Sanctions Screening Grounding DataSanctions Screening Grounding Data

OnlineCredit Usage:1 per callTool:SanctionsScreeningGroundingData

The tool

Ground compliance agents in the authoritative OFAC SDN list so sanctions answers cite the current published list instead of a model's recollection.

Once your client is connected to the VerveContext MCP server, this appears in its tool list as SanctionsScreeningGroundingData. It is read-only and open-world: it fetches, it never mutates anything on your side, so most clients will call it without asking you to confirm.

Tool call
{
  "name": "SanctionsScreeningGroundingData",
  "arguments": {
    "name": "Banco Nacional de Cuba"
  }
}

What that looks like in a conversation

You don't name the tool — the model picks it. Asking about Banco Nacional de Cuba in the terms this source covers is enough for it to reach for SanctionsScreeningGroundingData on its own.

Connecting

One server URL covers every source in the catalog, including this one. Authorization is OAuth — the client opens a browser once and there is no key to paste into a config file.

Client config
{
  "mcpServers": {
    "vervecontext": {
      "url": "https://api.vervecontext.com/v1/mcp"
    }
  }
}
Endpoint
https://api.vervecontext.com/v1/mcp

Per-client setup — Claude Desktop, Cursor, VS Code, ChatGPT — is on the MCP setup page.

Arguments

These are the properties on the tool's inputSchema, so a well-behaved client validates them before the call is made.

ArgumentTypeExampleDescription
nameRequiredstringBanco Nacional de CubaThe person or company name to screen (minimum 3 characters)
thresholdPremiumnumber0.85Minimum match score to return, between 0.5 and 1. Lower catches more names but returns more false positives
limitPremiumnumber10Maximum number of matches to return (1-50)
typePremiumstringindividualRestrict screening to one entry type

What the model gets back

The result carries a structuredContent object matching the tool's declared outputSchema, so a client can read fields without parsing prose. status is "ok" on success and error is null; a null field means the value wasn't available for that input, not that the call failed.

Result
{
  "status": "ok",
  "error": null,
  "data": {
    "query": "Banco Nacional de Cuba",
    "matched": true,
    "matchCount": 1,
    "verdict": "exact",
    "topScore": 1,
    "results": [
      {
        "uid": 306,
        "name": "BANCO NACIONAL DE CUBA",
        "type": "entity",
        "score": 1,
        "confidence": "exact",
        "matchedOn": "BANCO NACIONAL DE CUBA",
        "matchedVia": "primary",
        "isWeakAlias": false,
        "programs": [
          "CUBA"
        ],
        "title": null,
        "aka": [
          {
            "name": "BNC",
            "type": "aka",
            "strength": "weak"
          },
          {
            "name": "NATIONAL BANK OF CUBA",
            "type": "aka",
            "strength": "strong"
          }
        ],
        "dateOfBirth": [],
        "placeOfBirth": [],
        "nationalities": [],
        "citizenships": [],
        "addresses": [
          {
            "address1": "Zweierstrasse 35",
            "city": "Zurich",
            "postalCode": "CH-8022",
            "country": "Switzerland"
          },
          {
            "address1": "Avenida de Concha Espina 8",
            "city": "Madrid",
            "postalCode": "E-28036",
            "country": "Spain"
          },
          {
            "address1": "Dai-Ichi Bldg. 6th Floor, 10-2 Nihombashi, 2-chome, Chuo-ku",
            "city": "Tokyo",
            "postalCode": "103",
            "country": "Japan"
          },
          {
            "address1": "Federico Boyd Avenue & 51 Street",

