Delete an event.
AI agents call delete_event to permanently remove resources in Gcalendar — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a calendar event is a destructive action that cannot be undone through normal tool operations. Once deleted, the event and its details are lost. This poses a high blast radius if an AI agent incorrectly identifies and deletes important calendar events based on misunderstanding user intent or hallucination about which events to target.
From the tool's definition Tool name is 'delete_event' with description 'Delete an event.' The verb 'delete' combined with calendar event context indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete an event. It is categorised as a Destructive tool in the Gcalendar MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Gcalendar MCP server in PolicyLayer and add a rule for delete_event: 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 Gcalendar. Nothing to install.
delete_event 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_event 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_event. 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_event is provided by the Gcalendar MCP server (sandeepmallareddy/gcalendar-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 →