AI agents call clear_cache to permanently remove resources in Icon — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing a cache is a destructive, irreversible action that removes stored data. While the data can be re-fetched from the source, the cached entries are permanently deleted. The blast radius is medium because it affects cached icons, potentially causing performance degradation or temporary unavailability of icons, but does not delete source data.
From the tool's definition 'Clear icon cache' — clearing cache irreversibly removes cached data
Documented attack patterns abuse exactly the kind of access clear_cache gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Icon, and nothing reaches the server without passing your rules. This is the rule we recommend for clear_cache:
{
"version": "1",
"default": "deny",
"hide": [
"clear_cache"
]
}clear_cache 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.
Clear icon cache. It is categorised as a Destructive tool in the Icon MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Icon MCP server in PolicyLayer and add a rule for clear_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 Icon. Nothing to install.
clear_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_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_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_cache is provided by the Icon MCP server (liliangshan/mcp-server-icon). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Icon, 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.
5 Icon tools catalogued and risk-classified — across an index of 43,000+ MCP servers.