sanctions-screening-mcp-server: screen name
sanctions_screen_nameScreen a name (person, company, vessel, aircraft) against loaded sanctions and export-control watchlists — OFAC SDN + Consolidated, EU, UK, UN, and the six BIS/State CSL lists — alias- and fuzzy-aware. Check sanctions_list_sources for coverage before interpreting an empty result; zero-record CSL lists are not loaded. 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, a legal form matching any spelling of the same form (Ltd and Limited, LLC and OOO), then runs a fuzzy pass over each selected list strict finds nothing on, and over the UK and UN lists either way for a name holding a letter outside the Latin script: 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, by spelling or by sound, 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."
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"name": "<name>"
},
"name": "sanctions_screen_name"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | 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 | No | Maximum number of potential matches to return in one page. Values above 100 are clamped to 100. | |
| offset | No | 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 | No | Restrict to specific source lists. Omit to screen all loaded lists. | |
| minScore | No | Score floor for approximate hits (0–1), applied uniformly to every fuzzy candidate regardless of how it was matched (Jaro-Winkler, token, or phonetic); a query token counts toward queryTokenCoverage by spelling only when its match clears it too, and a token matched by sound counts toward coverage without admitting a candidate on its own. It governs every fuzzy pass: fuzzy mode, and in strict mode the pass that follows strict matching, 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 | No | strict (default): exact-normalized, then all-tokens-present with a legal form matching any spelling of the same form (Ltd and Limited, LLC and OOO), then a fuzzy pass over each selected list strict finds nothing on, and over the UK and UN lists either way for a name holding a letter outside the Latin script — 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, by spelling or by sound. fuzzy: a scored Jaro-Winkler + phonetic pass over every selected list. | strict |
| entityType | No | Restrict to one entity class, or "any" (default) to screen across all. A class filter excludes records whose known type differs; unknown types remain eligible. | any |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| hits | No | 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 — not by relevance. | |
| error | No | Present when the call failed. Absent on success. | |
| caveat | No | Decision-support caveat — this is a screening aid, not a compliance determination. | |
| notice | No | Guidance when no candidate matched — how to broaden, and what an empty result does NOT mean — 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. It also reports a clamped page limit. | |
| hasMore | No | True when the result set holds matches beyond this page — re-call with nextOffset. It describes pages only: false on the last page, whatever totalAvailableBasis says. | |
| nextOffset | No | The offset to request next. Present only when hasMore is true. | |
| totalCount | No | Number of potential matches returned in this page. | |
| fuzzySources | No | 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, plus the UK and UN lists for a name holding a letter outside the Latin script, 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, by spelling or by sound, were added. | |
| matchModeUsed | No | fuzzy when a full fuzzy pass searched every selected list (fuzzy mode, or a strict screen that found nothing on any list); strict otherwise, including a strict screen completed by a fuzzy pass over its strict-empty lists and, for a name holding a letter outside the Latin script, the UK and UN lists. | |
| totalAvailable | No | Potential matches in the result set across all pages, before limit and offset were applied — every one is reachable by paging. An OFAC party both OFAC lists publish counts once. | |
| normalizedQuery | No | The name as the server folded it for matching. | |
| totalAvailableBasis | No | How to read totalAvailable: exact = the complete strict match set, no fuzzy pass having run (fuzzySources is absent); 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. |