Delete a category
AI agents call deleteCategory to permanently remove resources in Memo — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a category from the memo database. Deletion is irreversible and cannot be undone without manual intervention or backups. The impact is high because deleting a category may cascade effects on associated memos or application logic that depends on that category.
From the tool's definition Tool name is 'deleteCategory' and description states 'Delete a category'. The verb 'delete' combined with action on a stored category indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete a category. It is categorised as a Destructive tool in the Memo MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Memo MCP server in PolicyLayer and add a rule for deleteCategory: 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 Memo. Nothing to install.
deleteCategory 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 deleteCategory 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 deleteCategory. 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.
deleteCategory is provided by the Memo MCP server (108yen/memo-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
deleteCategory is one line of Memo's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →