Skip to main content
Glama

sanctions-screening-mcp-server

sanctions-screening-mcp-server: list sources

sanctions_list_sources
Read-onlyIdempotent

List supported watchlists (OFAC SDN + Consolidated, EU, UK, UN, BIS Entity/Denied Persons/Unverified/Military End User, State ITAR Debarred/Nonproliferation) and GLEIF datasets with current mirrored counts, source URLs, licenses, readiness, and as-of timestamps. Each sanctions list carries lastHarvestedAt, its last successful harvest, and publishedAt, the date its publisher put on that document (not when the list's content last changed); both are absent until this server records a harvest of the list. lastRefresh reports a sanctions refresh that is running or failed and names the lists that failed; sanctionsAsOf is the last refresh in which every list harvested. coverageNotice names unloaded CSL lists and how to refresh them; prior mirror readiness does not establish coverage of newly added lists. For GLEIF, reports Level 2 ownership relationships, reporting-exception coverage, alternate-name index readiness, and whether entity status and successors are loaded. Use this for provenance, freshness, and coverage on any result. Attribution: UK data is under the Open Government Licence v3.0; BIS and State CSL data is supplied by the International Trade Administration under its published terms. This product uses the International Trade Administration’s Data API but is not endorsed or certified by the International Trade Administration.

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": "sanctions_list_sources"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Output Schema

