Stablecoin Gateways

Merchant Check (KYB facts)

merchant_check

Read-onlyIdempotent

Merchant check (KYB facts) before an agent pays: give a merchant's domain and optionally its company name, get neutral sourced facts in one call for merchant verification and vendor due diligence: domain registration date and age, expiry and registrar (registry RDAP), DNS and SPF/DMARC email-auth, an OFAC sanctions screen of the name, GLEIF LEI match and SEC EDGAR match. No risk score or fraud verdict. Signed receipt. Price: $0.01 per call via x402 (USDC on Base or XRP on XRPL). The response includes a provenance block (sg-provenance/1): each fact carries its source, source URL, retrieval time and limits; evidence only, no score, rating or verdict. Example arguments: {"domain":"apple.com","name":"Apple Inc."}.

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": {
      "domain": "<domain>"
    },
    "name": "merchant_check"
  }
}

Input Schema

Name	Required	Description
`lei`	No	Optional 20-character LEI (instead of a GLEIF name search)
`name`	No	Company legal or trading name; screens OFAC (entities only), GLEIF LEI and SEC
`domain`	Yes	Merchant domain or hostname (required)
`ticker`	No	Optional US stock ticker for the SEC match
`country`	No	Optional ISO 3166 alpha-2 country filter for LEI matches

Output Schema

Name	Required	Description	Default
`data`	No	Sourced facts[] plus domain, sanctions (OFAC), lei and sec sections for a merchant; no score or verdict
`receipt`	No	Ed25519-signed, hash-chained receipt; verify free with the verify_receipt tool or POST /v1/verify-receipt. New receipts carry a signed `evidence` object: service_version, data_timestamp, validation, terms_version, terms_hash, provenance_hash.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 24, 2026

addedOutput schema / properties / data / properties / provenance

Added value: +{
+  "description": "The response includes a `provenance` block (sg-provenance/1): each fact carries its source, source URL, retrieval time and limits; evidence only, no score, rating or verdict."
+}

Changed1 schema field changedOct 24, 2026

changedOutput schema / properties / receipt / description

Previous value: -"Ed25519-signed, hash-chained receipt; verify free with the verify_receipt tool or POST /v1/verify-receipt"New value: +"Ed25519-signed, hash-chained receipt; verify free with the verify_receipt tool or POST /v1/verify-receipt. New receipts carry a signed `evidence` object: service_version, data_timestamp, validation, terms_version, terms_hash, provenance_hash."

Changed2 schema fields changedOct 22, 2026

addedInput schema / properties / domain / examples
```
Added value: +[
+  "apple.com"
+]
```

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "description": "Paid result: { data, receipt }. Unpaid calls return an x402 PaymentRequired object instead (isError: true).",
+  "properties": {
+    "data": {
+      "description": "Sourced facts[] plus domain, sanctions (OFAC), lei and sec sections for a merchant; no score or verdict",
+      "properties": {
+        "checked_at": {},
+        "domain": {},
+        "facts": {},
+        "lei": {},
+        "name_domain_link": {},
+        "notice": {},
+        "query": {},
+        "sanctions": {},
+        "sec": {},
+        "sources": {}
+      }
+    },
+    "receipt": {
+      "description": "Ed25519-signed, hash-chained receipt; verify free with the verify_receipt tool or POST /v1/verify-receipt"
+    }
+  },
+  "type": "object"
+}

First observedOct 22, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Goes well beyond the readOnly/idempotent annotations by disclosing that the call is paid ($0.01 per call via x402, USDC on Base or XRP on XRPL) — a critical operational fact for an agent. It also describes the signed receipt and the `provenance` block with per-fact source, URL, retrieval time and limits, and reiterates the absence of scoring.

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 and the enumeration of sources is efficient, but the no-verdict claim is repeated three ways ('No risk score or fraud verdict', 'neutral', 'evidence only, no score, rating or verdict'), which is redundant text an agent must parse.

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 paid, open-world aggregation call with an output schema, the description covers everything an agent needs before invoking: trigger context, inputs, sources, cost and payment rails, what is not returned, and the shape of the provenance/signed receipt.

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

Parameters3/5

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

Schema coverage is 100%, so the baseline applies. The description only restates domain as required and name as optional, and its example argument demonstrates a valid domain+name combination; the lei, ticker and country parameters are left entirely to the schema.

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

Purpose4/5

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

States a specific verb and resource ('Merchant check (KYB facts) ... give a merchant's domain ... get neutral sourced facts') and enumerates the exact fact families returned (RDAP registration, DNS/SPF/DMARC, OFAC screen, GLEIF LEI, SEC EDGAR). The sibling relationship is only implicit: it never says it aggregates or replaces domain_facts, whois, sanctions_screen, lei_lookup or sec_company_facts, even though those are exact subcomponents of this call.

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

Usage Guidelines4/5

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

'before an agent pays' gives a clear triggering situation, and 'No risk score or fraud verdict' plus 'evidence only' set a clear when-not expectation. It stops short of naming alternatives, so an agent cannot tell from the text whether to call this or the narrower siblings for a single lookup.

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

All Stablecoin Gateways tools Inspect

Try in Browser

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

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?