Manually trigger cleanup of old or low-relevance short-term memories. This removes memories older than 1 year or with very low relevance scores, keeping at least 512 memories.
AI agents call cleanup_memories to permanently remove resources in Memory MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently removes memory records based on age and relevance scoring thresholds. The word 'removes' confirms irreversible deletion of data. While it has a floor of keeping 512 memories, the deletions themselves cannot be undone, making this Destructive. The blast radius is high because an AI agent could inadvertently purge large volumes of stored memory context that cannot be recovered without a backup.
From the tool's definition 'Manually trigger cleanup of old or low-relevance short-term memories. This removes memories older than 1 year or with very low relevance scores'
Attacks that exploit this kind of access
Manually trigger cleanup of old or low-relevance short-term memories. This removes memories older than 1 year or with very low relevance scores, keeping at least 512 memories. It is categorised as a Destructive tool in the Memory MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Memory MCP Server MCP server in PolicyLayer and add a rule for cleanup_memories: 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 MCP Server. Nothing to install.
cleanup_memories 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 cleanup_memories 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 cleanup_memories. 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.
cleanup_memories is provided by the Memory MCP Server MCP server (win10ogod/memory-mcp-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 →