MCP Server

sanctions-screening-mcp-server

io.github.cyanheads/sanctions-screening-mcp-server
Legal & Compliance Security Public & reachable MCP 2025-11-25

What this MCP does

Screens names and identifiers against OFAC, EU, UK, and UN sanctions lists and resolves entities and ownership through GLEIF data.

sanctions_get_designation
sanctions-screening-mcp-server: get designation
Fetch the full record for one sanctions designation by source list + entry ID or the list's published reference number — the drill-in after sanctions_screen_name or sanctions_screen_identifier surfaces a candidate, or the lookup for a reference a notice cites (UN QDe.004, EU EU.27.28, UK OFSI Group ID). Returns all published aliases, identifiers (passport, national ID, tax and registration numbers, SWIFT/BIC codes, digital-currency addresses, vessel call signs, aircraft tail and serial numbers, phone numbers, email addresses, websites), addresses, dates and places of birth at the precision the source published, nationalities, descriptive features (a vessel's flag, type, and tonnage; an aircraft's model and operator; a title or gender; sanctions notes), sanctioning program, legal basis, and designation date. The record reflects exactly what the source published; missing fields mean the source omitted them. This is a screening aid — the designation record supports a compliance review, it is not itself a determination.
Read only Idempotent
Input schema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['source', 'entryId'], 'properties': {'source': {'enum': ['ofac_sdn', 'ofac_consolidated', 'eu', 'uk', 'un'], 'type': 'string', 'description': 'Which source list the entry belongs to.'}, 'entryId': {'type': 'string', 'minLength': 1, 'description': "The source list's own entry ID (the sourceEntryId from sanctions_screen_name), or the reference number the list publishes for the entry (UN QDe.004, EU EU.27.28, UK OFSI Group ID 14196). Matched trimmed and case-insensitive, entry ID first."}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'anyOf': [{'not': {'required': ['error']}, 'required': ['source', 'sourceLabel', 'sourceEntryId', 'entityType', 'primaryName', 'aliases', 'identifiers', 'addresses', 'datesOfBirth', 'nationalities', 'features', 'caveat']}, {'required': ['error']}], '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'error': {'type': 'object', 'required': ['code', 'message'], 'properties': {'code': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'JSON-RPC error code for this failure.'}, 'data': {'type': 'object', 'properties': {'reason': {'type': 'string', 'examples': ['designation_not_found', 'reference_ambiguous', 'mirror_not_ready'], 'description': 'Machine-readable failure mode. Declared by this tool: `designation_not_found`: No designation in the given source has that entry ID or reference number in the mirror. `reference_ambiguous`: The entry ID is a reference number more than one designation in the source publishes. `mirror_not_ready`: The sanctions mirror has never completed an initial sync. Other values are possible when a failure originates below the handler.'}, 'recovery': {'type': 'object', 'required': ['hint'], 'properties': {'hint': {'type': 'string'}}, 'description': 'Actionable next step for the caller.', 'additionalProperties': {}}, 'retryable': {'type': 'boolean', 'description': 'Whether retrying may succeed.'}}, 'additionalProperties': {}}, 'message': {'type': 'string', 'description': 'Human-readable description of what went wrong.'}}, 'description': 'Present when the call failed. Absent on success.', 'additionalProperties': {}}, 'caveat': {'type': 'string', 'description': 'Decision-support caveat â\x80\x94 this is a screening aid, not a compliance determination.'}, 'source': {'enum': ['ofac_sdn', 'ofac_consolidated', 'eu', 'uk', 'un'], 'type': 'string', 'description': 'Source list the entry belongs to.'}, 'aliases': {'type': 'array', 'items': {'type': 'object', 'required': ['name', 'nameType'], 'properties': {'name': {'type': 'string', 'description': 'Alias as published.'}, 'nameType': {'enum': ['primary', 'aka', 'fka', 'low-quality-aka'], 'type': 'string', 'description': 'Alias provenance: a.k.a., f.k.a., or a low-quality a.k.a.'}}, 'description': 'One published alias.', 'additionalProperties': False}, 'description': 'All published aliases / name variants.'}, 'program': {'type': 'string', 'description': 'Sanctioning program / regime, when published.'}, 'remarks': {'type': 'string', 'description': 'Free-form remarks published by the source, when present.'}, 'features': {'type': 'array', 'items': {'type': 'object', 'required': ['type', 'value'], 'properties': {'type': {'type': 'string', 'description': "The source's own label for the value, verbatim (e.g. Vessel Flag, VESSEL TYPE, Secondary sanctions risk:, CurrentBelievedFlagOfShip)."}, 'circa': {'type': 'boolean', 'const': True, 'description': 'Present when the source flags a date value as approximate.'}, 'value': {'type': 'string', 'description': 'The value as published; a date is ISO 8601 at the precision the source published.'}}, 'description': 'One published descriptive value.', 'additionalProperties': False}, 'description': "Values the source publishes to describe the party rather than identify it, in published order: OFAC's vessel flag, type, and tonnage, aircraft model and operator, title, gender, and sanctions notes; the UK list's ship details. Empty when the source publishes none. Screening never matches on them."}, 'addresses': {'type': 'array', 'items': {'type': 'object', 'required': ['full'], 'properties': {'full': {'type': 'string', 'description': 'Single-line rendering of the address.'}, 'country': {'type': 'string', 'description': 'Country, when published.'}}, 'description': 'One published address.', 'additionalProperties': False}, 'description': 'Published addresses.'}, 'entityType': {'enum': ['person', 'organization', 'vessel', 'aircraft', 'unknown'], 'type': 'string', 'description': 'Entity classification as published.'}, 'legalBasis': {'type': 'string', 'description': "Statutory / regulatory basis as the list publishes it â\x80\x94 OFAC's legal-basis references, the EU regulation title, the UK regime's regulations â\x80\x94 several joined with '; '. Absent when unpublished; the UN list publishes none."}, 'identifiers': {'type': 'array', 'items': {'type': 'object', 'required': ['type', 'value'], 'properties': {'type': {'type': 'string', 'description': 'Identifier category as the source labels it (e.g. Passport, National ID, SWIFT/BIC, Digital Currency Address - XBT, Phone Number, Website).'}, 'value': {'type': 'string', 'description': 'Identifier value exactly as published, letter case included.'}, 'country': {'type': 'string', 'description': 'Issuing country/authority, when published.'}}, 'description': 'One structured identifier.', 'additionalProperties': False}, 'description': 'Published identifiers: identity documents (passport, national ID, tax, registration) and, where the source publishes them, SWIFT/BIC codes, digital-currency addresses, vessel call signs, aircraft tail and serial numbers, phone numbers, email addresses, and websites.'}, 'primaryName': {'type': 'string', 'description': 'Primary published name.'}, 'sourceLabel': {'type': 'string', 'description': 'Human-readable name of the source list.'}, 'datesOfBirth': {'type': 'array', 'items': {'type': 'object', 'properties': {'date': {'type': 'string', 'description': 'Date of birth in ISO 8601 at the precision the source published: YYYY-MM-DD, YYYY-MM, or YYYY. A range is an interval whose ends keep their own precision (1955/1957); an open end is .. (../1980). A value with no ISO form is kept as published.'}, 'circa': {'type': 'boolean', 'const': True, 'description': 'Present when the source flags the date as approximate; never without date.'}, 'place': {'type': 'string', 'description': 'Place of birth, when published.'}}, 'description': 'One date/place of birth.', 'additionalProperties': False}, 'description': 'Published dates and places of birth (persons).'}, 'nationalities': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Published nationalities / citizenships.'}, 'sourceEntryId': {'type': 'string', 'description': "The source list's own entry ID."}, 'designationDate': {'type': 'string', 'description': "The source's own designation date as YYYY-MM-DD; absent when unpublished. An OFAC party is dated from its entries on the lists that file publishes, so its ofac_sdn and ofac_consolidated records can differ."}, 'referenceNumber': {'type': 'string', 'description': "The list's published reference number (UN, EU, UK OFSI Group ID); absent when the list publishes none for the entry. OFAC publishes none â\x80\x94 its entry ID is its published number."}}, 'additionalProperties': False}
sanctions_get_entity
sanctions-screening-mcp-server: get entity
Fetch the full GLEIF Level 1 record for one LEI: legal name, other/trading names, legal and headquarters addresses, registration status, jurisdiction, registration authority and ID, and last-update date — plus a sanctions cross-reference against all loaded watchlists. The cross-reference screens the legal name and every other and transliterated name strict (exact, then all tokens present — never fuzzy, unlike sanctions_screen_name), and looks up the LEI and the registration number as exact non-document identifiers, the registration number matching only an identifier published for the country of the entity's legal jurisdiction. Hits merge to one per designation, an OFAC party both OFAC lists publish to one hit whose sources names both: matchedOn names every input that produced each, and a hit only an identifier produced carries matchedIdentifiers and no matchedName. The screening cross-reference is a screening AID: a hit is a candidate to verify against the official source, and no hit is not a clearance. screeningStatus says whether that cross-reference actually ran — an empty sanctionsHits under not_ready means the sanctions mirror was unavailable, not that nothing matched. sanctionsScreen says whether the hit list is the whole set: it reports how many potential matches existed before the cap, so a capped cross-reference is distinguishable from a complete one. LEI must be a 20-character GLEIF identifier (18 alphanumerics + 2 check digits).
