<!-- SanctionScreen llms.txt
     Status: LIVE at https://sanctionsscreen.io/llms.txt (2026-09-26). Header explains placeholder vs verified.
     Base URL VERIFIED: https://api.sanctionsscreen.io (live MCP Worker, 2026-09-26).
     PROPOSED (UNLOCKED): pricing (§6 of build spec) — charging anyone needs the user's money decision.
     VERIFIED from build-spec-2026-09-25.md §1: tool names, inputs/outputs, disposition values,
     disposition rules, fixed disclaimer text, "potential match" language rule.
     VERIFIED from matching-demo-2026-09-26.md: matching method summary.
     Data provenance: OFAC SDN ADVANCED XML Publish_Date 2026-09-23 (verified live 2026-09-26);
     UK FCDO CSV (OGL v3.0, verified in spec); EU FSD — PENDING EU Login account (not yet live);
     UN list EXCLUDED on licensing (v1 design decision).
-->
# SanctionScreen

SanctionScreen is a per-call sanctions screening API for AI agents:
company enrichment as MCP tools. No seats, no enterprise contract. Pay per call.

- Web: https://sanctionsscreen.io
- API docs: https://api.sanctionsscreen.io/docs  [PLACEHOLDER — replace with real Worker URL]
- MCP endpoint: https://api.sanctionsscreen.io/mcp  [PLACEHOLDER — replace with real Worker URL]
- Auth: API keys with `cs_live_` prefix, per-tool scopes (v1). OAuth 2.1 planned for
  Claude Connectors / ChatGPT listings.
- Pricing (PROPOSED — not yet chargeable; needs the user's money decision): Free 50 calls/mo,
  PAYG screen $0.10 / enrich $0.15 / bundle $0.20, Starter $29/mo, Growth $99/mo.

## Tools

### screen_counterparty
Screen a person or entity against sanctions lists with cited sources.

Input: `{ name (string, required), country? (ISO-3166 alpha-2), dob? (YYYY-MM-DD),
identifiers? ([{type, value}]), request_id? (idempotency), include_low_confidence? (default true) }`

Output includes: `screening_id`, `disposition` (clear | potential_match | review_advised),
`matches[]` each with `list`, `list_date`, `record_uid`, `matched_name`, `name_kind`
(primary | alias_strong | alias_weak), `confidence` (high | medium | low), `confidence_score`
(0-100), `matched_fields`, `citation` ({source, url, accessed_at}), the fixed disclaimer, `generated_at`.

Disposition rules: no matches → `clear`; ≥1 high/medium match → `potential_match`;
any high match corroborated by an identifier → `review_advised`.

Language rule: results are reported as "potential match" — never "sanctioned" or "is on a list."
Every response carries the fixed disclaimer: "Informational only — not a legal verdict.
Not a substitute for due diligence. Human review required before any adverse action."

All matches at or above the low threshold are always returned — hiding low-confidence
matches is a compliance liability. Matches sorted by confidence, descending.

Example input:
```json
{ "name": "Vladimir Putin", "country": "RU", "dob": "1952-10-07" }
```
Example output (schema):
```json
{
  "screening_id": "cs_scr_…",
  "disposition": "review_advised",
  "matches": [
    {
      "list": "OFAC_SDN",
      "list_date": "2026-09-23",
      "record_uid": "35096",
      "matched_name": "Putin Vladimir",
      "name_kind": "alias_strong",
      "confidence": "high",
      "confidence_score": 85,
      "matched_fields": ["name", "dob"],
      "citation": { "source": "…", "url": "…", "accessed_at": "…" }
    }
  ],
  "disclaimer": "Informational only — not a legal verdict. Not a substitute for due diligence. Human review required before any adverse action.",
  "generated_at": "…"
}
```

### enrich_company
Look up a company's legal identity and profile. Input is `domain?` or `name?`
(at least one), plus optional `request_id?`.

Output: `{ company_id, legal_name, domain, industry, industry_code?, size_band,
employee_range, hq: {country, city?}, founded?, sources: [{field, source, url}],
confidence, generated_at }`.

v1 data: GLEIF LEI data (free, public) for legal identity, plus one commodity
enrichment API wrapped in this schema. Every field carries its source in `sources`.

Example input:
```json
{ "domain": "acme.example" }
```
Example output (schema):
```json
{
  "company_id": "cs_co_…",
  "legal_name": "ACME Corporation",
  "domain": "acme.example",
  "industry": "Manufacturing",
  "size_band": "201-500",
  "employee_range": [201, 500],
  "hq": { "country": "US", "city": "Austin" },
  "sources": [{ "field": "legal_name", "source": "GLEIF", "url": "…" }],
  "confidence": "high",
  "generated_at": "…"
}
```

## Data sources (screening)
- OFAC SDN list (ADVANCED XML), daily full refresh. Last verified live file: Publish_Date 2026-09-23.
- EU consolidated sanctions list (FSD XML, daily) — PENDING: needs a free EU Login account;
  ships once the account exists.
- UK FCDO sanctions list (CSV, OGL v3.0).
- UN list: EXCLUDED from v1 on licensing grounds (EU regulations implement UN designations,
  so coverage largely overlaps).

## Matching method (summary)
Unicode NFKD fold → strip punctuation → lowercase → transliterate (anyascii); index both
token orderings per name variant. Alias expansion from OFAC akaList with strong/weak
quality tiers. Confidence: exact(normalized)+1 identifier → high (≥85); exact name, no
identifier → medium (≥60); fuzzy (Jaro-Winkler ≥0.92 or Levenshtein ≤2) → low (≥30).
Identifier corroboration via DOB/place of birth/nationality/ID numbers.
Calibrated on live OFAC data 2026-09-26: common names never produced a medium/high false
positive; every low-tier match is returned, never hidden.

Full schemas, few-shot examples, and the complete matching write-up: see llms-full.txt.