Fields

Fields marked Premium need a paid plan. On a plan without them the key is absent rather than wrong, so a model never reasons over a substituted value.
FieldTypeExampleDescription
querystringBanco Nacional de CubaThe name that was screened
matchedbooleantrueWhether any entry on the list matched the query
matchCountnumber1Number of matching entries returned
verdictstringexactHighest confidence across all matches: exact, high, possible, or none
topScorenumber1Match score of the strongest match, from 0 to 1
resultsarray[1]list of rowsMatching SDN entries, strongest first
results.0.uidnumber306OFAC unique identifier for the entry
results.0.namestringBANCO NACIONAL DE CUBAPrimary name as published by OFAC
results.0.typestringentityEntry type: individual, entity, vessel, or aircraft
results.0.scorenumber1Match score for this entry, from 0 to 1
results.0.confidencestringexactPlain-language score band: exact, high, or possible
results.0.matchedOnPremiumstringBANCO NACIONAL DE CUBAThe normalized name or alias the query actually matched
results.0.matchedViaPremiumstringprimaryWhether the match came from the primary name or an alias type
results.0.isWeakAliasPremiumbooleanfalseTrue when matched on an alias OFAC flags as low confidence
results.0.programsarray["CUBA"]Sanctions programs the entry is listed under
results.0.titlePremiumobjectnullRole or title of the listed individual
results.0.akaPremiumarray[2]list of rowsAll known aliases with type and strength
results.0.aka.0.namePremiumstringBNC
results.0.aka.0.typePremiumstringaka
results.0.aka.0.strengthPremiumstringweak
results.0.dateOfBirthPremiumarray[]Published dates of birth
results.0.placeOfBirthPremiumarray[]Published places of birth
results.0.nationalitiesPremiumarray[]Published nationalities
results.0.citizenshipsPremiumarray[]Published citizenships
results.0.addressesPremiumarray[4]list of rowsPublished addresses
results.0.addresses.0.address1PremiumstringZweierstrasse 35
results.0.addresses.0.cityPremiumstringZurich
results.0.addresses.0.postalCodePremiumstringCH-8022
results.0.addresses.0.countryPremiumstringSwitzerland
results.0.idsPremiumarray[]Published identity documents and registration numbers
results.0.remarksPremiumobjectnullOFAC remarks for the entry
listobject{…}
list.sourcestringOFAC SDNName of the sanctions list screened
list.authoritystringUS Department of the Treasury, Office of Foreign Assets ControlPublishing authority for the list
list.publishDatestring07/15/2026Date OFAC published the list version screened against
list.recordCountnumber19217Number of entries on the list version screened against
list.lastUpdatedstring2026-07-16T05:00:12.431ZISO 8601 timestamp of the last successful list sync

Why ground on it

A model can produce something that looks like this answer from its training data, and be confidently out of date or simply wrong. This source returns the current value with a shape you can check, which is the difference between an answer you can cite and one you have to hedge.

Point an evaluation at query: it is the field most worth pinning a claim to, and it is either present and current or absent — never plausibly invented.

Failure modes

Errors come back as tool errors with a sentence the model can act on, not a bare status code.

StatusWhat it means
400 / 422The arguments didn't validate. The message names the offending one.
401The OAuth session is invalid or expired — reconnect the server.
403Out of credits. Not a bad key — the month's allowance is spent.
404This source isn't part of VerveContext. Check the catalog.
429Brief rate limit. Retrying after a moment succeeds.

Other ways to use Sanctions Screening Grounding Data

Set up Sanctions Screening Grounding Data on VerveContext, or reach the same source a different way. Your VerveContext account and credits work on all of them — one key, one balance.

Call it as a REST APIOne HTTPS endpoint and an X-API-Key header, with SDKs for Node, Python and .NET.APIVerveReference →
Give it to an AI agentConnect over MCP and your agent calls it as a native tool — Claude, Cursor, ChatGPT.VerveKitReference →
Use it in Google Sheets or ExcelA =VERVE() formula fills a column — no script, no export, recalculates in place.VerveSheetsReference →

Frequently asked questions

Do I have to tell the agent to use SanctionsScreeningGroundingData?

No. The tool's name and description are in the model's context once the server is connected, so it selects the tool when the question calls for it. Naming it explicitly works too and is useful when you want to force the call.

Does connecting the server expose every tool at once?

Yes — one connection lists the whole VerveContext catalog. Clients with a tool budget can usually filter the list; the credit cost is per call, so an unused tool costs nothing.

What does a call cost?

1 credit each time the tool actually runs. A model that reasons about the tool without calling it costs nothing.

Is there a REST version of this?

Yes — the same source is available as a plain HTTPS endpoint on APIVerve, linked above. Same data, same credits, same account.

What's Next?

Continue your journey with these recommended resources

Was this page helpful?