Read only Idempotent
Input schema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['lei'], 'properties': {'lei': {'type': 'string', 'pattern': '^[A-Z0-9]{18}[0-9]{2}$', 'description': 'The 20-character GLEIF Legal Entity Identifier to look up.'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'anyOf': [{'not': {'required': ['error']}, 'required': ['lei', 'legalName', 'otherNames', 'alternateNames', 'sanctionsHits', 'screeningStatus', 'caveat']}, {'required': ['error']}], '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'lei': {'type': 'string', 'description': 'The 20-character GLEIF Legal Entity Identifier.'}, 'error': {'type': 'object', 'required': ['code', 'message'], 'properties': {'code': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'JSON-RPC error code for this failure.'}, 'data': {'type': 'object', 'properties': {'reason': {'type': 'string', 'examples': ['lei_not_found', 'invalid_lei_checksum', 'mirror_not_ready'], 'description': 'Machine-readable failure mode. Declared by this tool: `lei_not_found`: No GLEIF entity in the mirror carries the LEI, and its check digits are valid. `invalid_lei_checksum`: No GLEIF entity in the mirror carries the LEI, and its ISO 17442 check digits fail. `mirror_not_ready`: The GLEIF (LEI) mirror has never completed an initial sync. Other values are possible when a failure originates below the handler.'}, 'recovery': {'type': 'object', 'required': ['hint'], 'properties': {'hint': {'type': 'string'}}, 'description': 'Actionable next step for the caller.', 'additionalProperties': {}}, 'retryable': {'type': 'boolean', 'description': 'Whether retrying may succeed.'}}, 'additionalProperties': {}}, 'message': {'type': 'string', 'description': 'Human-readable description of what went wrong.'}}, 'description': 'Present when the call failed. Absent on success.', 'additionalProperties': {}}, 'caveat': {'type': 'string', 'description': 'Decision-support caveat â\x80\x94 the screening cross-reference is an aid, not a determination.'}, 'status': {'type': 'string', 'description': 'Registration status (e.g. ISSUED, LAPSED).'}, 'legalName': {'type': 'string', 'description': 'Registered legal name.'}, 'lastUpdate': {'type': 'string', 'description': 'ISO 8601 last-update timestamp from the LEI record.'}, 'otherNames': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Other names published in the LEI record (trading, previous, and alternative-language legal names), as plain strings.'}, 'jurisdiction': {'type': 'string', 'description': 'Legal jurisdiction (ISO code), when published.'}, 'legalAddress': {'type': 'string', 'description': 'Single-line legal address, when published.'}, 'sanctionsHits': {'type': 'array', 'items': {'type': 'object', 'required': ['source', 'sourceLabel', 'sourceEntryId', 'sources', 'primaryName', 'matchedOn'], 'properties': {'score': {'type': 'number', 'description': 'Never set by this cross-reference: only an approximate (fuzzy) match carries a raw Jaro-Winkler score, and the cross-reference screens strict.'}, 'source': {'enum': ['ofac_sdn', 'ofac_consolidated', 'eu', 'uk', 'un'], 'type': 'string', 'description': 'Watchlist whose record this hit is attributed to: primaryName comes from it. For an OFAC party both OFAC lists publish, ofac_sdn unless the Consolidated record matched alone or better, and matchedName, matchedIdentifiers, and matchedOn cover what either record matched; sources names every list.'}, 'sources': {'type': 'array', 'items': {'enum': ['ofac_sdn', 'ofac_consolidated', 'eu', 'uk', 'un'], 'type': 'string'}, 'description': 'Every screened list this candidate is on, in list order: one list, or ofac_sdn and ofac_consolidated together for an OFAC party both OFAC lists publish under one entry ID â\x80\x94 one hit, not two. Read this, not source, for every list; the entry ID resolves in sanctions_get_designation under each.'}, 'matchType': {'enum': ['exact', 'strong', 'approximate'], 'type': 'string', 'description': 'Match classification of matchedName: exact or strong, never approximate (the cross-reference screens strict, never fuzzy). Absent when only an identifier produced the hit.'}, 'matchedOn': {'type': 'array', 'items': {'type': 'object', 'required': ['input', 'value'], 'properties': {'input': {'enum': ['legal_name', 'other_name', 'lei', 'registration_number'], 'type': 'string', 'description': 'Which value: legal_name, or other_name (an other or transliterated name), each screened as a name, strict; lei, or registration_number (the ID at the registration authority), each looked up as a non-document identifier.'}, 'value': {'type': 'string', 'description': 'The value as GLEIF publishes it.'}, 'nameType': {'type': 'string', 'description': "GLEIF's type for an other_name (e.g. TRADING_OR_OPERATING_NAME, AUTO_ASCII_TRANSLITERATED_LEGAL_NAME), or UNKNOWN for a name the mirror stored without one. Present on other_name only."}}, 'description': 'One value of the entity the cross-reference screened.', 'additionalProperties': False}, 'description': 'Every input of the entity that produced this hit â\x80\x94 its legal name, an other or transliterated name, its LEI, or its registration number â\x80\x94 in screening order.'}, 'matchedName': {'type': 'string', 'description': "The designation's name or alias that matched one of the entity's screened names â\x80\x94 the strongest match. Absent when only an identifier produced the hit."}, 'primaryName': {'type': 'string', 'description': 'Primary published name of the designation.'}, 'sourceLabel': {'type': 'string', 'description': 'Human-readable source list name.'}, 'sourceEntryId': {'type': 'string', 'description': 'Source entry ID â\x80\x94 pass to sanctions_get_designation.'}, 'matchedIdentifiers': {'type': 'array', 'items': {'type': 'object', 'required': ['type', 'value'], 'properties': {'type': {'type': 'string', 'description': 'Identifier label as the list publishes it (e.g. Legal Entity Number, Registration Number).'}, 'value': {'type': 'string', 'description': 'The identifier value, as published.'}, 'country': {'type': 'string', 'description': 'Issuing country as published, when published.'}}, 'description': "An identifier the designation publishes that equals the entity's LEI, or its registration number published for the country of its legal jurisdiction.", 'additionalProperties': False}, 'description': "Every identifier the designation publishes that equals the entity's LEI or its country-matched registration number, as published. Present only when an identifier produced the hit."}}, 'description': "A potential watchlist match on one or more of the entity's names or identifiers â\x80\x94 verify, do not assume.", 'additionalProperties': False}, 'description': 'Sanctions screening cross-reference of the entity, one hit per designation (an OFAC party both OFAC lists publish once): exact name and identifier matches first, then strong name matches.'}, 'alternateNames': {'type': 'array', 'items': {'type': 'object', 'required': ['name', 'type'], 'properties': {'name': {'type': 'string', 'description': 'The name as published.'}, 'type': {'type': 'string', 'description': "GLEIF name type: PREVIOUS_LEGAL_NAME (a former legal name, not the current one), TRADING_OR_OPERATING_NAME, ALTERNATIVE_LANGUAGE_LEGAL_NAME, PREFERRED_ASCII_TRANSLITERATED_LEGAL_NAME, AUTO_ASCII_TRANSLITERATED_LEGAL_NAME, or UNKNOWN for a name the mirror stored without GLEIF's type."}}, 'description': 'One name GLEIF publishes beside the legal name.', 'additionalProperties': False}, 'description': 'Every other and transliterated name with its type, in the order published â\x80\x94 the typed view of otherNames plus the ASCII transliterations of a legal name in another script.'}, 'sanctionsScreen': {'type': 'object', 'required': ['totalAvailable', 'totalAvailableBasis', 'hasMore', 'screenedInputs'], 'properties': {'hasMore': {'type': 'boolean', 'description': "True when the potential matches were capped â\x80\x94 re-screen the entity's names with sanctions_screen_name and look up its LEI and registration number with sanctions_screen_identifier to see the rest."