nordic-data

screen_sanctions

Read-onlyIdempotent

Screen one or more person or company names against UN, EU, OFAC and PEP sanctions lists (768K+ entries via OpenSanctions). Typical use: counterparty checks before onboarding or processing a payment. Returns per-name match lists with fuzzy match scores, source-list attribution and risk topics, plus a 'disclaimer' field. Matches are informational decision-support from public sources, not legal or compliance advice — a match indicates a potential hit that requires verification, not a confirmed listing.

Input Schema

TableJSON Schema

Name	Required	Description
`fuzzy`	No	Enable fuzzy matching. Default true.
`names`	Yes	Array of person or company names to screen. Max 1000 names per call.
`min_score`	No	Minimum fuzzy match score, 0-1. Default 0.7. Lower values return more (lower-confidence) matches.

Output Schema

TableJSON Schema

Name	Required	Description
`total`	No	Number of names screened.
`matched`	No	Number of names with matched=true.
`results`	No	One entry per input name, in submission order.
`disclaimer`	No
`indexUpdated`	No	ISO-8601 last refresh per source list.
`sourcesUnavailable`	No	Lists that could not be checked on this call; non-empty means the screening is incomplete.

Schema Changelog

Changes observed during successful MCP inspections.

Changed16 schema fields changedSep 15, 2026

removedOutput schema / properties / checked_at

Removed value: -{
-  "description": "ISO-8601 timestamp of the screening.",
-  "type": "string"
-}

addedOutput schema / properties / disclaimer

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / indexUpdated

Added value: +{
+  "additionalProperties": true,
+  "description": "ISO-8601 last refresh per source list.",
+  "type": [
+    "object",
+    "null"
+  ]
+}

addedOutput schema / properties / matched

Added value: +{
+  "description": "Number of names with matched=true.",
+  "type": [
+    "integer",
+    "null"
+  ]
+}

addedOutput schema / properties / results / items / properties / classification

Added value: +{
+  "description": "Outcome for this name: none / potential_match / confirmed.",
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / results / items / properties / count

Added value: +{
+  "description": "Number of fuzzy candidates returned, including unflagged low-confidence ones — not a match count.",
+  "type": [
+    "integer",
+    "null"
+  ]
+}

addedOutput schema / properties / results / items / properties / flaggedCount

Added value: +{
+  "description": "Number of hits classified as a match.",
+  "type": [
+    "integer",
+    "null"
+  ]
+}

addedOutput schema / properties / results / items / properties / hits

Added value: +{
+  "description": "Fuzzy candidates, each with its own classification ('none' = not flagged).",
+  "items": {
+    "additionalProperties": true,
+    "properties": {
+      "classification": {
+        "description": "none / potential_match / confirmed.",
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "countries": {
+        "items": {
+          "type": "string"
+        },
+        "type": [
+          "array",
+          "null"
+        ]
+      },
+      "name": {
+        "description": "Listed entity name.",
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "programs": {
+        "description": "Sanctions programmes.",
+        "items": {
+          "type": "string"
+        },
+        "type": [
+          "array",
+          "null"
+        ]
+      },
+      "score": {
+        "description": "Fuzzy match score 0-1.",
+        "type": [
+          "number",
+          "null"
+        ]
+      },
+      "source": {
+        "description": "Source list (UN, EU FSF, US OFAC SDN, OpenSanctions PEPs).",
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "type": {
+        "description": "individual / entity.",
+        "type": [
+          "string",
+          "null"
+        ]
+      }
+    },
+    "type": "object"
+  },
+  "type": [
+    "array",
+    "null"
+  ]
+}

addedOutput schema / properties / results / items / properties / matched

Added value: +{
+  "description": "The screening outcome for this name: true only if at least one hit is classified as a match.",
+  "type": [
+    "boolean",
+    "null"
+  ]
+}

removedOutput schema / properties / results / items / properties / matches

Removed value: -{
-  "description": "Matched sanctioned / PEP entities, ranked by score descending.",
-  "items": {
-    "additionalProperties": true,
-    "properties": {
-      "datasets": {
-        "description": "Source lists (UN, EU, OFAC, PEP, ...).",
-        "items": {
-          "type": "string"
-        },
-        "type": "array"
-      },
-      "name": {
-        "description": "Matched entity name.",
-        "type": "string"
-      },
-      "schema": {
-        "description": "OpenSanctions schema, e.g. Person, Company.",
-        "type": "string"
-      },
-      "score": {
-        "description": "Fuzzy match score 0-1.",
-        "type": "number"
-      },
-      "topics": {
-        "description": "Risk topics tagged on the entity.",
-        "items": {
-          "type": "string"
-        },
-        "type": "array"
-      }
-    },
-    "type": "object"
-  },
-  "type": "array"
-}

changedOutput schema / properties / results / items / properties / query / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```

addedOutput schema / properties / results / items / properties / requiresManualReview

Added value: +{
+  "description": "True when hits need human verification.",
+  "type": [
+    "boolean",
+    "null"
+  ]
+}

addedOutput schema / properties / results / items / properties / topScore

Added value: +{
+  "description": "Highest fuzzy score among candidates; null when there are none. A high score alone is not a match — see classification.",
+  "type": [
+    "number",
+    "null"
+  ]
+}

changedOutput schema / properties / results / type

Previous value: -"array"New value: +[
+  "array",
+  "null"
+]

addedOutput schema / properties / sourcesUnavailable

Added value: +{
+  "description": "Lists that could not be checked on this call; non-empty means the screening is incomplete.",
+  "type": [
+    "array",
+    "null"
+  ]
+}

addedOutput schema / properties / total

Added value: +{
+  "description": "Number of names screened.",
+  "type": [
+    "integer",
+    "null"
+  ]
+}

First observedMay 23, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds substantial context beyond those: it discloses the return structure (per-name match lists, fuzzy scores, source attribution, risk topics, disclaimer) and, crucially, sets expectations that matches are 'informational decision-support... not legal or compliance advice' and that a match 'requires verification, not a confirmed listing.' This is exactly the kind of behavioral caveat agents need and that annotations cannot express.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four tight sentences with zero filler. The core purpose is front-loaded, followed by use case, return format, and the decision-support caveat. Every sentence earns its place and nothing is redundant with the schema or annotations.

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?

With an output schema present, return-value explanation is unnecessary, and the description still sketches the output fields. Combined with 100% schema coverage and full annotations (read-only, idempotent, non-destructive, open-world), the description covers purpose, usage, behavior, and limitations. Nothing an agent needs to invoke this correctly is missing.

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 description coverage is 100% — names, fuzzy, and min_score each have meaningful descriptions in the schema itself. The tool description references fuzzy match scores but adds no syntax or formatting detail beyond what the schema already documents. The baseline of 3 applies correctly since the schema carries the parameter-semantics burden.

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?

The description opens with a specific verb+resource: 'Screen one or more person or company names against UN, EU, OFAC and PEP sanctions lists'. It names the exact list sources (UN, EU, OFAC, PEP) and the data provider (OpenSanctions, 768K+ entries), making it clearly distinguishable from sibling tools like lookup_company, lookup_lei, or validate_vat, which serve different counterparty-check purposes.

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?

The description gives an explicit typical use case — 'counterparty checks before onboarding or processing a payment' — which tells an agent when to reach for this tool. It does not, however, explicitly name alternative tools or state when NOT to use it, leaving some routing to inference. Given the siblings include overlapping due-diligence tools (kyb_full, company_enriched, lookup_company), an explicit exclusion would have pushed this to 5.

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

All nordic-data 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.