Permanently delete a memory by ID.
AI agents call memory_delete to permanently remove resources in Agent Memory — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes data (a memory record) from persistent storage. Permanent deletion cannot be undone and fits the Destructive category definition. Severity is high because an AI agent could accidentally or maliciously erase important memories, affecting system state and agent behavior continuity. The impact is significant but scoped to the memory store rather than critical infrastructure.
From the tool's definition Tool name is 'memory_delete' and description states 'Permanently delete a memory by ID.' The word 'Permanently' indicates irreversible deletion.
Attacks that exploit this kind of access
Permanently delete a memory by ID. It is categorised as a Destructive tool in the Agent Memory MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Agent Memory MCP server in PolicyLayer and add a rule for memory_delete: 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 Agent Memory. Nothing to install.
memory_delete 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 memory_delete 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 memory_delete. 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.
memory_delete is provided by the Agent Memory MCP server (khaled1174/agent-memory). 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 →