Delete a reminder permanently.
AI agents call delete_reminder to permanently remove resources in Reminders — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently deletes reminders, which cannot be undone. This qualifies as Destructive rather than Write (which is reversible) or Execute (which may have variable effects). The 'permanently' qualifier and deletion action confirm irreversibility. Severity is high because an agent could delete many important reminders if misdirected, though the blast radius is limited to the user's reminder data on this device.
From the tool's definition Tool name and description explicitly state 'Delete a reminder permanently.' This is irreversible data destruction.
Attacks that exploit this kind of access
Delete a reminder permanently. It is categorised as a Destructive tool in the Reminders MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Reminders MCP server in PolicyLayer and add a rule for delete_reminder: 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 Reminders. Nothing to install.
delete_reminder 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_reminder 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_reminder. 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_reminder is provided by the Reminders MCP server (walalabs/reminders-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 →