NameRequiredDescriptionDefault
errorNoPresent when the call failed. Absent on success.
leiAsOfNoISO 8601 timestamp of the last completed GLEIF sync, when available.
sourcesNoAll supported sources, sanctions lists then the GLEIF dataset. Check coverageNotice for unloaded CSL lists.
leiReadyNoTrue once the GLEIF (LEI) mirror has completed at least one full sync.
lastRefreshNoThe last sanctions refresh, present only while one is running (in_progress) or after one failed (error); absent before any refresh and once the last one succeeded. While a refresh runs, each list keeps the values of the last run that finished it.
sanctionsAsOfNoISO 8601 timestamp of the last completed sanctions sync — the last refresh in which every list harvested — when available. A list that harvested in a later, partly failed refresh carries a later lastHarvestedAt; neither is a publisher's date.
coverageNoticeNoUnloaded CSL list codes and refresh guidance. Present when any CSL list has zero mirrored records; prior sanctions readiness does not establish coverage of newly added lists.
sanctionsReadyNoTrue once the sanctions mirror has completed at least one full sync.
entityStatusLoadedNoWhether a completed mirror:init golden-copy load has written entity status and successors for every GLEIF entity in that copy. A sanctions_get_entity record's own entityStatusLoaded is the per-record answer in either state.
alternateNamesIndexedNoWhether the GLEIF alternate-name index — trading, previous, alternative-language, and transliterated names — is built. When false, sanctions_resolve_entity searches legal names only until mirror:init reloads the GLEIF golden copy. True on a GLEIF mirror that has never loaded (leiReady false): its empty index is complete, and the first load builds it with the entities.
reportingExceptionsLoadedNoWhether GLEIF reporting exceptions are loaded. When false, sanctions_trace_ownership reads a parent level with no published relationship as unknown.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • changedOutput schema / anyOf
      Previous value: -[
      -  {
      -    "not": {
      -      "required": [
      -        "error"
      -      ]
      -    },
      -    "required": [
      -      "sanctionsReady",
      -      "leiReady",
      -      "reportingExceptionsLoaded",
      -      "alternateNamesIndexed",
      -      "sources"
      -    ]
      -  },
      -  {
      -    "required": [
      -      "error"
      -    ]
      -  }
      -]New value: +[
      +  {
      +    "not": {
      +      "required": [
      +        "error"
      +      ]
      +    },
      +    "required": [
      +      "sanctionsReady",
      +      "leiReady",
      +      "reportingExceptionsLoaded",
      +      "alternateNamesIndexed",
      +      "entityStatusLoaded",
      +      "sources"
      +    ]
      +  },
      +  {
      +    "required": [
      +      "error"
      +    ]
      +  }
      +]
    • addedOutput schema / properties / entityStatusLoaded
      Added value: +{
      +  "description": "Whether a completed mirror:init golden-copy load has written entity status and successors for every GLEIF entity in that copy. A sanctions_get_entity record's own entityStatusLoaded is the per-record answer in either state.",
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / lastRefresh
      Added value: +{
      +  "description": "The last sanctions refresh, present only while one is running (in_progress) or after one failed (error); absent before any refresh and once the last one succeeded. While a refresh runs, each list keeps the values of the last run that finished it.",
      +  "oneOf": [
      +    {
      +      "additionalProperties": false,
      +      "description": "A sanctions refresh that is running.",
      +      "properties": {
      +        "startedAt": {
      +          "description": "When the running refresh started (UTC ISO 8601).",
      +          "type": "string"
      +        },
      +        "status": {
      +          "const": "in_progress",
      +          "description": "A sanctions refresh is running — or was killed before it finished, which reads the same way.",
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "status"
      +      ],
      +      "type": "object"
      +    },
      +    {
      +      "additionalProperties": false,
      +      "description": "A sanctions refresh that failed.",
      +      "properties": {
      +        "failedSources": {
      +          "description": "The lists whose harvest failed in that refresh, in list order; each keeps its previous lastHarvestedAt and publishedAt. Empty when the run recorded its lists' outcomes and none failed: it stopped for another reason (cancelled or out of time). Absent when no list's outcome is recorded for that run — one an earlier server version made, or one that stopped before any list finished — so which lists failed is unknown.",
      +          "items": {
      +            "enum": [
      +              "ofac_sdn",
      +              "ofac_consolidated",
      +              "eu",
      +              "uk",
      +              "un",
      +              "bis_el",
      +              "bis_dpl",
      +              "bis_uvl",
      +              "bis_meu",
      +              "state_dtc",
      +              "state_acn"
      +            ],
      +            "type": "string"
      +          },
      +          "type": "array"
      +        },
      +        "startedAt": {
      +          "description": "When the failed refresh started (UTC ISO 8601).",
      +          "type": "string"
      +        },
      +        "status": {
      +          "const": "error",
      +          "description": "The last sanctions refresh failed.",
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "status"
      +      ],
      +      "type": "object"
      +    }
      +  ]
      +}
    • changedOutput schema / properties / sanctionsAsOf / description
      Previous value: -"ISO 8601 timestamp of the last completed sanctions sync, when available."New value: +"ISO 8601 timestamp of the last completed sanctions sync — the last refresh in which every list harvested — when available. A list that harvested in a later, partly failed refresh carries a later lastHarvestedAt; neither is a publisher's date."
    • changedOutput schema / properties / sources / items / description
      Previous value: -"One supported source with current mirrored count, provenance, and license; zero-record CSL lists are not loaded."New value: +"One supported source with current mirrored count, provenance, and license, and for a sanctions list its last harvest and that document's date; zero-record CSL lists are not loaded."
    • addedOutput schema / properties / sources / items / properties / lastHarvestedAt
      Added value: +{
      +  "description": "When this list's last successful harvest completed (UTC ISO 8601; sanctions lists only). Absent until this server records a successful harvest of the list — so on a mirror an earlier server version wrote, until its next refresh — which means unknown, not stale. sanctionsAsOf is the mirror-wide value, not this list's.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / sources / items / properties / publishedAt
      Added value: +{
      +  "description": "The date the publisher put on the document that harvest read, ISO 8601 at the precision and offset published (a date-only value stays YYYY-MM-DD): OFAC DateOfIssue, EU generationDate, UK DateGenerated, UN dateGenerated, and each CSL list's source_last_updated. It dates the document, not the last change to the list's content: some publishers move it when nothing in the list changed (the UN file is regenerated daily). Absent with lastHarvestedAt, or when the document carried no date this server reads.",
      +  "type": "string"
      +}
  2. Changed3 schema fields changed
    • addedOutput schema / properties / coverageNotice
      Added value: +{
      +  "description": "Unloaded CSL list codes and refresh guidance. Present when any CSL list has zero mirrored records; prior sanctions readiness does not establish coverage of newly added lists.",
      +  "type": "string"
      +}
    • changedOutput schema / properties / sources / description
      Previous value: -"All loaded sources, sanctions lists then the GLEIF dataset."New value: +"All supported sources, sanctions lists then the GLEIF dataset. Check coverageNotice for unloaded CSL lists."
