Delete memory with automatic cache invalidation
AI agents call delete_memory to permanently remove resources in r3 (Recall) — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes stored memories from the system. While the data domain is application memory rather than critical business data, deletion operations are irreversible and cannot be undone by normal means. An AI agent with unsupervised access could inadvertently wipe important long-term context or user memories.
From the tool's definition Tool name is 'delete_memory' with description 'Delete memory with automatic cache invalidation'. The verb 'delete' indicates irreversible removal of data. The mention of 'automatic cache invalidation' confirms the operation has persistent side effects.
Attacks that exploit this kind of access
Delete memory with automatic cache invalidation. It is categorised as a Destructive tool in the r3 (Recall) MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the r3 (Recall) MCP server in PolicyLayer and add a rule for 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 r3 (Recall). Nothing to install.
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 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 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.
delete_memory is provided by the r3 (Recall) MCP server (n3wth/r3). 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 →