OFACScreen Sanctions Screening

Sanctions address screening (14 lists)

screen_address

Read-onlyIdempotent

Screen a street address against the addresses recorded on 14 sanctions and export-control lists: OFAC SDN, OFAC Non-SDN, EU Financial Sanctions, UN Security Council, UK Sanctions List, Canada SEMA, Swiss SECO, Australia DFAT, BIS Denied Persons, BIS Entity List, BIS Unverified List, BIS Military End-User, ITAR Debarred and State Nonproliferation. Returns the number of listed parties whose recorded address resembles it and the ten highest scoring, each with matched_address (the listed address it matched on), its score, list and program, plus jurisdiction_flags: an embargoed or high-risk country or region the address points to. A jurisdiction flag says where, not who: it is not a sanctions match and never counts as one. The lists record addresses for only some of the parties on them, so no match clears no one at the address: screen their names with screen_entity too. The address must name a street or a building, e.g. "Tverskaya 7, Moscow"; a city or a country alone is refused. Free, no account, 25 screenings a day from each internet address, shared by screen_entity and screen_address; in ChatGPT, each user has their own 25. A screening is not recorded and produces no document: its report_url opens the same search on ofacscreen.com, where a timestamped PDF record of it can be bought. The price is in report_price. Calling this tool is free. Searched only when named in lists: UAE Local Terrorist List, UFLPA Entity List, FBI Most Wanted, FinCEN Special Measures, France Registre des gels, Israel NBCTF crypto wallets, Japan MOF, Mexico SAT 69-B, Poland MSWiA.

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": {
      "address": "<address>"
    },
    "name": "screen_address"
  }
}

Input Schema

Name	Required	Description	Default
`lists`	No	List codes to search instead of the default 14. Omit to search the default lists.
`address`	Yes	The street address to screen: the street and number or the building, with the city and country if known, e.g. "Tverskaya 7, Moscow, Russia". Up to 300 characters.

Output Schema

Name	Required	Description	Default
`mode`	Yes
`query`	Yes
`results`	Yes
`contacts`	No
`report_url`	Yes
`match_found`	Yes
`screened_at`	No
`report_price`	Yes
`results_count`	Yes
`results_shown`	No
`lists_screened`	No
`contact_matches`	No
`is_audit_record`	No
`lists_refreshed`	No
`place_data_credit`	No
`results_truncated`	No
`jurisdiction_flags`	Yes
`results_count_is_capped`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 19, 2026

addedOutput schema / properties / contact_matches

Added value: +{
+  "items": {
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / contacts

Added value: +{
+  "items": {
+    "type": "object"
+  },
+  "type": "array"
+}

AddedOct 15, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Goes well beyond the read-only/idempotent annotations: it discloses the daily quota (25, shared with screen_entity), that screenings are not recorded and produce no document, that report_url is an external paid search with price in report_price, and that jurisdiction_flags indicate location and never count as a sanctions match.

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

Conciseness4/5

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

Front-loads purpose, scope and the key caveat, and most sentences carry unique information. It is dense and the inline enumeration of all 14 lists plus the trailing 'searched only when named' sentence make it longer than ideal, but nothing is truly redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description still usefully explains the shape of the key return fields (matched_address, score, list/program, jurisdiction_flags) and their semantics. Quota, refusal conditions, caveats and the name-screening alternative are all covered, leaving no gap for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning: it enumerates the default 14 lists and explains that the remaining lists (UAE, UFLPA, FBI, FinCEN, etc.) are searched only when explicitly named via the lists parameter. It also gives an address format example and the street-or-building constraint.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource ('Screen a street address') and names the exact scope: 14 enumerated sanctions and export-control lists. It clearly separates itself from the sibling screen_entity by stating this tool screens addresses while names go to screen_entity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use guidance ('the address must name a street or a building... a city or a country alone is refused'), routes name screening to screen_entity, and documents the shared 25/day rate limit. The condition selecting the alternative tool is stated, not implied.

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

All OFACScreen Sanctions Screening tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?