Clear embedding cache
AI agents call clear_cache to permanently remove resources in Self-Improving Memory MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool destroys persisted embeddings and cached knowledge that the system has built over time. While the blast radius depends on the cache size and recovery options (which are not described), the irreversible nature of cache clearing—combined with the system's stated purpose of persistent memory—makes this a destructive operation.
From the tool's definition Tool name is 'clear_cache' with description 'Clear embedding cache'. The verb 'clear' indicates deletion or erasure of cached data.
Attacks that exploit this kind of access
Clear embedding cache. It is categorised as a Destructive tool in the Self-Improving Memory MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Self-Improving Memory 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 Self-Improving Memory MCP. 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 Self-Improving Memory MCP server (superpitt/self-improving-memory-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 →