Card Validation for AI Agents
The tool
Give enterprise agents Luhn-based card validation through the same real-data layer, returning brand and validity for any number on demand.
Once your client is connected to the VerveContext MCP server, this appears in its tool list as CardValidationforAIAgents. 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": "CardValidationforAIAgents",
"arguments": {
"number": "4900264223817524"
}
}What that looks like in a conversation
You don't name the tool — the model picks it. Asking about 4900264223817524 in the terms this source covers is enough for it to reach for CardValidationforAIAgents 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 |
|---|---|---|---|
numberRequired | string | 4900264223817524 | The card number to validate |
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": {
"card": {
"niceType": "Visa",
"type": "visa",
"patterns": [
4
],
"gaps": [
4,
8,
12
],
"lengths": [
16,
18,
19
],
"code": {
"name": "CVV",
"size": 3
},
"matchStrength": 1
},
"brand": "Visa",
"cardNumber": "4900264223817524",
"bin": "490026",
"last4": "7524",
"isValid": true,
"isPotentiallyValid": true,
"isTestCard": false,
"riskScore": 0,
"riskLevel": "low"
}
}Fields
| Field | Type | Example | Description |
|---|---|---|---|
card | object | Card identification and validation details | |
└ card.niceType | string | Human-readable card type name like Visa | |
└ card.typePremium | string | Machine-readable card type identifier | |
└ card.patternsPremium | array | Starting digit patterns for card type | |
└ card.gapsPremium | array | Character positions for spacing formatting | |
└ card.lengthsPremium | array | Valid card length values in digits | |
└ card.codePremium | object | Security code specifications for card | |
└ card.code.namePremium | string | Name of security code like CVV | |
└ card.code.sizePremium | number | Number of digits in security code | |
└ card.matchStrengthPremium | number | Confidence level of card type match | |
brand | string | Human-readable card brand (e.g. Visa, Mastercard), or null if the scheme could not be identified | |
cardNumber | string | The validated card number provided | |
bin | string | The card's BIN/IIN (first 6 digits), or null if fewer than 6 digits were supplied | |
last4 | string | The last 4 digits of the card, or null if fewer than 4 digits were supplied | |
isValid | boolean | Whether the card number is complete and passes the Luhn checksum | |
isPotentiallyValid | boolean | Whether the number could still become valid (correct brand prefix but possibly incomplete) — useful while a user is still typing | |
isTestCardPremium | boolean | Whether the number is a known published processor test card (Stripe, Adyen, etc.) rather than a live card | |
riskScorePremium | number | Composite 0-100 risk score combining Luhn validity, test-card and scheme-recognition signals (higher is riskier) | |
riskLevelPremium | string | Risk band derived from the score: low, medium or high |
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 brand: 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 Card Validation for AI Agents
Set up Card Validation for AI Agents 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 CardValidationforAIAgents?
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.