Clear usage data
AI agents call clear_usage to permanently remove resources in Llm Token Tracker — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
An AI agent that decides to call clear_usage doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Llm Token Tracker is gone — there is no undo for destructive operations.
Attacks that exploit this kind of access
Clear usage data. It is categorised as a Destructive tool in the Llm Token Tracker MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Llm Token Tracker MCP server in PolicyLayer and add a rule for clear_usage: 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 Llm Token Tracker. Nothing to install.
clear_usage 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 clear_usage 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 clear_usage. 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.
clear_usage is provided by the Llm Token Tracker MCP server (wn01011/llm-token-tracker). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.