AI agents call cache_status to permanently remove resources in Qualys — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool has a dual function: reading cache stats (a Read operation) and clearing all caches (a Destructive operation). Per the rules, the most severe applicable category must be chosen. Clearing all caches irreversibly destroys cached data, which qualifies as Destructive.
From the tool's definition 'clear all caches' — clearing caches is an irreversible operation that destroys cached data and cannot be undone
Risk signalsBulk/mass operation — affects multiple targets · Admin/system-level operation
Documented attack patterns abuse exactly the kind of access cache_status gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Qualys, and nothing reaches the server without passing your rules. This is the rule we recommend for cache_status:
{
"version": "1",
"default": "deny",
"hide": [
"cache_status"
]
}cache_status disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
[Admin] Show cache stats or clear all caches. It is categorised as a Destructive tool in the Qualys MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Qualys MCP server in PolicyLayer and add a rule for cache_status: 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 Qualys. Nothing to install.
cache_status 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 cache_status 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 cache_status. 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.
cache_status is provided by the Qualys MCP server (nelssec/qualys-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Qualys, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 Qualys tools catalogued and risk-classified — across an index of 43,000+ MCP servers.