Clear specific or all cache entries
AI agents call clear_cache to permanently remove resources in Memory Cache Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing cache entries permanently removes stored data from the cache. Since this can wipe all cache entries at once, a misuse by an AI agent could destroy all cached context/data that was accumulated during a session, with no recovery path. This maps to Destructive rather than Write because the operation is a deletion/purge, not a modification.
From the tool's definition 'Clear specific or all cache entries' — the tool removes cached data, which is irreversible within the cache lifecycle.
Attacks that exploit this kind of access
Clear specific or all cache entries. It is categorised as a Destructive tool in the Memory Cache Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Memory Cache Server 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 Memory Cache Server. 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 Memory Cache Server MCP server (tosin2013/mcp-memory-cache-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 →