Skip to main content
Glama

ARM Verify — Entity Intelligence API

by app.railway.up.brilliant-illumination-production-9bda
OverviewDiscussionsAdmin

screen_sanctions

Screen a company or person against consolidated government sanctions lists and a politically-exposed-person dataset. RETURNS JSON with: screening_result (one of "MATCH", "POSSIBLE_MATCH", "CLEAR"), risk_level ("CRITICAL" for a confirmed match, "HIGH" for a possible match, "LOW" when clear), recommendation ("DO_NOT_PROCEED", "ENHANCED_DUE_DILIGENCE" or "PROCEED"), matches (array, each with list, matched_name, confidence as a percentage string such as "100%", type and id), pep_screening (separate PEP verdict with its own matches), sanctions_lists_checked, total_entries_screened, data_freshness (ISO timestamp of the last refresh), screening_date, and evidence (reference_id, screened_at, matching method and thresholds, one row per list with its result and last refresh, the 5 closest names even below the threshold, and a one-sentence conclusion). SOURCES: OFAC SDN (US Treasury), UN Security Council Consolidated List, EU Financial Sanctions List, and the UK FCDO UK Sanctions List (UKSL) — approximately 32,600 designations in total, plus roughly 1,000,000 PEP names from OpenSanctions. All lists are re-downloaded from the official government endpoints daily at 03:00 UTC. USE WHEN you must clear a counterparty before payment, onboarding, or any transaction with sanctions exposure. BILLING: with an API key each call is charged $4.00 from the key's credits, exactly as POST /verify (refused when the balance is too low); bank portal sessions are not charged.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
countryNoOptional ISO 3166-1 alpha-2 country code of incorporation, residence or principal operation, uppercase. Examples: "RU", "IR", "GB", "AE". Recorded on the screening report for audit purposes; screening itself runs against every list regardless of country, and it does not change the risk score. Omit if unknown — the report then shows country as null.
thresholdNoMatch confidence threshold 0.5-1.0. Default 0.75. Lower values catch more potential matches; higher values reduce false positives. MATCH requires >=0.90 regardless of threshold.
entity_nameYesFull name of the company or individual to screen. Examples: "Rosneft", "Gazprom PJSC", "Vladimir Putin". Matching is token-based and case-insensitive, and also searches recorded aliases and a.k.a. names.
entity_typeNoWhether the subject is a legal entity or a natural person. Accepts exactly "company" or "individual". Defaults to "company" when omitted.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / country / description
      Previous value: -"ISO 3166-1 alpha-2 country code of incorporation, residence or principal operation, uppercase. Examples: \"RU\", \"IR\", \"GB\", \"AE\". Recorded on the screening report for audit purposes; screening itself runs against every list regardless of country."New value: +"Optional ISO 3166-1 alpha-2 country code of incorporation, residence or principal operation, uppercase. Examples: \"RU\", \"IR\", \"GB\", \"AE\". Recorded on the screening report for audit purposes; screening itself runs against every list regardless of country, and it does not change the risk score. Omit if unknown — the report then shows country as null."
    • changedInput schema / required
      Previous value: -[
-  "entity_name",
-  "country"
-]New value: +[
+  "entity_name"
+]
  2. Changed1 schema field changed
    • addedInput schema / properties / threshold
      Added value: +{
+  "description": "Match confidence threshold 0.5-1.0. Default 0.75. Lower values catch more potential matches; higher values reduce false positives. MATCH requires >=0.90 regardless of threshold.",
+  "maximum": 1,
+  "minimum": 0.5,
+  "type": "number"
+}
  3. Changed3 schema fields changed
    • changedInput schema / properties / country / description
      Previous value: -"Country of incorporation or operation"New value: +"ISO 3166-1 alpha-2 country code of incorporation, residence or principal operation, uppercase. Examples: \"RU\", \"IR\", \"GB\", \"AE\". Recorded on the screening report for audit purposes; screening itself runs against every list regardless of country."
    • changedInput schema / properties / entity_name / description
      Previous value: -"Entity name to screen"New value: +"Full name of the company or individual to screen. Examples: \"Rosneft\", \"Gazprom PJSC\", \"Vladimir Putin\". Matching is token-based and case-insensitive, and also searches recorded aliases and a.k.a. names."
    • changedInput schema / properties / entity_type / description
      Previous value: -"Type of entity"New value: +"Whether the subject is a legal entity or a natural person. Accepts exactly \"company\" or \"individual\". Defaults to \"company\" when omitted."
  4. Changed3 schema fields changed
    • addedInput schema / properties / country / description
      Added value: +"Country of incorporation or operation"
    • addedInput schema / properties / entity_name / description
      Added value: +"Entity name to screen"
    • addedInput schema / properties / entity_type / description
      Added value: +"Type of entity"
  5. Changed3 schema fields changed
    • removedInput schema / properties / country / description
      Removed value: -"Country of incorporation or operation"
    • removedInput schema / properties / entity_name / description
      Removed value: -"Entity name to screen"
    • removedInput schema / properties / entity_type / description
      Removed value: -"Type of entity"
  6. First observed

TDQS

Score is being calculated.

All ARM Verify — Entity Intelligence API 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