Clear expired weather cache entries.
AI agents call clear_old_cache to permanently remove resources in MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing cache entries deletes data (expired cache), which is irreversible. However, the blast radius is low since only expired/stale weather cache entries are removed, not user data or critical system state. The server only stores transient weather data, so losing it is inconsequential — the data can be re-fetched.
From the tool's definition 'Clear expired weather cache entries' — removes cached data entries
Attacks that exploit this kind of access
Clear expired weather cache entries. It is categorised as a Destructive tool in the MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Server MCP server in PolicyLayer and add a rule for clear_old_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 MCP Server. Nothing to install.
clear_old_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_old_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_old_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_old_cache is provided by the MCP Server MCP server (naggbagg/mcp-server). 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 →