Clear old memories to free space (keeps frequently accessed).
AI agents call clear_old_memories to permanently remove resources in Vector Memory MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes data (old memory records) from persistent storage. Although it applies heuristics (keeps frequently accessed memories), the action is not reversible and constitutes permanent data loss. This is characteristic of the Destructive category.
From the tool's definition clear_old_memories - Clear old memories to free space. The verb 'clear' combined with the function of removing old memories indicates irreversible deletion of data records, which cannot be undone.
Attacks that exploit this kind of access
Clear old memories to free space (keeps frequently accessed). It is categorised as a Destructive tool in the Vector Memory MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Vector Memory MCP server in PolicyLayer and add a rule for clear_old_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 Vector Memory MCP. Nothing to install.
clear_old_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 clear_old_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 clear_old_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.
clear_old_memories is provided by the Vector Memory MCP server (xsaven/vector-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 →