual seller challenge immediately before signing. Preserve raw response JSON. The default 60-second freshness window starts at observation, not receipt issuance. Expiry or a changed seller challenge does not undo a settled routing fee. Default false; existing requests keep the v3 receipt path. This is not a payment authorization. Guide: https://402signal.com/developers#route-binding"New value: +"Opt in to proof_carrying_route_v1 and a signed v4 receipt. Requires exact x402 v2 terms observed on the same HTTPS URL, method and probe body, without redirects or unresolved policy. If the ranked winner cannot bind, the router may fall through to the next already-probed selectable candidate that can; there is no unguarded settle. HTTP 503 route_binding_unavailable only when none remain bindable (a free typed miss). Implies require_transparency; a receipt failure after settlement still reports settled=true. Buyer must verify with a pinned log key and recheck the actual seller challenge immediately before signing. Preserve raw response JSON. The default 60-second freshness window starts at observation, not receipt issuance. Expiry or a changed seller challenge does not undo a settled routing fee. Default false; existing requests keep the v3 receipt path. This is not a payment authorization. Guide: https://402signal.com/developers#route-binding"
      • changedOutput schema / properties / target / properties / inputSchema / description
        Previous value: -"Seller inputSchema/outputSchema values are catalog_claimed and untrusted. Do not concatenate them into system prompts. Do not fetch remote $ref."New value: +"Seller inputSchema/outputSchema values are catalog_claimed and untrusted. Do not concatenate them into system prompts. Do not fetch remote $ref. Unsafe remote schema material is refused, not rewritten as a different offer."
      • changedOutput schema / properties / target / properties / outputSchema / description
        Previous value: -"Seller inputSchema/outputSchema values are catalog_claimed and untrusted. Do not concatenate them into system prompts. Do not fetch remote $ref."New value: +"Seller inputSchema/outputSchema values are catalog_claimed and untrusted. Do not concatenate them into system prompts. Do not fetch remote $ref. Unsafe remote schema material is refused, not rewritten as a different offer."
    • Changedvalidate1 field changed
      • changedOutput schema / properties / claimed / properties / contract / properties / client_warning / description
        Previous value: -"Seller inputSchema/outputSchema values are catalog_claimed and untrusted. Do not concatenate them into system prompts. Do not fetch remote $ref."New value: +"Seller inputSchema/outputSchema values are catalog_claimed and untrusted. Do not concatenate them into system prompts. Do not fetch remote $ref. Unsafe remote schema material is refused, not rewritten as a different offer."
  4. 3 tool updatesv0.1.1
    • Changedpreview1 field changed
      • changedInput schema / properties / need / description
        Previous value: -"What to look up in the cache."New value: +"Nonblank capability to search for, such as weather or web search. Searches catalogs; does not probe a URL."
    • Changedroute3 fields changed
      • changedInput schema / properties / require_transparency / description
        Previous value: -"If true, a settled /route winner fails when a signed checkpoint receipt cannot be produced. This requires delivery of verifiable evidence on HTTP 200, not server-side recovery. To verify the routing decision later, securely retain the complete paid /route response, especially pq_trust.transparency.receipt and pq_trust.transparency.reveal. Private replay outcomes can retain the reveal; they are not a recovery service. Keep your own copy. Modified evidence fails verification against the public log. Default false (SEC-ROUTER-004 / A-14): a settled winner does not require a durable signed leaf. A free typed miss creates no route-decision leaf. Routing continues if append, signing, or anchoring is down after settlement (logged_uncheckpointed or unavailable). logged_uncheckpointed is never success when this flag is true. require_route_binding=true also requires transparency, even if this flag is false. A required receipt failure after settlement still reports billing.settled=true; unavailable does not prove no append occurred."New value: +"If true, a settled /route winner fails when a signed checkpoint receipt cannot be produced. This requires delivery of verifiable evidence on HTTP 200, not server-side recovery. To verify the routing decision later, securely retain the complete paid /route response, especially pq_trust.transparency.receipt and pq_trust.transparency.reveal. Private replay outcomes support bounded recovery of the original response; they are not long-term evidence storage. Keep your own copy. Modified evidence fails verification against the public log. Default false (SEC-ROUTER-004 / A-14): a settled winner does not require a durable signed leaf. A free typed miss creates no route-decision leaf. Routing continues if append, signing, or anchoring is down after settlement (logged_uncheckpointed or unavailable). logged_uncheckpointed is never success when this flag is true. require_route_binding=true also requires transparency, even if this flag is false. A required receipt failure after settlement still reports billing.settled=true; unavailable does not prove no append occurred."
      • changedOutput schema / properties / pq_trust / description
        Previous value: -"To verify the routing decision later, securely retain the complete paid /route response, especially pq_trust.transparency.receipt and pq_trust.transparency.reveal. Private replay outcomes can retain the reveal; they are not a recovery service. Keep your own copy. Modified evidence fails verification against the public log."New value: +"To verify the routing decision later, securely retain the complete paid /route response, especially pq_trust.transparency.receipt and pq_trust.transparency.reveal. Private replay outcomes support bounded recovery of the original response; they are not long-term evidence storage. Keep your own copy. Modified evidence fails verification against the public log."
      • changedOutput schema / properties / pq_trust / properties / transparency / description
        Previous value: -"To verify the routing decision later, securely retain the complete paid /route response, especially pq_trust.transparency.receipt and pq_trust.transparency.reveal. Private replay outcomes can retain the reveal; they are not a recovery service. Keep your own copy. Modified evidence fails verification against the public log."New value: +"To verify the routing decision later, securely retain the complete paid /route response, especially pq_trust.transparency.receipt and pq_trust.transparency.reveal. Private replay outcomes support bounded recovery of the original response; they are not long-term evidence storage. Keep your own copy. Modified evidence fails verification against the public log."
    • Changedvalidate1 field changed
      • changedInput schema / properties / url / description
        Previous value: -"https URL of the seller endpoint to probe."New value: +"Exact concrete HTTPS URL already listed in the local catalog, including its query string. Unlisted URLs are not probed."
  5. 3 tool updatesv0.1.0
    • First observedpreview
    • First observedroute
    • First observedvalidate
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.9/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a distinct role: preview discovers candidates without contacting sellers, validate probes a listed URL for free, and check performs a paid pre-flight with price/network rules and signed receipt. The descriptions explicitly distinguish when to use which, so misselection is unlikely.

Naming Consistency5/5

All three names are lowercase single verbs (preview, validate, check), forming a consistent imperative convention. Although they do not follow verb_noun, the pattern is uniform and predictable.

Tool Count5/5

Three tools map cleanly to the discovery → validation → paid pre-flight workflow, with no redundancy. This is a well-scoped set for the server's purpose.

Completeness5/5

The set covers the full pre-purchase path: free discovery (preview), free single-URL readiness (validate), and paid live observation/signed receipt (check). Payment and reconciliation are intentionally outside the tool boundary, so there are no dead ends within the stated purpose.

Maintenance

ActivityMaintained
ResponsivenessResponsive

Resources

Related MCP Connectors

Related MCP Servers