Request to delete a memory. Requires confirmation via remember_confirm. ⚠️ IMPORTANT: This is a two-step process: 1. Call remember_delete_memory to request deletion (returns token) 2. User must confirm via remember_confirm with the token The memory will be soft-deleted (marked as deleted but not ...
AI agents call remember_delete_memory to permanently remove resources in Remember — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although soft-deletion preserves data at the database level for recovery, from a user and application perspective this tool irreversibly removes memories from active access. This is a classic destructive operation that cannot be undone without explicit recovery procedures outside normal tool use. In a multi-tenant system, an agent misusing this could delete another user's memories in bulk, causing data loss.
From the tool's definition Tool name is 'remember_delete_memory' and description states 'Request to delete a memory' and 'memory will be soft-deleted (marked as deleted but not removed from database)'.
Attacks that exploit this kind of access
Request to delete a memory. Requires confirmation via remember_confirm. ⚠️ IMPORTANT: This is a two-step process: 1. Call remember_delete_memory to request deletion (returns token) 2. User must confirm via remember_confirm with the token The memory will be soft-deleted (marked as deleted but not removed from database). Examples: -. It is categorised as a Destructive tool in the Remember MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Remember MCP server in PolicyLayer and add a rule for remember_delete_memory: 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 Remember. Nothing to install.
remember_delete_memory 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 remember_delete_memory 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 remember_delete_memory. 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.
remember_delete_memory is provided by the Remember MCP server (@prmichaelsen/remember-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 →