Delete a specific memory by ID
AI agents call mem0_delete to permanently remove resources in VibeServe — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs a DELETE operation on stored memories by ID, which is irreversible and cannot be undone. Even though memories in a UI-generation context may be less critical than financial or operational data, deletion is a destructive action that destroys information. An AI agent misusing this could erase important context, user preferences, or system state required for proper function.
From the tool's definition Tool name 'mem0_delete' and description 'Delete a specific memory by ID' explicitly indicate irreversible deletion of data.
Attacks that exploit this kind of access
Delete a specific memory by ID. It is categorised as a Destructive tool in the VibeServe MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the VibeServe MCP server in PolicyLayer and add a rule for mem0_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 VibeServe. Nothing to install.
mem0_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 mem0_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 mem0_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.
mem0_delete is provided by the VibeServe MCP server (ncsound919/vibeserve). 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 →