clear_query_cache
AI agents call clear_query_cache to permanently remove resources in Ai Analyst — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The name suggests purging a query cache, which is typically an irreversible action (cached data is discarded). However, the description is empty, so confidence is reduced. Clearing a cache is generally low-blast-radius since caches are ephemeral by design, but it could cause performance degradation or data loss if cached results are the only copy.
From the tool's definition Tool name: 'clear_query_cache' — 'clear' implies irreversible removal of cached query data.
Attacks that exploit this kind of access
clear_query_cache. It is categorised as a Destructive tool in the Ai Analyst MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ai Analyst MCP server in PolicyLayer and add a rule for clear_query_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 Ai Analyst. Nothing to install.
clear_query_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_query_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_query_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_query_cache is provided by the Ai Analyst MCP server (sbdk-dev/local-ai-analyst). 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 →