[Variable API calls] [Workflow] Prepares a category for deletion by cleaning up its history:
AI agents call delete_category to permanently remove resources in Ynab — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes financial data (budget categories). Even though the description mentions 'cleaning up history' as preparation rather than immediate deletion, the deletion itself cannot be undone.
From the tool's definition Tool name is 'delete_category' and description states it 'Prepares a category for deletion', which is an irreversible data removal operation.
Attacks that exploit this kind of access
[Variable API calls] [Workflow] Prepares a category for deletion by cleaning up its history:. It is categorised as a Destructive tool in the Ynab MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ynab MCP server in PolicyLayer and add a rule for delete_category: 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 Ynab. Nothing to install.
delete_category 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_category 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_category. 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_category is provided by the Ynab MCP server (justmytwospence/ynab-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →