KeyVex

get_ofac_sdn

Read-only

Returns OFAC Specially Designated Nationals (SDN) sanctions list entries, republished as-is (not a screening service; verify against treasury.gov). Use this for: sanctions-program queries (e.g., 'who's on the Russia SDN list'), or cross-referencing named individuals / entities against the canonical US sanctions list. Source: US Treasury OFAC — sanctionslistservice.ofac.treas.gov. ~19,000 entries refreshed daily. Each entry represents a person, entity, vessel, or aircraft sanctioned by the US government under one or more programs (CUBA, IRAN, SDGT [terrorism], NPWMD [WMD proliferation], RUSSIA-EO14024, etc.). US persons (citizens, residents, US-domiciled companies) are legally prohibited from transacting with SDNs — this is the canonical list published by OFAC. Filter by name substring for primary lookups. entity_type values: 'individual', 'entity', 'vessel', 'aircraft'. Every SDN record carries exactly one of the four — companies are 'entity'. program is a substring filter against the comma-delimited Program field (e.g., 'iran', 'russia', 'narcotics'). remarks substring catches aliases, DOB / passport references, and related-party hints. Direct ent_num lookup is fastest (OFAC's stable entity number). WHAT'S NOT IN v1A (data-model limitations to know about): the schema does NOT include designation_date (when OFAC originally added the entry). OFAC's basic SDN.csv source file only provides 12 columns and omits this — the date lives in OFAC's advanced XML and a separate 'Recent Actions' page on their site. So 'sanctions added in the last N days' is not directly queryable via this tool — point users at ofac.treasury.gov/recent-actions for that specific question. v1.1 polish will add advanced-XML ingestion to capture designation_date. Also: there's no since/until filter and no date sort option for the same reason — the only sort options are name and ent_num. Pure-publisher posture: KeyVex returns OFAC's published list as-is. No derived 'risk score' or 'similarity match' — agents handle fuzzy matching downstream. For broader list coverage, agents should also consult the US Consolidated Screening List (get_screening_list) which spans 12 export-control / sanctions lists from State + Commerce + Treasury.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	No	Case-insensitive substring against the primary listed name (e.g., 'kim jong un', 'gazprom').
`limit`	No	Maximum entries to return. Default 50, max 500.
`ent_num`	No	Direct OFAC entity number lookup. Fastest path.
`program`	No	Substring against the comma-delimited program field (e.g., 'IRAN', 'RUSSIA', 'SDGT' for terrorism, 'NARCOTICS').
`remarks`	No	Substring against free-text remarks (aliases, DOB / passport references, related-party hints).
`sort_by`	No	Default: ent_num.
`sort_order`	No	Default: asc.
`entity_type`	No	Filter to one entity type. 'entity' covers companies / orgs; 'individual' for people; 'vessel' / 'aircraft' for transports.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 4, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations cover readOnly/openWorld/destructive, but the description adds substantial context beyond them: republished as-is with no risk score, ~19,000 entries refreshed daily, a legal prohibition notice, and explicit v1A data-model limitations (no designation_date, no since/until filter, sort limited to name/ent_num). Return-format/pagination behavior is not described, keeping it below a 5.

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-loaded with purpose and usage before the long v1A limitations block, and every section carries information. However it is verbose with some repetition ('canonical US sanctions list' / 'canonical list published by OFAC'), so not maximally tight.

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?

For an 8-param tool with no output schema, the description covers what an entry represents, the domain scope, filtering semantics, and honest data-model gaps. Nothing critical to calling it correctly appears to be missing.

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 meaning beyond the schema: entity_type semantics ('companies are entity'), the substring nature of program and remarks filters, and the emphasis on ent_num as the fastest path. Some of this overlaps the schema, but it adds contextual framing.

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?

States a specific verb and resource ('Returns OFAC Specially Designated Nationals (SDN) sanctions list entries') and explicitly disclaims what it is not ('not a screening service'). It names the sibling get_screening_list and the recent-actions alternative, so the agent can distinguish it from nearby tools.

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?

Provides explicit 'Use this for:' cases (sanctions-program queries, cross-referencing named individuals/entities), states when-not (designation_date / 'added in last N days' questions point at recent-actions), and routes broader coverage to get_screening_list. When, when-not, and alternatives are all present.

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

All KeyVex 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?