Skip to main content
Glama
Sign In

Sanctions screening

by io.github.Bosco-Labs
OverviewDiscussionsAdmin

Counterparty Check API: KYB checklist from official registers

counterparty_check
Read-onlyIdempotent

Can I do business with this company? One call checks a supplier, customer or partner against official sources and returns a checklist: pass, fail, review or unverified per check, each with its source link and time. Built for AI agents doing KYB, vendor onboarding or "may I pay this party?" checks, and for people who want a fast, sourced first screen. To screen a vendor list, pass up to 10 companies in companies: one checklist per company, same price each.

Price: $0.05 per counterparty-check.

Input Schema

NameRequiredDescriptionDefault
ibanNoThe bank account the counterparty wants to be paid on, e.g. "DK5000400440116243"
queryNoThe counterparty to check: a name (e.g. "Novo Nordisk") or an identifier: LEI
countryNoISO 3166 alpha-2 country code to disambiguate, e.g. "DK", "GB", "NO", "FR", "FI", "EE", "IE", "CZ", "LV", "NL", "US"
companiesNoCheck a list of companies in one run instead of `query`: up to 10 companies, each a name or number ("Tesco PLC") or an object with the fields above
vatNumberNoThe VAT number the counterparty gave you, with its country prefix, e.g. "DK24256790"
walletAddressesNoWallet addresses the counterparty wants to be paid on, e.g. ["0x7FF9cFad3877F21d41Da833E2F775dB0569eE3D9"]

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / country / description
      Previous value: -"ISO 3166 alpha-2 country code to disambiguate, e.g. \"DK\", \"GB\", \"NO\", \"FR\", \"FI\", \"EE\", \"NL\", \"US\""New value: +"ISO 3166 alpha-2 country code to disambiguate, e.g. \"DK\", \"GB\", \"NO\", \"FR\", \"FI\", \"EE\", \"IE\", \"CZ\", \"LV\", \"NL\", \"US\""
  2. Changed5 schema fields changed
    • changedInput schema / properties / companies / description
      Previous value: -"Check a list of companies in one run instead of `query`: up to 10 objects with the fields above"New value: +"Check a list of companies in one run instead of `query`: up to 10 companies, each a name or number (\"Tesco PLC\") or an object with the fields above"
    • addedInput schema / properties / companies / items / anyOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "properties": {
+      "country": {
+        "description": "ISO 3166 alpha-2 code, e.g. \"DK\"",
+        "type": "string"
+      },
+      "iban": {
+        "description": "As in `iban`, e.g. \"DK5000400440116243\"",
+        "type": "string"
+      },
+      "query": {
+        "description": "Name, LEI or registration number, as in `query`, e.g. \"24256790\"",
+        "type": "string"
+      },
+      "vatNumber": {
+        "description": "As in `vatNumber`, e.g. \"DK24256790\"",
+        "type": "string"
+      }
+    },
+    "required": [
+      "query"
+    ],
+    "type": "object"
+  }
+]
    • removedInput schema / properties / companies / items / properties
      Removed value: -{
-  "country": {
-    "description": "ISO 3166 alpha-2 code, as in `country`, e.g. \"DK\"",
-    "type": "string"
-  },
-  "iban": {
-    "description": "As in `iban`, e.g. \"DK5000400440116243\"",
-    "type": "string"
-  },
-  "query": {
-    "description": "Name, LEI or registration number, as in `query`, e.g. \"24256790\"",
-    "type": "string"
-  },
-  "vatNumber": {
-    "description": "As in `vatNumber`, e.g. \"DK24256790\"",
-    "type": "string"
-  }
-}
    • removedInput schema / properties / companies / items / required
      Removed value: -[
-  "query"
-]
    • removedInput schema / properties / companies / items / type
      Removed value: -"object"
  3. Changed2 schema fields changed
    • addedInput schema / properties / companies
      Added value: +{
+  "description": "Check a list of companies in one run instead of `query`: up to 10 objects with the fields above",
+  "items": {
+    "properties": {
+      "country": {
+        "description": "ISO 3166 alpha-2 code, as in `country`, e.g. \"DK\"",
+        "type": "string"
+      },
+      "iban": {
+        "description": "As in `iban`, e.g. \"DK5000400440116243\"",
+        "type": "string"
+      },
+      "query": {
+        "description": "Name, LEI or registration number, as in `query`, e.g. \"24256790\"",
+        "type": "string"
+      },
+      "vatNumber": {
+        "description": "As in `vatNumber`, e.g. \"DK24256790\"",
+        "type": "string"
+      }
+    },
+    "required": [
+      "query"
+    ],
+    "type": "object"
+  },
+  "maxItems": 10,
+  "type": "array"
+}
    • changedInput schema / required
      Previous value: -[
-  "query"
-]New value: +[]
  4. First observed

TDQS

A4/5.0
Behavior4/5

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

The annotations already cover read-only, idempotent, open-world and non-destructive behavior, so the bar is lower. The description adds material context they do not: the result shape (per-check verdicts with source link and time) and pricing at $0.05 per counterparty-check with the same price per company in a batch. It omits latency, auth requirements, and what happens on partial matches, so it is strong but not exhaustive.

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 front-loaded with the core question and the return format, then the audience, then the batch mode and price. There is mild promotional framing ('Can I do business with this company?', 'fast, sourced first screen') that does not carry operational information, but nothing is confusing or padded.

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

Completeness4/5

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

For a six-parameter tool with no output schema, the description usefully explains what comes back and the pricing model. The one gap is that all schema parameters are optional, yet the description never says that at least one of `query` or `companies` must be supplied for the call to be meaningful. Otherwise it covers what an agent needs to call it correctly.

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 and the schema does most of the work. The description still adds real meaning: `companies` is positioned as the batch alternative to `query` with a 10-company limit and per-company pricing, which helps an agent choose between the two input styles. It adds nothing about iban, vatNumber, country or walletAddresses beyond the schema text.

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 gives a specific verb and resource: it checks a supplier, customer or partner against official sources and returns a per-check KYB checklist with pass/fail/review/unverified verdicts. That is far more concrete than the title alone. It does not explicitly differentiate itself from the sibling sanctions_screening, so a 4 rather than a 5.

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?

It names the use cases clearly: KYB, vendor onboarding, 'may I pay this party?' checks, and fast sourced first screens. It also explains the batch mode (pass up to 10 companies in `companies` to screen a vendor list). It never states when not to use it or which sibling to prefer for sanctions-only lookups, which keeps it below 5.

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

All Sanctions screening 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