}, 'screenedInputs': {'type': 'array', 'items': {'type': 'object', 'required': ['input', 'value'], 'properties': {'input': {'enum': ['legal_name', 'other_name', 'lei', 'registration_number'], 'type': 'string', 'description': 'Which value: legal_name, or other_name (an other or transliterated name), each screened as a name, strict; lei, or registration_number (the ID at the registration authority), each looked up as a non-document identifier.'}, 'value': {'type': 'string', 'description': 'The value as GLEIF publishes it.'}, 'nameType': {'type': 'string', 'description': "GLEIF's type for an other_name (e.g. TRADING_OR_OPERATING_NAME, AUTO_ASCII_TRANSLITERATED_LEGAL_NAME), or UNKNOWN for a name the mirror stored without one. Present on other_name only."}}, 'description': 'One value of the entity the cross-reference screened.', 'additionalProperties': False}, 'description': 'What the cross-reference screened beyond the legal name and the LEI, which it always screens: every other and transliterated name, then the registration number when the entity publishes one (a not-available placeholder such as N/A is none) and a legal jurisdiction to match it by. Empty when there is nothing beyond those two.'}, 'totalAvailable': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'Distinct designations the cross-reference found across every screened name and identifier, an OFAC party both OFAC lists publish counted once, before the cap was applied.'}, 'totalAvailableBasis': {'enum': ['exact', 'lower_bound'], 'type': 'string', 'description': 'How to read totalAvailable. Always exact here: every name is screened strict, never fuzzy, and a strict screen counts every designation it reaches, so totalAvailable is the whole set across the screened names and identifiers.'}}, 'description': "Disclosure for the cross-reference: how many potential matches existed before the cap, whether sanctionsHits is the complete set, and what was screened. Present only when screeningStatus is 'screened'.", 'additionalProperties': False}, 'screeningStatus': {'enum': ['screened', 'not_ready'], 'type': 'string', 'description': "Whether the cross-reference ran: screened = the entity's names and identifiers were screened against every loaded watchlist; not_ready = the sanctions mirror has never synced, so no screening ran and the empty sanctionsHits says nothing about this entity. Read sanctionsHits only when this is 'screened'."}, 'headquartersAddress': {'type': 'string', 'description': 'Single-line headquarters address, when published.'}, 'registrationAuthorityId': {'type': 'string', 'description': 'Registration authority (RA) code, when published.'}, 'registrationAuthorityEntityId': {'type': 'string', 'description': "The entity's ID at its registration authority, when published."}}, 'additionalProperties': False}
sanctions_list_sources
sanctions-screening-mcp-server: list sources
List the sanctions watchlists (OFAC SDN + Consolidated, EU, UK, UN) and GLEIF datasets currently loaded in the local mirror, each with its record count, source URL, license, and the mirror's readiness and as-of timestamp — for GLEIF, also its Level 2 ownership relationship count, whether its reporting exceptions are loaded and how many, and whether its alternate-name index is built. Use this for provenance and freshness on any result — results are only as current as the last mirror refresh, and a not-ready mirror means screening cannot run yet. Attribution: UK data is under the Open Government Licence v3.0; all sources are cited here.
Read only Idempotent
Input schema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {}, 'additionalProperties': False}
Output schema
{'type': 'object', 'anyOf': [{'not': {'required': ['error']}, 'required': ['sanctionsReady', 'leiReady', 'reportingExceptionsLoaded', 'alternateNamesIndexed', 'sources']}, {'required': ['error']}], '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'error': {'type': 'object', 'required': ['code', 'message'], 'properties': {'code': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'JSON-RPC error code for this failure.'}, 'data': {'type': 'object', 'properties': {'reason': {'type': 'string', 'description': 'Machine-readable failure mode.'}, 'recovery': {'type': 'object', 'required': ['hint'], 'properties': {'hint': {'type': 'string'}}, 'description': 'Actionable next step for the caller.', 'additionalProperties': {}}, 'retryable': {'type': 'boolean', 'description': 'Whether retrying may succeed.'}}, 'additionalProperties': {}}, 'message': {'type': 'string', 'description': 'Human-readable description of what went wrong.'}}, 'description': 'Present when the call failed. Absent on success.', 'additionalProperties': {}}, 'leiAsOf': {'type': 'string', 'description': 'ISO 8601 timestamp of the last completed GLEIF sync, when available.'}, 'sources': {'type': 'array', 'items': {'type': 'object', 'required': ['code', 'label', 'recordCount', 'url', 'license'], 'properties': {'url': {'type': 'string', 'description': 'Upstream URL the mirror harvests this source from, as configured â\x80\x94 for gleif, the golden-copy API base.'}, 'code': {'type': 'string', 'description': 'Source code (ofac_sdn, eu, â\x80¦, or gleif).'}, 'label': {'type': 'string', 'description': 'Human-readable source name.'}, 'license': {'type': 'string', 'description': 'Redistribution license / terms for this source.'}, 'recordCount': {'type': 'number', 'description': 'Records currently loaded for this source â\x80\x94 for gleif, Level 1 entity records.'}, 'relationshipCount': {'type': 'number', 'description': 'GLEIF Level 2 ownership relationships loaded (gleif only).'}, 'reportingExceptionCount': {'type': 'number', 'description': 'GLEIF reporting-exception records loaded (gleif only). Absent when the dataset has never been loaded â\x80\x94 never read as zero.'}}, 'description': 'One loaded source with count, provenance, and license.', 'additionalProperties': False}, 'description': 'All loaded sources, sanctions lists then the GLEIF dataset.'}, 'leiReady': {'type': 'boolean', 'description': 'True once the GLEIF (LEI) mirror has completed at least one full sync.'}, 'sanctionsAsOf': {'type': 'string', 'description': 'ISO 8601 timestamp of the last completed sanctions sync, when available.'}, 'sanctionsReady': {'type': 'boolean', 'description': 'True once the sanctions mirror has completed at least one full sync.'}, 'alternateNamesIndexed': {'type': 'boolean', 'description': 'Whether the GLEIF alternate-name index â\x80\x94 trading, previous, alternative-language, and transliterated names â\x80\x94 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.'}, 'reportingExceptionsLoaded': {'type': 'boolean', 'description': 'Whether GLEIF reporting exceptions are loaded. When false, sanctions_trace_ownership reads a parent level with no published relationship as unknown.'}}, 'additionalProperties': False}
sanctions_resolve_entity
sanctions-screening-mcp-server: resolve entity
Resolve a company or organization name (with an optional jurisdiction: a country code, which includes its subdivisions, or an ISO 3166-2 subdivision code) to candidate GLEIF Legal Entity Identifiers (LEIs), ranked. This turns a free-text counterparty name into a stable global identifier that sanctions_get_entity and sanctions_trace_ownership key off. Every name GLEIF publishes takes part: the legal name, previous legal names, trading names, alternative-language legal names, and ASCII transliterations of a legal name in another script — each candidate reports the name it matched on and that name's type, one candidate per LEI. Strict mode (default) matches exact-normalized then all-tokens-present; fuzzy mode (or auto when strict is empty) adds Jaro-Winkler scoring labeled approximate with a raw 0–1 score plus the count of query tokens the matched name covers, which orders candidates that tie on score. Results are paged: totalAvailable and hasMore report candidates beyond the returned page, and nextOffset retrieves them. Returns potential matches to confirm against the GLEIF record — name resolution is a candidate ranking, not an authoritative identification.
