Skip to main content
Glama

Check an x402 endpoint

settled_check
Read-onlyIdempotent

Free: 25 calls/day per address, 300 with a payer record (free, keyed to your wallet), no daily cap with a pass. Check an x402 endpoint before paying it, from Settled’s index (cached up to 5 min): status, payability, latency, parsed price/network/payTo, payee on-chain history, the scout’s last real purchase, paying agents’ reports, seller claim, quality breakdown and risk flags, with a recommendation (pay, caution, avoid or unknown) and its reasons. Use when: deciding whether to call an endpoint, and for routine re-checks. Not for: a fresh probe right now (settled_preflight) or searching (settled_find_endpoints). If status is unknown, call settled_submit; after paying, call settled_report.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "settled_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesFull URL of the x402 endpoint, e.g. https://api.example.com/search
passNoSettled day pass token: lifts the free daily cap; or send it as the x-settled-pass header
forceNotrue to probe now instead of using the 5-minute cache; needs a pass
payer_tokenNoA Settled payer token (x4t_…, from POST /x401/token with your payer record): the free tier then follows your wallet, 300 a day, through any gateway

Output Schema

NameRequiredDescriptionDefault
urlNoThe endpoint
assetNoAsset of the cheapest option
errorNoPresent only when the call failed or needs another step: an error code such as pass_required, next to the fields that explain it
flagsNoRisk flags
payeeNoWhether the payTo has on-chain history
cachedNoWhether this came from Settled's 5-minute cache
pay_toNoThe payTo Settled's probe sees; compare it with the quote you are about to pay
schemeNoPayment scheme, e.g. exact
statusNoEndpoint status, e.g. live, degraded, dead, free, auth_gated, not_found or quote_invalid
networkNoNetwork of the cheapest option (CAIP-2)
onchainNoSettlements and unique payers over the last 30 days
qualityNoQuality score breakdown
reasonsNoWhy, one line each; the first positive one is the scout's receipt when there is one
reportsNoPaying agents' reports
evidenceNoThe grade of the evidence and the receipt line first: grade purchased (Settled paid this endpoint and compared what came back with the listing; receipt has the amount, day, bytes, listing verdict and Base transaction) or observed (live probes, payTo history and agent reports only; the scout buys and the ledger reads on Base, so an endpoint on another network is observed only)
verifierNoThe verdict in the x402 Foundation Domain Discovery working group’s draft verifier schema: verdict (true|false|inconclusive), a reason code from its closed set, evidence (none|terms|probe|purchase; purchase_by verifier when Settled bought), the quote’s digest, and an attestation with the key URL, a signed record URL, the two domains compared, valid_until and the relationship disclosure; method_digest pins the method document (/verifier-method.md)
price_usdNoPrice per call in USD (cheapest option)
checked_atNoWhen this answer was built
first_seenNoWhen Settled first saw it
last_ok_atNoWhen it last answered with a valid quote
latency_msNoLatency of the latest probe
payabilityNoPayability verdict and the verb that pays
attestationNoEIP-191 signature over the answer; verify it with settled_verify or any EVM library
attested_atNoWhen Settled signed this answer (ISO 8601)
descriptionNoThe listing's description
network_nameNoReadable network name
seller_claimNoThe seller's claim and profile, if claimed
service_nameNoThe listing's service name
x402_versionNox402 version of the quote
last_probe_atNoWhen Settled last probed it
seller_alertsNoOnly when the caller's payer record is the claimed wallet: that seller's own Seller Watch alerts (down_now, new_24h, latest, feed)
recommendationNopay, caution, avoid or unknown: avoid means money at risk (sanctioned or clone-farm payee, a purchase that did not deliver, a honeypot, agents' reports); caution includes an endpoint Settled could not get a quote from, which your own 402 outweighs (compare its payTo with pay_to); unknown means no quote on record and nothing against it
delivery_receiptNoThe scout's last purchase, with its settlement transaction and checks (when the scout has bought it)
http_status_lastNoHTTP status of the latest probe
last_delivery_atNoWhen the scout last bought it
delivery_verifiedNoWhether a real payment by Settled's scout came back with content

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedOutput schema / properties / reasons
      Added value: +{
      +  "description": "Why, one line each; the first positive one is the scout's receipt when there is one"
      +}
    • addedOutput schema / properties / recommendation
      Added value: +{
      +  "description": "pay, caution, avoid or unknown: avoid means money at risk (sanctioned or clone-farm payee, a purchase that did not deliver, a honeypot, agents' reports); caution includes an endpoint Settled could not get a quote from, which your own 402 outweighs (compare its payTo with pay_to); unknown means no quote on record and nothing against it"
      +}
  2. Changed1 schema field changed
    • addedOutput schema / properties / verifier
      Added value: +{
      +  "description": "The verdict in the x402 Foundation Domain Discovery working group’s draft verifier schema: verdict (true|false|inconclusive), a reason code from its closed set, evidence (none|terms|probe|purchase; purchase_by verifier when Settled bought), the quote’s digest, and an attestation with the key URL, a signed record URL, the two domains compared, valid_until and the relationship disclosure; method_digest pins the method document (/verifier-method.md)"
      +}
  3. Changed1 schema field changed
    • addedOutput schema / properties / seller_alerts
      Added value: +{
      +  "description": "Only when the caller's payer record is the claimed wallet: that seller's own Seller Watch alerts (down_now, new_24h, latest, feed)"
      +}
  4. Changed1 schema field changed
    • addedOutput schema / properties / evidence
      Added value: +{
      +  "description": "The grade of the evidence and the receipt line first: grade purchased (Settled paid this endpoint and compared what came back with the listing; receipt has the amount, day, bytes, listing verdict and Base transaction) or observed (live probes, payTo history and agent reports only; the scout buys and the ledger reads on Base, so an endpoint on another network is observed only)"
      +}
  5. Changed1 schema field changed
    • addedInput schema / properties / payer_token
      Added value: +{
      +  "description": "A Settled payer token (x4t_…, from POST /x401/token with your payer record): the free tier then follows your wallet, 300 a day, through any gateway",
      +  "type": "string"
      +}
  6. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds quota mechanics (25 calls/day per address, 300 with a payer record, uncapped with a pass), cache staleness (up to 5 min), and the shape of the answer including the recommendation enum values (pay, caution, avoid, unknown). That is meaningful behavior beyond what the annotations 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?

Dense but tight, with the when/not-for routing in a single clause. Minor deduction because it leads with pricing tiers rather than the tool's core function, pushing the actual purpose into the second sentence.

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, yet the description still summarizes the returned signals (status, payability, latency, parsed price/network/payTo, on-chain history, reports, risk flags, recommendation) so an agent knows what it can decide on. Quotas, cache, and fallback paths are all covered; nothing needed 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.

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 description still adds value by tying tokens to consequences: a pass lifts the daily cap, a payer record raises the limit to 300 from any gateway, and force bypasses the cache but requires a pass. The quota context makes the token parameters intelligible rather than just documented.

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 ('Check an x402 endpoint before paying it') and immediately scopes the source: Settled's index, cached up to 5 min. It names the two siblings it is not (settled_preflight for a fresh probe, settled_find_endpoints for search), so an agent can distinguish it 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?

Explicit 'Use when' (deciding whether to call an endpoint, routine re-checks) and 'Not for' clauses that route to named alternatives. It goes further with a follow-up chain: call settled_submit if status is unknown, call settled_report after paying.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources