Retrieve the stored card data associated with a Cartão Protegido token (GET /card/{token}). Returns masked card fields + brand + expiration.
AI agents call get_card_token to retrieve information from Mcp Afip without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves card token data in masked form (PII is redacted). While it accesses sensitive payment card information, the masked return values and read-only nature (GET endpoint) classify it as Read rather than higher severity. The low severity reflects that masked data carries reduced risk compared to full card details, though access controls should still be strict in production.
From the tool's definition Tool name and description both indicate retrieval: 'Retrieve the stored card data' and 'Returns masked card fields'. The action is a GET operation that queries existing data without modification or deletion.
Documented attack patterns abuse exactly the kind of access get_card_token gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Afip, and nothing reaches the server without passing your rules. This is the rule we recommend for get_card_token:
{
"version": "1",
"default": "deny",
"tools": {
"get_card_token": {}
}
} get_card_token is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Retrieve the stored card data associated with a Cartão Protegido token (GET /card/{token}). Returns masked card fields + brand + expiration. It is categorised as a Read tool in the Mcp Afip MCP Server, which means it retrieves data without modifying state.
Register the Mcp Afip MCP server in PolicyLayer and add a rule for get_card_token: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Afip. Nothing to install.
get_card_token is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_card_token rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_card_token. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_card_token is provided by the Mcp Afip MCP server (codespar/mcp-dev-latam). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Afip, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
1300 Mcp Afip tools catalogued and risk-classified — across an index of 43,000+ MCP servers.