Read only Idempotent
Input schema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['name'], 'properties': {'name': {'type': 'string', 'minLength': 1, 'description': 'The company / organization name to resolve to an LEI, in any script. It must contain at least one letter or digit, and at most 64 words and 1024 characters.'}, 'limit': {'type': 'integer', 'default': 10, 'maximum': 50, 'minimum': 1, 'description': 'Maximum LEI candidates to return in one page.'}, 'offset': {'type': 'integer', 'default': 0, 'maximum': 9007199254740991, 'minimum': 0, 'description': 'Zero-based index of the first LEI candidate to return. Re-call with the returned nextOffset to page through every candidate when hasMore is true; an offset past the end returns an empty page, not an error.'}, 'status': {'enum': ['any', 'issued', 'lapsed'], 'type': 'string', 'default': 'issued', 'description': "Registration status filter. issued (default) matches ISSUED; lapsed matches exactly LAPSED; any applies no filter and is the only value that reaches the other states (RETIRED, DUPLICATE, ANNULLED, PENDING_TRANSFER, PENDING_ARCHIVAL, MERGED) â\x80\x94 each candidate's status field names its state."}, 'minScore': {'type': 'number', 'maximum': 1, 'minimum': 0, 'description': "Jaro-Winkler floor for fuzzy hits (0â\x80\x931); defaults to the server's configured floor."}, 'matchMode': {'enum': ['strict', 'fuzzy'], 'type': 'string', 'default': 'strict', 'description': 'strict (default): exact then all-tokens-present. fuzzy: also scored Jaro-Winkler.'}, 'jurisdiction': {'anyOf': [{'type': 'string', 'const': ''}, {'type': 'string', 'pattern': '^[A-Za-z]{2}(-[A-Za-z0-9]{1,3})?$', 'description': 'ISO 3166-1 alpha-2 country code (e.g. US) or ISO 3166-2 subdivision code (e.g. US-DE), case-insensitive.'}], 'description': 'Optional legal-jurisdiction filter. A country code ("US") matches that country and every subdivision under it (US-DE, US-CA); a subdivision code ("US-DE") matches exactly. Case-insensitive. Empty string disables it.'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'anyOf': [{'not': {'required': ['error']}, 'required': ['matches', 'normalizedQuery', 'matchModeUsed', 'totalCount', 'totalAvailable', 'totalAvailableBasis', 'hasMore']}, {'required': ['error']}], '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'error': {'type': 'object', 'required': ['code', 'message'], 'properties': {'code': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'JSON-RPC error code for this failure.'}, 'data': {'type': 'object', 'properties': {'reason': {'type': 'string', 'examples': ['name_not_searchable', 'name_too_long', 'mirror_not_ready'], 'description': 'Machine-readable failure mode. Declared by this tool: `name_not_searchable`: The name contains no letter or digit, so nothing in it can be matched. `name_too_long`: The name is longer than 64 words or 1024 characters. `mirror_not_ready`: The GLEIF (LEI) mirror has never completed an initial sync. Other values are possible when a failure originates below the handler.'}, 'recovery': {'type': 'object', 'required': ['hint'], 'properties': {'hint': {'type': 'string'}}, 'description': 'Actionable next step for the caller.', 'additionalProperties': {}}, 'retryable': {'type': 'boolean', 'description': 'Whether retrying may succeed.'}}, 'additionalProperties': {}}, 'message': {'type': 'string', 'description': 'Human-readable description of what went wrong.'}}, 'description': 'Present when the call failed. Absent on success.', 'additionalProperties': {}}, 'notice': {'type': 'string', 'description': "Guidance when no LEI matched and how to broaden, when the requested offset sits past the end of the result set, when a bound cut the candidate set and how to narrow the name, or when the mirror has not indexed GLEIF's other and transliterated names yet, so only legal names were searched."}, 'hasMore': {'type': 'boolean', 'description': 'True when the result set holds candidates beyond this page â\x80\x94 re-call with nextOffset. It describes pages only: false on the last page, whatever totalAvailableBasis says.'}, 'matches': {'type': 'array', 'items': {'type': 'object', 'required': ['lei', 'legalName', 'matchedName', 'matchedNameType', 'matchType'], 'properties': {'lei': {'type': 'string', 'description': '20-character GLEIF Legal Entity Identifier.'}, 'score': {'type': 'number', 'description': 'Raw Jaro-Winkler similarity (0â\x80\x931) for approximate hits only â\x80\x94 a real measurement.'}, 'status': {'type': 'string', 'description': 'Registration status (e.g. ISSUED, LAPSED).'}, 'legalName': {'type': 'string', 'description': 'Registered legal name of the entity.'}, 'matchType': {'enum': ['exact', 'strong', 'approximate'], 'type': 'string', 'description': 'exact = normalized equality; strong = all tokens present; approximate = fuzzy.'}, 'matchedName': {'type': 'string', 'description': 'The name that matched the query â\x80\x94 the legal name or one of the other or transliterated names GLEIF publishes for the entity.'}, 'jurisdiction': {'type': 'string', 'description': 'Legal jurisdiction (ISO code), when published.'}, 'matchedNameType': {'type': 'string', 'description': "Type of matchedName: LEGAL_NAME, PREVIOUS_LEGAL_NAME (a former legal name, not the current one), TRADING_OR_OPERATING_NAME, ALTERNATIVE_LANGUAGE_LEGAL_NAME, PREFERRED_ASCII_TRANSLITERATED_LEGAL_NAME, AUTO_ASCII_TRANSLITERATED_LEGAL_NAME, or UNKNOWN for a name the mirror stored without GLEIF's type."}, 'queryTokenCoverage': {'type': 'object', 'required': ['covered', 'total'], 'properties': {'total': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'Total tokens in the normalized query.'}, 'covered': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': "Query tokens individually matched by one of the matched name's tokens at the applied score floor."}}, 'description': 'How much of the query the matched name explains, as a literal token count â\x80\x94 a second real measurement, never folded into score. It is the tie-break applied after score, because one shared exact token pins several candidates at the same score. Absent for exact/strong matches.', 'additionalProperties': False}}, 'description': 'One LEI candidate â\x80\x94 confirm against the GLEIF record before relying on it.', 'additionalProperties': False}, 'description': 'LEI candidates, ranked by match type, then score, then how much of the query each matched name explains.'}, 'nextOffset': {'type': 'number', 'description': 'The offset to request next. Present only when hasMore is true.'}, 'totalCount': {'type': 'number', 'description': 'Number of LEI candidates returned in this page.'}, 'matchModeUsed': {'type': 'string', 'description': 'The match mode actually applied (strict may upgrade to fuzzy).'}, 'totalAvailable': {'type': 'number', 'description': 'LEI candidates in the result set across all pages, before limit and offset were applied â\x80\x94 every one is reachable by paging.'}, 'normalizedQuery': {'type': 'string', 'description': 'The name as the server folded it for matching.'}, 'totalAvailableBasis': {'enum': ['exact', 'lower_bound'], 'type': 'string', 'description': 'How to read totalAvailable: exact = the complete strict candidate set; lower_bound = a fuzzy pass ran, which scores only the candidates blocking pooled, or the strict scan stopped at its 2,000-name bound, so more candidates may exist beyond the result set.'}}, 'additionalProperties': False}
sanctions_screen_identifier
sanctions-screening-mcp-server: screen identifier
Look up an identifier — a vessel IMO number, a SWIFT/BIC code, a digital-currency wallet address, a passport or national ID number, or any other identifier a list publishes — against all loaded sanctions watchlists at once: OFAC SDN + Consolidated, EU, UK, and UN. Exact match after normalization, with no fuzzy or partial matching and no score: spacing, letter case, and the separators - . / are ignored, an IMO number matches with or without its IMO prefix, a SWIFT/BIC code compares on its first eight characters so a branch code matches its institution, and a wallet address folds case only where its encoding is case-insensitive (hex, bech32, cashaddr — never base58). Returns every designation that publishes a matching identifier, one per designation — an OFAC party both OFAC lists publish under one entry ID is one hit, its sources naming both lists — with the identifiers that matched as published; sanctions_get_designation pulls the full record. This is a screening AID for a human/compliance review, NOT a compliance determination: a hit means "review this candidate against the official source," and an empty result never means "cleared" — an identifier a list prints only in free-text remarks, or bundled with other numbers in one field, does not match.
