Skip to main content
Glama
Sign In

Stablecoin Gateways

by com.stablecoingateways
OverviewDiscussionsAdmin

Counterparty Check (KYB facts)

counterparty_check
Read-onlyIdempotent

Counterparty check (KYB preflight) in one call: give any of a company name, domain, LEI or crypto wallet address (plus an optional EU VAT number), get neutral sourced facts for vendor onboarding and supplier due diligence: sanctions screen of the name on OFAC, EU and UK lists with UN designations flagged, US federal exclusions (SAM.gov debarments and suspensions of firms, by name or UEI), OFAC wallet check, GLEIF LEI match and status, domain age, registrar and email-auth, and an EU VAT number format check. A name screen needs fresh OFAC, EU and UK lists (48 hours each) and returns 503 before payment if any of those is stale. Domain-only, address-only and UEI-only checks do not require the EU or UK lists. No risk score or 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: {"name":"Siemens Aktiengesellschaft","domain":"siemens.com","vat":"DE129274202"}.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "counterparty_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
leiNo20-character LEI (instead of a GLEIF name search)
ueiNo12-character SAM.gov Unique Entity ID: exact match in the SAM.gov exclusions extract (name= is also matched there)
vatNoEU VAT number with 2-letter country prefix (EL for Greece, XI for Northern Ireland); format check only, not a VIES registration check
nameNoCompany legal or trading name: screened on OFAC, EU and UK sanctions lists and SAM.gov exclusions (entities only) and matched in GLEIF
domainNoCompany domain: registration age, registrar, DNS and email-auth facts
addressNoCrypto wallet address to check against OFAC-listed addresses
countryNoISO 3166 alpha-2 country filter for LEI matches

Output Schema

NameRequiredDescriptionDefault
dataNoSourced facts[] plus sanctions, us_exclusions (SAM.gov), wallet, lei, domain and vat sections; each section says whether it was checked and why not
receiptNoEd25519-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.

  1. Changed2 schema fields changed
    • 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."
+}
    • 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."
  2. Changed3 schema fields changed
    • changedInput schema / properties / name / description
      Previous value: -"Company legal or trading name: screened on OFAC, EU and UK sanctions lists (entities only) and matched in GLEIF"New value: +"Company legal or trading name: screened on OFAC, EU and UK sanctions lists and SAM.gov exclusions (entities only) and matched in GLEIF"
    • addedInput schema / properties / uei
      Added value: +{
+  "description": "12-character SAM.gov Unique Entity ID: exact match in the SAM.gov exclusions extract (name= is also matched there)",
+  "pattern": "^[A-Za-z0-9]{12}$",
+  "type": "string"
+}
    • changedOutput schema / properties / data / description
      Previous value: -"Sourced facts[] plus sanctions, wallet, lei, domain and vat sections; each section says whether it was checked and why not"New value: +"Sourced facts[] plus sanctions, us_exclusions (SAM.gov), wallet, lei, domain and vat sections; each section says whether it was checked and why not"
  3. Added

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, and the description adds substantial behavior beyond that: a $0.01 x402 charge (USDC on Base or XRPL), a specific pre-payment failure mode (503 on stale lists), per-source freshness windows, a signed receipt, and a provenance block with source URL, retrieval time and limits. It also explicitly bounds the output — 'No risk score or verdict' — which prevents an agent from over-claiming what the result means.

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?

It is a dense single paragraph but front-loads the core promise (one call, these inputs, these facts) before the constraints, pricing and example arguments. The main cost is redundancy: 'No risk score or verdict' and 'evidence only, no score, rating or verdict' make the same point twice, and the provenance sentence repeats the evidence-only framing a third time.

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 seven-parameter, multi-source, paid composite tool this is thorough: it covers pricing, the payment rail, the pre-payment failure condition, per-list freshness requirements, which input combinations relax those requirements, and the no-verdict posture. An output schema exists, so the description is not obliged to explain return shape, and the brief provenance-block note is an appropriate pointer rather than wasted space.

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, but the description earns more because it resolves a real ambiguity: required parameters are zero and additionalProperties is false, and the description clarifies that at least one of name/domain/LEI/wallet must be supplied, plus an optional VAT. It also explains that a name is screened on several lists and matched in GLEIF, and that a UEI hits the SAM.gov exclusions extract — semantics the schema only partially carries.

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?

The description opens with a specific verb+resource ('Counterparty check (KYB preflight) in one call') and enumerates exactly what facts come back: sanctions screens, SAM.gov exclusions, OFAC wallet check, GLEIF LEI status, domain age/registrar/email-auth, and EU VAT format. This is far more than a restatement of the name. It stops short of a 5 because it never names the overlapping siblings (sanctions_screen, lei_lookup, domain_facts, sanctions_address) that a caller might pick instead for single-fact needs.

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?

Use context is stated explicitly ('vendor onboarding and supplier due diligence'), as are the operational conditions: a name screen requires fresh OFAC/EU/UK lists (48 hours) and returns 503 before payment if any is stale, while domain-only, address-only and UEI-only checks skip the EU/UK list requirement. What is missing is explicit routing against alternatives — it says 'in one call' but never says 'if you only need a domain, use domain_facts instead'.

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

All Stablecoin Gateways toolsInspect
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