AI agents call delete_token to permanently remove resources in Mcp Afip — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a stored payment token, which cannot be undone. The action is irreversible and affects financial infrastructure (card tokenization). While not directly moving funds, deleting authentication/authorization tokens for payments is a destructive operation with potential financial impact if misused (e.g., deleting legitimate tokens to disrupt payment processing).
From the tool's definition Tool name 'delete_token' with description 'Delete a stored card token' explicitly performs irreversible deletion of payment-related data.
Documented attack patterns abuse exactly the kind of access delete_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 delete_token:
{
"version": "1",
"default": "deny",
"hide": [
"delete_token"
]
} delete_token disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Delete a stored card token. It is categorised as a Destructive tool in the Mcp Afip MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Afip MCP server in PolicyLayer and add a rule for delete_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.
delete_token is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_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 delete_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.
delete_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.