Read only Idempotent
Input schema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['value'], 'properties': {'type': {'enum': ['any', 'imo', 'swift_bic', 'digital_currency_address', 'passport', 'national_id'], 'type': 'string', 'default': 'any', 'description': 'Restrict to one identifier category, matched on the label each list publishes, or "any" (default) to search every published identifier, including categories with no name here (MMSI, call signs, tail numbers, tax and registration numbers, email, websites).'}, 'value': {'type': 'string', 'minLength': 1, 'description': 'The identifier to look up, as you hold it (e.g. "IMO 7406784", "DCBKKPPY", a wallet address, a passport number). Must contain at least one character other than whitespace and - . /'}, 'sources': {'type': 'array', 'items': {'enum': ['ofac_sdn', 'ofac_consolidated', 'eu', 'uk', 'un'], 'type': 'string'}, 'description': 'Restrict to specific source lists. Omit to search all loaded lists.'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'anyOf': [{'not': {'required': ['error']}, 'required': ['hits', 'caveat', 'totalCount']}, {'required': ['error']}], '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'hits': {'type': 'array', 'items': {'type': 'object', 'required': ['source', 'sourceLabel', 'sourceEntryId', 'sources', 'primaryName', 'entityType', 'matchedIdentifiers'], 'properties': {'source': {'enum': ['ofac_sdn', 'ofac_consolidated', 'eu', 'uk', 'un'], 'type': 'string', 'description': "The watchlist whose record this hit's fields come from â\x80\x94 its provenance. For an OFAC party both OFAC lists publish, ofac_sdn unless the Consolidated record matched alone; sources names every list."}, 'program': {'type': 'string', 'description': 'Sanctioning program / regime, when published by the source.'}, 'sources': {'type': 'array', 'items': {'enum': ['ofac_sdn', 'ofac_consolidated', 'eu', 'uk', 'un'], 'type': 'string'}, 'description': 'Every screened list this candidate is on, in list order: one list, or ofac_sdn and ofac_consolidated together for an OFAC party both OFAC lists publish under one entry ID â\x80\x94 one hit, not two. Read this, not source, for every list; the entry ID resolves in sanctions_get_designation under each.'}, 'entityType': {'enum': ['person', 'organization', 'vessel', 'aircraft', 'unknown'], 'type': 'string', 'description': 'Entity classification as published by the source.'}, 'primaryName': {'type': 'string', 'description': 'Primary published name of the designated entity.'}, 'sourceLabel': {'type': 'string', 'description': 'Human-readable name of the source list.'}, 'sourceEntryId': {'type': 'string', 'description': "The list's own entry ID â\x80\x94 pass to sanctions_get_designation for the full record."}, 'matchedIdentifiers': {'type': 'array', 'items': {'type': 'object', 'required': ['type', 'value'], 'properties': {'type': {'type': 'string', 'description': 'Identifier label as the list publishes it (e.g. Vessel Registration Identification, IMO Number, SWIFT BIC, Digital Currency Address - ETH, Passport).'}, 'value': {'type': 'string', 'description': 'Identifier value exactly as published, letter case included.'}, 'country': {'type': 'string', 'description': 'Issuing country/authority, when published.'}}, 'description': 'One published identifier that matched the lookup.', 'additionalProperties': False}, 'description': 'Every identifier this designation publishes that matched, as published â\x80\x94 several when the list prints one number more than one way.'}}, 'description': 'One designation that publishes a matching identifier â\x80\x94 a candidate to verify.', 'additionalProperties': False}, 'description': 'Designations that publish a matching identifier, one per designation (an OFAC party on both OFAC lists once), ordered by source list then entry ID. Not paged â\x80\x94 the most widely shared published identifiers map to about a dozen designations.'}, 'error': {'type': 'object', 'required': ['code', 'message'], 'properties': {'code': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'JSON-RPC error code for this failure.'}, 'data': {'type': 'object', 'properties': {'reason': {'type': 'string', 'examples': ['identifier_not_searchable', 'mirror_not_ready'], 'description': 'Machine-readable failure mode. Declared by this tool: `identifier_not_searchable`: The value is left with nothing to compare once whitespace and the separators - . / are removed (or, for type imo, a bare IMO prefix). `mirror_not_ready`: The sanctions mirror has never completed an initial sync. Other values are possible when a failure originates below the handler.'}, 'recovery': {'type': 'object', 'required': ['hint'], 'properties': {'hint': {'type': 'string'}}, 'description': 'Actionable next step for the caller.', 'additionalProperties': {}}, 'retryable': {'type': 'boolean', 'description': 'Whether retrying may succeed.'}}, 'additionalProperties': {}}, 'message': {'type': 'string', 'description': 'Human-readable description of what went wrong.'}}, 'description': 'Present when the call failed. Absent on success.', 'additionalProperties': {}}, 'caveat': {'type': 'string', 'description': 'Decision-support caveat â\x80\x94 this is a screening aid, not a compliance determination.'}, 'notice': {'type': 'string', 'description': 'Guidance when no designation matched â\x80\x94 what to try next, and what an empty result does NOT mean.'}, 'totalCount': {'type': 'number', 'description': 'Number of designations returned.'}}, 'additionalProperties': False}
sanctions_screen_name
sanctions-screening-mcp-server: screen name
Screen a name (person, company, vessel, aircraft) against all loaded sanctions watchlists at once — OFAC SDN + Consolidated, EU, UK, and UN — alias- and fuzzy-aware. Returns scored potential matches with the source list, sanctioning program, designation date, and the matched alias; an OFAC party both OFAC lists publish under one entry ID is one hit, its sources naming both lists. Strict mode (default) matches exact-normalized then all-tokens-present, then runs a fuzzy pass over each selected list strict finds nothing on: a full pass when strict finds nothing on any list, otherwise one that adds only candidates covering every word of the name other than legal forms, articles and other function words, and the jurisdiction codes uk, usa, uae, and rf, ranked after the strict hits. Fuzzy mode runs the fuzzy pass over every selected list. It adds Jaro-Winkler and phonetic matching and labels hits approximate with a raw 0–1 similarity score plus the count of query tokens the candidate covers, which orders candidates that tie on score; fuzzySources names the lists it searched. Results are paged: totalAvailable and hasMore report matches beyond the returned page, and nextOffset retrieves them. This is a screening AID for a human/compliance review, NOT a compliance determination: a hit means "review this candidate against the official source," and an empty result never means "cleared."
Read only Idempotent
Input schema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['name'], 'properties': {'name': {'type': 'string', 'minLength': 1, 'description': 'The name to screen (person, organization, vessel, or aircraft), in any script. It must contain at least one letter or digit, and at most 64 words and 1024 characters.'}, 'limit': {'type': 'integer', 'default': 25, 'maximum': 100, 'minimum': 1, 'description': 'Maximum number of potential matches to return in one page.'}, 'offset': {'type': 'integer', 'default': 0, 'maximum': 9007199254740991, 'minimum': 0, 'description': 'Zero-based index of the first potential match to return. Re-call with the returned nextOffset to page through every match when hasMore is true; an offset past the end returns an empty page, not an error.'}, 'sources': {'type': 'array', 'items': {'enum': ['ofac_sdn', 'ofac_consolidated', 'eu', 'uk', 'un'], 'type': 'string'}, 'description': 'Restrict to specific source lists. Omit to screen all loaded lists.'}, 'minScore': {'type': 'number', 'maximum': 1, 'minimum': 0, 'description': "Score floor for approximate hits (0â\x80\x931), applied uniformly to every fuzzy candidate regardless of how it was matched (Jaro-Winkler, token, or phonetic); a query token counts toward queryTokenCoverage only when its match clears it too. It governs every fuzzy pass: fuzzy mode, and in strict mode the pass over the lists strict found nothing on, so raising it can remove approximate hits from a strict screen as well. Exact and strong hits are unaffected. Defaults to the server's configured floor."}, 'matchMode': {'enum': ['strict', 'fuzzy'], 'type': 'string', 'default': 'strict', 'description': 'strict (default): exact-normalized then all-tokens-present, then a fuzzy pass over each selected list strict finds nothing on â\x80\x94 a full pass when strict finds nothing on any list, otherwise adding only candidates that cover every word of the name other than legal forms, articles and other function words, and the jurisdiction codes uk, usa, uae, and rf. fuzzy: a scored Jaro-Winkler + phonetic pass over every selected list.'}, 'entityType': {'enum': ['any', 'person', 'organization', 'vessel', 'aircraft'], 'type': 'string', 'default': 'any', 'description': 'Restrict to one entity class, or "any" (default) to screen across all.'