Sanctions Screening Grounding Data
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.
{
"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.
{
"mcpServers": {
"vervecontext": {
"url": "https://api.vervecontext.com/v1/mcp"
}
}
}https://api.vervecontext.com/v1/mcpPer-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.
| Argument | Type | Example | Description |
|---|---|---|---|
nameRequired | string | Banco Nacional de Cuba | The person or company name to screen (minimum 3 characters) |
thresholdPremium | number | 0.85 | Minimum match score to return, between 0.5 and 1. Lower catches more names but returns more false positives |
limitPremium | number | 10 | Maximum number of matches to return (1-50) |
typePremium | string | individual | Restrict 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.
{
"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
| Field | Type | Example | Description |
|---|---|---|---|
query | string | The name that was screened | |
matched | boolean | Whether any entry on the list matched the query | |
matchCount | number | Number of matching entries returned | |
verdict | string | Highest confidence across all matches: exact, high, possible, or none | |
topScore | number | Match score of the strongest match, from 0 to 1 | |
results | array[1] | Matching SDN entries, strongest first | |
└ results.0.uid | number | OFAC unique identifier for the entry | |
└ results.0.name | string | Primary name as published by OFAC | |
└ results.0.type | string | Entry type: individual, entity, vessel, or aircraft | |
└ results.0.score | number | Match score for this entry, from 0 to 1 | |
└ results.0.confidence | string | Plain-language score band: exact, high, or possible | |
└ results.0.matchedOnPremium | string | The normalized name or alias the query actually matched | |
└ results.0.matchedViaPremium | string | Whether the match came from the primary name or an alias type | |
└ results.0.isWeakAliasPremium | boolean | True when matched on an alias OFAC flags as low confidence | |
└ results.0.programs | array | Sanctions programs the entry is listed under | |
└ results.0.titlePremium | object | Role or title of the listed individual | |
└ results.0.akaPremium | array[2] | All known aliases with type and strength | |
└ results.0.aka.0.namePremium | string | ||
└ results.0.aka.0.typePremium | string | ||
└ results.0.aka.0.strengthPremium | string | ||
└ results.0.dateOfBirthPremium | array | Published dates of birth | |
└ results.0.placeOfBirthPremium | array | Published places of birth | |
└ results.0.nationalitiesPremium | array | Published nationalities | |
└ results.0.citizenshipsPremium | array | Published citizenships | |
└ results.0.addressesPremium | array[4] | Published addresses | |
└ results.0.addresses.0.address1Premium | string | ||
└ results.0.addresses.0.cityPremium | string | ||
└ results.0.addresses.0.postalCodePremium | string | ||
└ results.0.addresses.0.countryPremium | string | ||
└ results.0.idsPremium | array | Published identity documents and registration numbers | |
└ results.0.remarksPremium | object | OFAC remarks for the entry | |
list | object | ||
└ list.source | string | Name of the sanctions list screened | |
└ list.authority | string | Publishing authority for the list | |
└ list.publishDate | string | Date OFAC published the list version screened against | |
└ list.recordCount | number | Number of entries on the list version screened against | |
└ list.lastUpdated | string | ISO 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.
| Status | What it means |
|---|---|
400 / 422 | The arguments didn't validate. The message names the offending one. |
401 | The OAuth session is invalid or expired — reconnect the server. |
403 | Out of credits. Not a bad key — the month's allowance is spent. |
404 | This source isn't part of VerveContext. Check the catalog. |
429 | Brief 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.
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.