Delete a specific state entry by namespace+key, or all entries in a namespace. First call without delete_token to preview what will be deleted. Then call with the returned delete_token to execute.\n\nIf this is your first memory operation in this conversation, call memory_orient first.
AI agents call memory_delete to permanently remove resources in Munin Memory — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently removes data from user-controlled storage with no undo mechanism. While the preview-then-execute pattern mitigates accidental misuse, the core function is irreversible deletion. An AI agent with malicious intent or poor instruction could delete all stored context/memory, causing data loss.
From the tool's definition Tool name contains 'delete'; description explicitly states 'Delete a specific state entry' and 'all entries in a namespace' with execution via delete_token. This is irreversible data removal from a persistent SQLite database.
Attacks that exploit this kind of access
Delete a specific state entry by namespace+key, or all entries in a namespace. First call without delete_token to preview what will be deleted. Then call with the returned delete_token to execute.\n\nIf this is your first memory operation in this conversation, call memory_orient first. It is categorised as a Destructive tool in the Munin Memory MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Munin 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 Munin 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 Munin Memory MCP server (magnus-gille/munin-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
memory_delete is one line of Munin 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 →