Clear the menu cache to force fresh data on next request
AI agents call clear_menu_cache to permanently remove resources in For Five Coffee MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing a cache irreversibly removes cached data, forcing a reload on next request. While the blast radius is low (only menu cache data is affected, and it's recoverable by re-fetching), the action is non-reversible in the sense that the cached state is permanently discarded. No financial, code execution, or write implications; closest fit is Destructive at low severity.
From the tool's definition Clear the menu cache to force fresh data on next request
Attacks that exploit this kind of access
Clear the menu cache to force fresh data on next request. It is categorised as a Destructive tool in the For Five Coffee MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the For Five Coffee MCP Server MCP server in PolicyLayer and add a rule for clear_menu_cache: 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 For Five Coffee MCP Server. Nothing to install.
clear_menu_cache 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_menu_cache 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_menu_cache. 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_menu_cache is provided by the For Five Coffee MCP Server MCP server (kong/for-five-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 →