Sanctions Screening: Check Names Against OFAC, EU, UK & UN

Screen any name or company against current official OFAC, EU, UK and UN sanctions lists. Bulk or single, with match scores and details. For people and AI agents.

Screens against official OFAC/EU/UK/UN lists. We store nothing beyond the run's own output. Not legal advice.

Use with AI agents (MCP)

This Actor is also an MCP tool — AI agents like Claude and Cursor can call it directly; usage bills through your Apify account.

MCP server URL:

https://mcp.apify.com?tools=apifmcpfactory/sanctions-screening

Claude Desktop (claude_desktop_config.json):

{
    "mcpServers": {
        "sanctions-screening": {
            "command": "npx",
            "args": [
                "mcp-remote",
                "https://mcp.apify.com?tools=apifmcpfactory/sanctions-screening",
                "--header",
                "Authorization: Bearer YOUR_APIFY_TOKEN"
            ]
        }
    }
}

Cursor (.cursor/mcp.json):

{
    "mcpServers": {
        "sanctions-screening": {
            "url": "https://mcp.apify.com?tools=apifmcpfactory/sanctions-screening",
            "headers": {
                "Authorization": "Bearer YOUR_APIFY_TOKEN"
            }
        }
    }
}

Replace YOUR_APIFY_TOKEN with your API token from Apify Console.

No Apify account? AI agents can also pay per call with USDC via the x402 protocol: buy a prepaid token at agi.apify.com and use it as the Bearer token above.

One atomic tool: screen_entity

screen_entity(names, [entityType], [country], [threshold], [includeAliases]) -> match results — screen one or more names against OFAC, EU, UK and UN sanctions lists and return deterministic match scores.

Field	Type	Description
names	string[] (required)	One or more names/companies to screen.
entityType	"any" | "person" | "org"	Narrow to persons or organizations. Default any.
country	string	Narrow matching to entries tagged with this country. Optional.
threshold	integer 0-100	Minimum fuzzy-match score to return. Default 85.
includeAliases	boolean	Also match known aliases (a.k.a./f.k.a.), not just the primary name. Default true.

Example call:

{ "names": ["AeroCaribbean Airlines"], "entityType": "org", "threshold": 85 }

A secondary mode, list_status, reports each official list's cached record count and last-refresh date — call it to confirm data freshness before relying on results: { "mode": "list_status" }.

Why use it?

• Official sources only — OFAC SDN, OFAC Consolidated Non-SDN, EU Consolidated Financial Sanctions List, UK OFSI, and the UN Security Council Consolidated List. No aggregated third-party data, no commercially-licensed feeds.
• Deterministic, explainable matching — normalised names and aliases scored with Jaro-Winkler token alignment. Same input always produces the same score. No LLM in the matching path, so results are reproducible and auditable.
• Bulk or single, human or agent — screen one name from a form or thousands from a CSV-derived array; the same tool works identically as an MCP call from an AI agent.
• Fast repeat screening — the 5 official lists are cached and refreshed on a schedule, so a screening call doesn't pay the cost of re-downloading ~70MB of government data every time.

How to use it

1. Open the Input tab and enter one or more Names to screen (a working example is pre-filled — just click Start to try it).
2. Optionally narrow by Entity type or Country, and tune the Match threshold.
3. Click Start. Results appear in the Output tab — one row per name, with every match at or above the threshold.
4. To keep the underlying lists fresh, click Schedule on this Actor, set mode to refresh_cache, and run it daily.

Input

{
    "names": ["AeroCaribbean Airlines", "Acme Test Company"],
    "entityType": "any",
    "threshold": 85,
    "includeAliases": true
}

Field	Description
names	Array of names/companies to screen. Billed per name checked.
entityType	any | person | org. Default any.
country	Narrow matching to entries tagged with this country. Optional.
threshold	Minimum fuzzy-match score 0-100 to return as a match. Default 85.
includeAliases	Also match known aliases, not just the primary listed name. Default true.
mode	screen (default) | list_status | refresh_cache. Advanced field.

Output

One row per screened name:

{
    "mode": "screen",
    "query": "AeroCaribbean Airlines",
    "isMatch": true,
    "topScore": 100,
    "matches": [
        {
            "matchedName": "AEROCARIBBEAN AIRLINES",
            "list": "OFAC SDN",
            "program": "CUBA",
            "entityType": "org",
            "score": 100,
            "entityId": "OFAC SDN-36"
        }
    ]
}

A clean name returns "isMatch": false with an empty matches array and its highest computed score in topScore for context, even though it fell below the threshold. list_status returns each list's cached record count and last-refresh timestamp instead.

What are the OFAC, EU, UK and UN sanctions lists?

Governments and the UN Security Council publish lists of individuals, companies and vessels subject to financial sanctions or trade restrictions. This Actor screens against four of the most widely required sources:

1. OFAC SDN — the US Treasury's Specially Designated Nationals list.
2. OFAC Consolidated Non-SDN — other US Treasury sanctions programs (e.g. sectoral sanctions).
3. EU Consolidated Financial Sanctions List — the European Commission's consolidated list of EU financial sanctions targets.
4. UK OFSI Consolidated List — the UK Office of Financial Sanctions Implementation's consolidated list of asset-freeze targets.
5. UN Security Council Consolidated List — sanctions targets designated under UN Security Council resolutions.

Names are normalised (case, punctuation, diacritics) and matched against both primary listed names and known aliases using a deterministic Jaro-Winkler-based algorithm — the same names always produce the same scores.

Pricing — pay per event

Event	Price	Charged when
Name screened	$0.015	one name successfully screened against all lists

Empty or invalid names are skipped and never charged. list_status and refresh_cache runs cost nothing beyond the automatic actor-start event.

Compliance

Screens against official OFAC/EU/UK/UN lists only — no OpenSanctions or other aggregated/commercially-licensed data. We store nothing beyond the run's own output: screening is transient, and the only thing persisted between runs is the lists' own public data (names, aliases, programs) in a cache used to keep screening fast. This tool is a screening aid — the human or agent using it makes the compliance decision, not this Actor. Not legal advice.

FAQ

Why did a name score below 100 even though it's clearly the same entity? Real-world data entry varies — punctuation, word order, abbreviations. The match score reflects how close the normalised names are; review matches for anything at or near your threshold rather than relying on exact string equality.

Why is topScore sometimes non-zero with no matches? topScore reports the best score found across all lists even when it falls below your threshold, so you can see how close the nearest candidate was.

How fresh is the underlying data? Check list_status for each list's last-refresh timestamp. Attach mode: "refresh_cache" to a daily Apify Schedule to keep it current; screening also self-heals (re-fetches) any list whose cache is more than 48 hours old.

Does this use OpenSanctions or any paid data provider? No — only the free, official government/UN sources listed above.

More tools from MCP Factory

• EU VAT Validator — bulk-validate EU VAT numbers against the EU's official VIES service.
• llms.txt Generator & Checker — audit, generate and monitor a site's AI-readiness llms.txt.
• PDF Toolkit — merge, split, compress, convert, rotate and watermark PDFs.

Tags: sanctions screening, OFAC SDN check, sanctions list API, AML screening, watchlist screening, denied party screening, EU sanctions, UK sanctions, UN sanctions, KYC screening