    • changedOutput schema / properties / sources / items / description
      Previous value: -"One loaded source with count, provenance, and license."New value: +"One supported source with current mirrored count, provenance, and license; zero-record CSL lists are not loaded."
  3. Changed5 schema fields changed
    • changedOutput schema / anyOf
      Previous value: -[
      -  {
      -    "not": {
      -      "required": [
      -        "error"
      -      ]
      -    },
      -    "required": [
      -      "sanctionsReady",
      -      "leiReady",
      -      "reportingExceptionsLoaded",
      -      "sources"
      -    ]
      -  },
      -  {
      -    "required": [
      -      "error"
      -    ]
      -  }
      -]New value: +[
      +  {
      +    "not": {
      +      "required": [
      +        "error"
      +      ]
      +    },
      +    "required": [
      +      "sanctionsReady",
      +      "leiReady",
      +      "reportingExceptionsLoaded",
      +      "alternateNamesIndexed",
      +      "sources"
      +    ]
      +  },
      +  {
      +    "required": [
      +      "error"
      +    ]
      +  }
      +]
    • addedOutput schema / properties / alternateNamesIndexed
      Added value: +{
      +  "description": "Whether the GLEIF alternate-name index — trading, previous, alternative-language, and transliterated names — is built. When false, sanctions_resolve_entity searches legal names only until mirror:init reloads the GLEIF golden copy. True on a GLEIF mirror that has never loaded (leiReady false): its empty index is complete, and the first load builds it with the entities.",
      +  "type": "boolean"
      +}
    • changedOutput schema / properties / sources / items / properties / recordCount / description
      Previous value: -"Records currently loaded for this source (Level 1 entities for gleif)."New value: +"Records currently loaded for this source — for gleif, Level 1 entity records."
    • addedOutput schema / properties / sources / items / properties / relationshipCount
      Added value: +{
      +  "description": "GLEIF Level 2 ownership relationships loaded (gleif only).",
      +  "type": "number"
      +}
    • changedOutput schema / properties / sources / items / properties / url / description
      Previous value: -"Upstream source URL the mirror harvests from."New value: +"Upstream URL the mirror harvests this source from, as configured — for gleif, the golden-copy API base."
  4. Changed4 schema fields changed
    • changedOutput schema / anyOf
      Previous value: -[
      -  {
      -    "not": {
      -      "required": [
      -        "error"
      -      ]
      -    },
      -    "required": [
      -      "sanctionsReady",
      -      "leiReady",
      -      "sources"
      -    ]
      -  },
      -  {
      -    "required": [
      -      "error"
      -    ]
      -  }
      -]New value: +[
      +  {
      +    "not": {
      +      "required": [
      +        "error"
      +      ]
      +    },
      +    "required": [
      +      "sanctionsReady",
      +      "leiReady",
      +      "reportingExceptionsLoaded",
      +      "sources"
      +    ]
      +  },
      +  {
      +    "required": [
      +      "error"
      +    ]
      +  }
      +]
    • addedOutput schema / properties / reportingExceptionsLoaded
      Added value: +{
      +  "description": "Whether GLEIF reporting exceptions are loaded. When false, sanctions_trace_ownership reads a parent level with no published relationship as unknown.",
      +  "type": "boolean"
      +}
    • changedOutput schema / properties / sources / items / properties / recordCount / description
      Previous value: -"Records currently loaded for this source."New value: +"Records currently loaded for this source (Level 1 entities for gleif)."
    • addedOutput schema / properties / sources / items / properties / reportingExceptionCount
      Added value: +{
      +  "description": "GLEIF reporting-exception records loaded (gleif only). Absent when the dataset has never been loaded — never read as zero.",
      +  "type": "number"
      +}
  5. Changed6 schema fields changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedInput schema / additionalProperties
      Added value: +false
    • changedOutput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedOutput schema / anyOf
      Added value: +[
      +  {
      +    "not": {
      +      "required": [
      +        "error"
      +      ]
      +    },
      +    "required": [
      +      "sanctionsReady",
      +      "leiReady",
      +      "sources"
      +    ]
      +  },
      +  {
      +    "required": [
      +      "error"
      +    ]
      +  }
      +]
    • addedOutput schema / properties / error
      Added value: +{
      +  "additionalProperties": {},
      +  "description": "Present when the call failed. Absent on success.",
      +  "properties": {
      +    "code": {
      +      "description": "JSON-RPC error code for this failure.",
      +      "maximum": 9007199254740991,
      +      "minimum": -9007199254740991,
      +      "type": "integer"
      +    },
      +    "data": {
      +      "additionalProperties": {},
      +      "properties": {
      +        "reason": {
      +          "description": "Machine-readable failure mode.",
      +          "type": "string"
      +        },
      +        "recovery": {
      +          "additionalProperties": {},
      +          "description": "Actionable next step for the caller.",
      +          "properties": {
      +            "hint": {
      +              "type": "string"
      +            }
      +          },
      +          "required": [
      +            "hint"
      +          ],
      +          "type": "object"
      +        },
      +        "retryable": {
      +          "description": "Whether retrying may succeed.",
      +          "type": "boolean"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "message": {
      +      "description": "Human-readable description of what went wrong.",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "code",
      +    "message"
      +  ],
      +  "type": "object"
      +}
    • removedOutput schema / required
      Removed value: -[
      -  "sanctionsReady",
      -  "leiReady",
      -  "sources"
      -]
  6. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint/idempotentHint/openWorldHint=false, yet the description still adds real behavior: fields are absent until a harvest is recorded, lastRefresh may indicate a running or failed refresh, and 'prior mirror readiness does not establish coverage of newly added lists' is a genuine caveat. Much of the middle passage, however, documents individual return fields rather than behavior, which overlaps with the existing output schema.

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

Conciseness3/5

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

The what-it-returns claim is correctly front-loaded, but the body is a single dense sentence chain enumerating return fields to an output schema that already defines them, and it closes with a multi-clause licensing/attribution block. Every clause is defensible individually, but the whole is heavier than an agent needs to select and call a zero-argument listing tool.

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?

With no parameters, a full output schema, and safety annotations already supplied, the description covers the remaining gap an agent cares about for a provenance tool: freshness, failed-refresh reporting, and coverage caveats. Nothing an agent needs in order to call it correctly is absent.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. No parameter syntax or format detail is needed or missing.

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 ('List supported watchlists ... and GLEIF datasets') and enumerates exactly which sources are covered (OFAC, EU, UK, UN, BIS, State, GLEIF), which no sibling tool does. It never explicitly names a sibling to contrast with, so differentiation is inferable from the resource rather than stated.

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 this for provenance, freshness, and coverage on any result' gives a clear use context that an agent can act on. There are no exclusions or named alternatives telling the agent when NOT to call this, so it stops short of full routing guidance.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.