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'anyOf': [{'not': {'required': ['error']}, 'required': ['hits', 'caveat', 'normalizedQuery', 'matchModeUsed', 'totalCount', 'totalAvailable', 'totalAvailableBasis', 'hasMore']}, {'required': ['error']}], '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'hits': {'type': 'array', 'items': {'type': 'object', 'required': ['source', 'sourceLabel', 'sourceEntryId', 'sources', 'entityType', 'primaryName', 'matchedName', 'matchedNameType', 'matchType'], 'properties': {'score': {'type': 'number', 'description': 'Raw Jaro-Winkler similarity (0â\x80\x931) for approximate hits only â\x80\x94 a real measurement, not a confidence verdict. Absent for exact/strong hits.'}, 'source': {'enum': ['ofac_sdn', 'ofac_consolidated', 'eu', 'uk', 'un'], 'type': 'string', 'description': "The watchlist whose record this hit's fields come from â\x80\x94 its provenance. For an OFAC party both OFAC lists publish, ofac_sdn unless the Consolidated record matched alone or better; sources names every list."}, 'program': {'type': 'string', 'description': 'Sanctioning program / regime, when published by the source.'}, 'sources': {'type': 'array', 'items': {'enum': ['ofac_sdn', 'ofac_consolidated', 'eu', 'uk', 'un'], 'type': 'string'}, 'description': 'Every screened list this candidate is on, in list order: one list, or ofac_sdn and ofac_consolidated together for an OFAC party both OFAC lists publish under one entry ID â\x80\x94 one hit, not two. Read this, not source, for every list; the entry ID resolves in sanctions_get_designation under each.'}, 'matchType': {'enum': ['exact', 'strong', 'approximate'], 'type': 'string', 'description': 'exact = normalized name equality; strong = all query tokens present; approximate = fuzzy/phonetic.'}, 'entityType': {'enum': ['person', 'organization', 'vessel', 'aircraft', 'unknown'], 'type': 'string', 'description': 'Entity classification as published by the source.'}, 'matchedName': {'type': 'string', 'description': 'The specific name or alias string that matched the query.'}, 'primaryName': {'type': 'string', 'description': 'Primary published name of the designated entity.'}, 'sourceLabel': {'type': 'string', 'description': 'Human-readable name of the source list.'}, 'sourceEntryId': {'type': 'string', 'description': "The list's own entry ID â\x80\x94 pass to sanctions_get_designation for the full record."}, 'designationDate': {'type': 'string', 'description': "The source's own designation date as YYYY-MM-DD; absent when unpublished. For an OFAC party both OFAC lists publish, the date of the source record: each OFAC file dates the party from its own lists, so the two often differ, and sanctions_get_designation under the other list returns that record's date."}, 'matchedNameType': {'enum': ['primary', 'aka', 'fka', 'low-quality-aka'], 'type': 'string', 'description': 'Provenance of the matched name: primary, a.k.a., f.k.a., or a low-quality a.k.a.'}, 'referenceNumber': {'type': 'string', 'description': "The list's published reference number (UN, EU, UK OFSI Group ID); absent when the list publishes none for the entry."}, 'queryTokenCoverage': {'type': 'object', 'required': ['covered', 'total'], 'properties': {'total': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'Total tokens in the normalized query.'}, 'covered': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': "Query tokens individually matched by one of this candidate's tokens at the applied score floor."}}, 'description': 'How much of the query this candidate explains, as a literal token count â\x80\x94 a second real measurement, never folded into score. It is the tie-break applied after score, because one shared exact token pins several candidates at the same score. Absent for exact/strong hits.', 'additionalProperties': False}}, 'description': 'One potential match â\x80\x94 a candidate to verify, never a determination.', 'additionalProperties': False}, 'description': 'Potential matches, ranked by match type, then score, then how much of the query each candidate explains. Candidates tied on all three are ordered by source list, then entry ID â\x80\x94 not by relevance.'}, 'error': {'type': 'object', 'required': ['code', 'message'], 'properties': {'code': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'JSON-RPC error code for this failure.'}, 'data': {'type': 'object', 'properties': {'reason': {'type': 'string', 'examples': ['name_not_searchable', 'name_too_long', 'mirror_not_ready'], 'description': 'Machine-readable failure mode. Declared by this tool: `name_not_searchable`: The name contains no letter or digit, so nothing in it can be matched. `name_too_long`: The name is longer than 64 words or 1024 characters. `mirror_not_ready`: The sanctions mirror has never completed an initial sync. Other values are possible when a failure originates below the handler.'}, 'recovery': {'type': 'object', 'required': ['hint'], 'properties': {'hint': {'type': 'string'}}, 'description': 'Actionable next step for the caller.', 'additionalProperties': {}}, 'retryable': {'type': 'boolean', 'description': 'Whether retrying may succeed.'}}, 'additionalProperties': {}}, 'message': {'type': 'string', 'description': 'Human-readable description of what went wrong.'}}, 'description': 'Present when the call failed. Absent on success.', 'additionalProperties': {}}, 'caveat': {'type': 'string', 'description': 'Decision-support caveat â\x80\x94 this is a screening aid, not a compliance determination.'}, 'notice': {'type': 'string', 'description': 'Guidance when no candidate matched â\x80\x94 how to broaden, and what an empty result does NOT mean â\x80\x94 when the requested offset sits past the end of the result set, or when the fuzzy pass reached its candidate bound and a more distinctive word would narrow it.'}, 'hasMore': {'type': 'boolean', 'description': 'True when the result set holds matches beyond this page â\x80\x94 re-call with nextOffset. It describes pages only: false on the last page, whatever totalAvailableBasis says.'}, 'nextOffset': {'type': 'number', 'description': 'The offset to request next. Present only when hasMore is true.'}, 'totalCount': {'type': 'number', 'description': 'Number of potential matches returned in this page.'}, 'fuzzySources': {'type': 'array', 'items': {'enum': ['ofac_sdn', 'ofac_consolidated', 'eu', 'uk', 'un'], 'type': 'string'}, 'description': 'The selected lists the fuzzy pass searched, in list order; absent when no fuzzy pass ran. Beside strict hits these are the lists strict found nothing on, and only their candidates covering every word of the name other than legal forms, articles and other function words, and the jurisdiction codes uk, usa, uae, and rf were added.'}, 'matchModeUsed': {'type': 'string', 'description': 'fuzzy when every selected list was fuzzy-searched (fuzzy mode, or a strict screen that found nothing on any list); strict otherwise, including a strict screen whose strict-empty lists were completed by a fuzzy pass.'}, 'totalAvailable': {'type': 'number', 'description': 'Potential matches in the result set across all pages, before limit and offset were applied â\x80\x94 every one is reachable by paging. An OFAC party both OFAC lists publish counts once.'}, 'normalizedQuery': {'type': 'string', 'description': 'The name as the server folded it for matching.'}, 'totalAvailableBasis': {'enum': ['exact', 'lower_bound'], 'type': 'string', 'description': 'How to read totalAvailable: exact = the complete strict match set, strict having found a match on every selected list; lower_bound = a fuzzy pass ran (fuzzySources is present), which scores only the candidates blocking pooled, so more matches may exist beyond the result set.'}}, 'additionalProperties': False}
sanctions_trace_ownership
sanctions-screening-mcp-server: trace ownership
Trace the GLEIF Level 2 corporate-ownership graph for an LEI: direct and ultimate parents and/or children, traversed breadth-first to a bounded depth, with relationship type for each edge. Direction both walks up to the parents and down to the children from the root, never sideways into siblings or co-parents. An ultimate-parent edge is a shortcut to the top of the group, not a hop: a node only it reaches within the depth is returned as a leaf flagged reachedVia: ultimate. Set screenNodes to also cross-reference every entity in the graph against all loaded watchlists — resolving "is anyone in this ownership chain sanctioned." Each node is cross-referenced as sanctions_get_entity does it: its legal name and every other and transliterated name screened strict (exact, then all tokens present — never fuzzy), and its LEI and registration number looked up as exact non-document identifiers, the registration number matching only an identifier published for the country of its legal jurisdiction; hits merge to one per designation, an OFAC party both OFAC lists publish to one hit whose sources names both, matchedOn naming every input that produced each. A node with no Level 1 record (missingEntityLeis) has no names, so it is looked up by its LEI alone. Each per-node screen is a screening AID: hits are candidates to verify, and an empty result for a node is not a clearance of that node. Each node whose parents were walked carries parentStatus for its direct and ultimate parent: a published relationship, a reporting exception with the reasons the entity gave (such as NATURAL_PERSONS or NON_CONSOLIDATING), none, or unknown when reporting exceptions are not loaded. The response says what it could not do: complete/truncated/missingEntityLeis report whether the loaded relationship graph within the depth is fully shown, screeningStatus reports whether the cross-reference actually ran, and each screened node reports whether its own hit list was capped. Requires a valid 20-character LEI (use sanctions_resolve_entity to obtain one).
