Delete memory by ID (permanent, cannot be undone).
AI agents call delete_by_memory_id 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.
The tool explicitly states it permanently deletes a memory record and cannot be undone, which is the defining characteristic of a Destructive action. Misuse by an AI agent could result in irreversible loss of stored knowledge or experiences.
From the tool's definition Delete memory by ID (permanent, cannot be undone).
Attacks that exploit this kind of access
Delete memory by ID (permanent, cannot be undone). 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 delete_by_memory_id: 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.
delete_by_memory_id 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 delete_by_memory_id 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 delete_by_memory_id. 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.
delete_by_memory_id 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.
delete_by_memory_id is one line of Vector Memory's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →