Delete a memory by its ID.
AI agents call memory_delete to permanently remove resources in MCP Router — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes data (memories) without the ability to undo the operation. While the blast radius is constrained to the memory system rather than critical infrastructure, deletion of stored memories could cause significant harm if misused by an AI agent (e.g., erasing audit trails, user context, or important historical data).
From the tool's definition Tool name is 'memory_delete' with description 'Delete a memory by its ID.' The verb 'delete' is explicitly destructive; deletion is irreversible.
Attacks that exploit this kind of access
Delete a memory by its ID. It is categorised as a Destructive tool in the MCP Router MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Router 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 MCP Router. 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 MCP Router MCP server (justinpreston/mcp-router). 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 →