Read only Idempotent
Input schema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['lei'], 'properties': {'lei': {'type': 'string', 'pattern': '^[A-Z0-9]{18}[0-9]{2}$', 'description': 'The 20-character GLEIF LEI at the root of the ownership graph.'}, 'depth': {'type': 'integer', 'default': 3, 'maximum': 5, 'minimum': 1, 'description': 'Maximum traversal depth from the root entity (1â\x80\x935), on each side of a both walk. Ultimate-parent edges do not count as hops.'}, 'direction': {'enum': ['parents', 'children', 'both'], 'type': 'string', 'default': 'both', 'description': 'Walk parents (who owns it), children (what it owns), or both (default): a parents walk plus a children walk from the root, each to depth, never into siblings or co-parents.'}, 'screenNodes': {'type': 'boolean', 'default': False, 'description': "When true, cross-reference every node against all watchlists â\x80\x94 the ownership-chain cross-reference: the node's legal, other, and transliterated names screened strict, and its LEI and country-matched registration number looked up as identifiers. A node with no Level 1 record has no names: its LEI lookup alone."}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'anyOf': [{'not': {'required': ['error']}, 'required': ['rootLei', 'nodes', 'edges', 'complete', 'truncated', 'reportingExceptionsLoaded', 'missingEntityLeis', 'screeningStatus', 'screenedNodeCount', 'flaggedNodeCount', 'caveat']}, {'required': ['error']}], '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'edges': {'type': 'array', 'items': {'type': 'object', 'required': ['childLei', 'parentLei', 'relationshipType'], 'properties': {'childLei': {'type': 'string', 'description': 'LEI of the owned (child) entity.'}, 'parentLei': {'type': 'string', 'description': 'LEI of the owning (parent) entity.'}, 'relationshipType': {'type': 'string', 'description': 'GLEIF relationship type (e.g. IS_DIRECTLY_CONSOLIDATED_BY).'}, 'relationshipStatus': {'type': 'string', 'description': 'Relationship status, when published.'}}, 'description': 'One directed ownership edge (child is consolidated by parent).', 'additionalProperties': False}, 'description': 'Directed ownership edges between the nodes â\x80\x94 every edge joins two nodes of this graph.'}, 'error': {'type': 'object', 'required': ['code', 'message'], 'properties': {'code': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'JSON-RPC error code for this failure.'}, 'data': {'type': 'object', 'properties': {'reason': {'type': 'string', 'examples': ['lei_not_found', 'invalid_lei_checksum', 'mirror_not_ready'], 'description': 'Machine-readable failure mode. Declared by this tool: `lei_not_found`: No GLEIF entity in the mirror carries the root LEI, and its check digits are valid. `invalid_lei_checksum`: No GLEIF entity in the mirror carries the root LEI, and its ISO 17442 check digits fail. `mirror_not_ready`: The GLEIF (LEI) mirror has never completed an initial sync. Other values are possible when a failure originates below the handler.'}, 'recovery': {'type': 'object', 'required': ['hint'], 'properties': {'hint': {'type': 'string'}}, 'description': 'Actionable next step for the caller.', 'additionalProperties': {}}, 'retryable': {'type': 'boolean', 'description': 'Whether retrying may succeed.'}}, 'additionalProperties': {}}, 'message': {'type': 'string', 'description': 'Human-readable description of what went wrong.'}}, 'description': 'Present when the call failed. Absent on success.', 'additionalProperties': {}}, 'nodes': {'type': 'array', 'items': {'type': 'object', 'required': ['lei', 'legalName', 'depth', 'role'], 'properties': {'lei': {'type': 'string', 'description': "The node's LEI."}, 'role': {'enum': ['root', 'parent', 'child'], 'type': 'string', 'description': 'root = the traced entity; parent = an ancestor, reached by walking parents; child = a descendant, reached by walking children. On a both walk, the side that reached the node â\x80\x94 siblings and co-parents are never walked.'}, 'depth': {'type': 'number', 'description': 'Breadth-first depth from the root (root = 0), counted over every relationship type except IS_ULTIMATELY_CONSOLIDATED_BY. On a node flagged reachedVia: ultimate it counts that one ultimate hop instead, so it can be shallower than the direct chain to the node.'}, 'status': {'type': 'string', 'description': 'GLEIF registration status, when known.'}, 'legalName': {'type': 'string', 'description': "The node's legal name (the LEI itself if not hydrated)."}, 'reachedVia': {'enum': ['ultimate'], 'type': 'string', 'description': 'Present (ultimate) when only an IS_ULTIMATELY_CONSOLIDATED_BY edge reaches this node within the depth. That edge is a shortcut to the top of the group, not a hop, so the node is a leaf: its own parents (on the parents side) or children (on the children side) are never walked, and truncated is true when any of them is not in this graph. A higher depth places it by direct links only when a direct chain from the root reaches it; where that chain is broken (a parent reported by exception, or not at all), no depth does.'}, 'jurisdiction': {'type': 'string', 'description': 'Jurisdiction (ISO code), when known.'}, 'parentStatus': {'type': 'object', 'required': ['direct', 'ultimate'], 'properties': {'direct': {'type': 'object', 'required': ['status'], 'properties': {'status': {'enum': ['relationship', 'exception', 'none', 'unknown'], 'type': 'string', 'description': "relationship = a Level 2 relationship at this level is published â\x80\x94 it is in edges when that parent is also a node of this graph (a flagged leaf's parents and a children-side node's other parents are read for this status, never walked); exception = the entity filed a GLEIF reporting exception instead of naming this parent; none = GLEIF publishes neither; unknown = no relationship is published and reporting exceptions are not loaded in the mirror, so whether one was filed is unknown."}, 'exceptionReasons': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Every reason given in the reporting exception (e.g. NATURAL_PERSONS, NON_CONSOLIDATING, NO_KNOWN_PERSON). Present only when status is exception.'}}, 'description': 'What GLEIF publishes about the direct parent.', 'additionalProperties': False}, 'ultimate': {'type': 'object', 'required': ['status'], 'properties': {'status': {'enum': ['relationship', 'exception', 'none', 'unknown'], 'type': 'string', 'description': "relationship = a Level 2 relationship at this level is published â\x80\x94 it is in edges when that parent is also a node of this graph (a flagged leaf's parents and a children-side node's other parents are read for this status, never walked); exception = the entity filed a GLEIF reporting exception instead of naming this parent; none = GLEIF publishes neither; unknown = no relationship is published and reporting exceptions are not loaded in the mirror, so whether one was filed is unknown."}, 'exceptionReasons': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Every reason given in the reporting exception (e.g. NATURAL_PERSONS, NON_CONSOLIDATING, NO_KNOWN_PERSON). Present only when status is exception.'}}, 'description': 'What GLEIF publishes about the ultimate parent.', 'additionalProperties': False}}, 'description': "What GLEIF publishes about this node's direct and ultimate accounting-consolidation parents. Present only on nodes whose parents the traversal read â\x80\x94 every node short of the depth limit when direction is parents or both; absent on a children walk.", 'additionalProperties': False}, 'sanctionsHits': {'type': 'array', 'items': {'type': 'object', 'required': ['source', 'sourceLabel', 'sourceEntryId', 'sources', 'primaryName', 'matchedOn'], 'properties': {'score': {'type': 'number', 'description': 'Never set by this cross-reference: only an approximate (fuzzy) match carries a raw Jaro-Winkler score, and the cross-reference screens strict.'}, 'source': {'enum': ['ofac_sdn', 'ofac_consolidated', 'eu', 'uk', 'un'], 'type': 'string', 'description': 'Watchlist whose record this hit is attributed to: primaryName comes from it. For an OFAC party both OFAC lists publish, ofac_sdn unless the Consolidated record matched alone or better, and matchedName, matchedIdentifiers, and matchedOn cover what either record matched; sources names every list.'}, 'sources': {'type': 'array', 'items': {'enum': ['ofac_sdn', 'ofac_consolidated', 'eu', 'uk', 'un'], 'type': 'string'}, 'description': 'Every screened list this candidate is on, in list order: one list, or ofac_sdn and ofac_consolidated together for an OFAC party both OFAC lists publish under one entry ID â\x80\x94 one hit, not two. Read this, not source, for every list; the entry ID resolves in sanctions_get_designation under each.'}, 'matchType': {'enum': ['exact', 'strong', 'approximate'], 'type': 'string', 'description': 'Match classification of matchedName: exact or strong, never approximate (the cross-reference screens strict, never fuzzy). Absent when only an identifier produced the hit.'