전체 캐시 삭제
AI agents call cache_clear to permanently remove resources in PM-MCP (Portfolio Management MCP Server) — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool deletes the entire cache, which is an irreversible bulk deletion operation. While cache data is typically regeneratable, the action itself cannot be undone and may impact ongoing analyses or performance. Classified as Destructive with medium severity since cache loss doesn't permanently destroy primary data, but wiping all cached portfolio/market data could disrupt active operations.
From the tool's definition '전체 캐시 삭제' means 'delete entire cache' in Korean — irreversibly clears all cached data
Attacks that exploit this kind of access
전체 캐시 삭제. It is categorised as a Destructive tool in the PM-MCP (Portfolio Management MCP Server) MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the PM-MCP (Portfolio Management MCP Server) MCP server in PolicyLayer and add a rule for cache_clear: 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 PM-MCP (Portfolio Management MCP Server). Nothing to install.
cache_clear 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_clear 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_clear. 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_clear is provided by the PM-MCP (Portfolio Management MCP Server) MCP server (surplus96/pm-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 →