}, 'matchedOn': {'type': 'array', 'items': {'type': 'object', 'required': ['input', 'value'], 'properties': {'input': {'enum': ['legal_name', 'other_name', 'lei', 'registration_number'], 'type': 'string', 'description': 'Which value: legal_name, or other_name (an other or transliterated name), each screened as a name, strict; lei, or registration_number (the ID at the registration authority), each looked up as a non-document identifier.'}, 'value': {'type': 'string', 'description': 'The value as GLEIF publishes it.'}, 'nameType': {'type': 'string', 'description': "GLEIF's type for an other_name (e.g. TRADING_OR_OPERATING_NAME, AUTO_ASCII_TRANSLITERATED_LEGAL_NAME), or UNKNOWN for a name the mirror stored without one. Present on other_name only."}}, 'description': 'One value of the entity the cross-reference screened.', 'additionalProperties': False}, 'description': 'Every input of this node that produced the hit â\x80\x94 its legal name, an other or transliterated name, its LEI, or its registration number â\x80\x94 in screening order. Only its LEI on a node in missingEntityLeis.'}, 'matchedName': {'type': 'string', 'description': "The designation's name or alias that matched one of this node's screened names â\x80\x94 the strongest match. Absent when only an identifier produced the hit."}, 'primaryName': {'type': 'string', 'description': 'Primary published name of the designation.'}, 'sourceLabel': {'type': 'string', 'description': 'Human-readable source list name.'}, 'sourceEntryId': {'type': 'string', 'description': 'Source entry ID â\x80\x94 pass to sanctions_get_designation.'}, 'matchedIdentifiers': {'type': 'array', 'items': {'type': 'object', 'required': ['type', 'value'], 'properties': {'type': {'type': 'string', 'description': 'Identifier label as the list publishes it (e.g. Legal Entity Number, Registration Number).'}, 'value': {'type': 'string', 'description': 'The identifier value, as published.'}, 'country': {'type': 'string', 'description': 'Issuing country as published, when published.'}}, 'description': "An identifier the designation publishes that equals the entity's LEI, or its registration number published for the country of its legal jurisdiction.", 'additionalProperties': False}, 'description': "Every identifier the designation publishes that equals this node's LEI or its country-matched registration number, as published. Present only when an identifier produced the hit."}}, 'description': 'A potential watchlist match on this node â\x80\x94 verify, do not assume.', 'additionalProperties': False}, 'description': 'Per-node cross-reference results, one hit per designation (an OFAC party both OFAC lists publish once) â\x80\x94 exact name and identifier matches first, then strong name matches. Present only when screenNodes is true.'}, 'sanctionsScreen': {'type': 'object', 'required': ['totalAvailable', 'totalAvailableBasis', 'hasMore', 'screenedInputs'], 'properties': {'hasMore': {'type': 'boolean', 'description': "True when this node's potential matches were capped â\x80\x94 re-screen its names with sanctions_screen_name and look up its LEI and registration number with sanctions_screen_identifier to see the rest. A node in missingEntityLeis has no names: look up its LEI."}, 'screenedInputs': {'type': 'array', 'items': {'type': 'object', 'required': ['input', 'value'], 'properties': {'input': {'enum': ['legal_name', 'other_name', 'lei', 'registration_number'], 'type': 'string', 'description': 'Which value: legal_name, or other_name (an other or transliterated name), each screened as a name, strict; lei, or registration_number (the ID at the registration authority), each looked up as a non-document identifier.'}, 'value': {'type': 'string', 'description': 'The value as GLEIF publishes it.'}, 'nameType': {'type': 'string', 'description': "GLEIF's type for an other_name (e.g. TRADING_OR_OPERATING_NAME, AUTO_ASCII_TRANSLITERATED_LEGAL_NAME), or UNKNOWN for a name the mirror stored without one. Present on other_name only."}}, 'description': 'One value of the entity the cross-reference screened.', 'additionalProperties': False}, 'description': 'What the cross-reference screened beyond the legal name and the LEI, which it screens on every node with a Level 1 record: every other and transliterated name, then the registration number when the node publishes one (a not-available placeholder such as N/A is none) and a legal jurisdiction to match it by. Empty when there is nothing beyond those two, and always on a node in missingEntityLeis, which has no name and is looked up by its LEI alone.'}, 'totalAvailable': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': "Distinct designations this node's cross-reference found across every screened name and identifier, an OFAC party both OFAC lists publish counted once, before the per-node cap was applied."}, 'totalAvailableBasis': {'enum': ['exact', 'lower_bound'], 'type': 'string', 'description': "How to read totalAvailable. Always exact here: every name is screened strict, never fuzzy, and a strict screen counts every designation it reaches, so totalAvailable is the whole set across this node's screened names and identifiers."}}, 'description': "Disclosure for this node's cross-reference: how many potential matches existed before the per-node cap, whether sanctionsHits is the complete set, and what was screened. Present only when the node was screened.", 'additionalProperties': False}}, 'description': 'One entity in the ownership graph.', 'additionalProperties': False}, 'description': 'All entities reached in the traversal, including the root.'}, 'caveat': {'type': 'string', 'description': 'Decision-support caveat â\x80\x94 node screening is an aid, not a determination.'}, 'rootLei': {'type': 'string', 'description': 'The LEI the traversal started from.'}, 'complete': {'type': 'boolean', 'description': "True when truncated is false (no loaded relationship on the walked side is left out) AND every node resolved to a GLEIF Level 1 record. It does not say every parent is known â\x80\x94 most entities publish no parent relationship; read each node's parentStatus for what GLEIF publishes instead. False means the graph below is a partial view â\x80\x94 read truncated and missingEntityLeis for which."}, 'truncated': {'type': 'boolean', 'description': 'True when the loaded relationships hold ownership links on the walked side that this graph does not show: past the requested depth (re-run with a higher depth to see them), or the parents (or, on the children side, children) of a node flagged reachedVia: ultimate, which is never walked. An ultimate-parent edge counts only when it leads to an entity this graph does not return. False means neither: every chain the walk followed ends within the depth. Siblings and co-parents are never walked and never count.'}, 'screeningStatus': {'enum': ['screened', 'not_requested', 'not_ready'], 'type': 'string', 'description': 'Whether the per-node cross-reference ran: screened = every node was screened; not_requested = screenNodes was false; not_ready = screening was requested but the sanctions mirror has never synced, so NO node was screened and the absence of hits says nothing about any node.'}, 'flaggedNodeCount': {'type': 'number', 'description': 'How many screened nodes had at least one potential watchlist match.'}, 'missingEntityLeis': {'type': 'array', 'items': {'type': 'string'}, 'description': 'LEIs published in the relationship corpus but absent from the GLEIF Level 1 entity mirror. Their nodes carry the LEI in place of a legal name and no jurisdiction/status â\x80\x94 never read that LEI as a legal name. A per-node screen for them is the LEI looked up as an identifier, nothing else: with no record there is no legal name, other name, or registration number to screen, so their screenedInputs is empty and each hit is matchedOn their lei.'}, 'screenedNodeCount': {'type': 'number', 'description': 'How many nodes were screened (0 when screenNodes is false).'}, 'reportingExceptionsLoaded': {'type': 'boolean', 'description': "Whether GLEIF reporting exceptions are loaded in the mirror. When false, a node's parent level with no published relationship reads unknown rather than exception or none."}}, 'additionalProperties': False}
Changed
sanctions_trace_ownership
Oct. 5, 2026, 2:45 a.m.
Changed
sanctions_get_entity
Oct. 5, 2026, 2:45 a.m.
Changed
sanctions_resolve_entity
Oct. 5, 2026, 2:45 a.m.
Changed
sanctions_list_sources
Oct. 5, 2026, 2:45 a.m.
Changed
sanctions_get_designation
Oct. 5, 2026, 2:45 a.m.
Changed
sanctions_screen_identifier
Oct. 5, 2026, 2:45 a.m.
Changed
sanctions_screen_name
Oct. 5, 2026, 2:45 a.m.
Changed
sanctions_trace_ownership
Sept. 27, 2026, 2:44 a.m.
Changed
sanctions_get_entity
Sept. 27, 2026, 2:44 a.m.
Changed
sanctions_resolve_entity
Sept. 27, 2026, 2:44 a.m.
Changed
sanctions_list_sources
Sept. 27, 2026, 2:44 a.m.
Changed
sanctions_get_designation
Sept. 27, 2026, 2:44 a.m.
Added
sanctions_screen_identifier
Sept. 27, 2026, 2:44 a.m.
Changed
sanctions_screen_name
Sept. 27, 2026, 2:44 a.m.
Added
sanctions_trace_ownership
Sept. 17, 2026, 12:41 p.m.
Added
sanctions_get_entity
Sept. 17, 2026, 12:41 p.m.
Added
sanctions_resolve_entity
Sept. 17, 2026, 12:41 p.m.
Added
sanctions_list_sources
Sept. 17, 2026, 12:41 p.m.
Added
sanctions_get_designation
Sept. 17, 2026, 12:41 p.m.
Added
sanctions_screen_name
Sept. 17, 2026, 12:41 p.m.