Delete a task
AI agents call delete_task to permanently remove resources in Calendar Mcp — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of tasks is a destructive operation that cannot be undone. Once deleted, the task data is lost. This falls under the Destructive category per the classification rules, as it irreversibly removes data. Severity is high because unintended deletion of important tasks could disrupt user workflows, though the blast radius is limited to calendar/task data rather than system-wide or financial impacts.
From the tool's definition Tool name is 'delete_task' with description 'Delete a task'. The verb 'delete' in both name and description indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete a task. It is categorised as a Destructive tool in the Calendar Mcp MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Calendar MCP server in PolicyLayer and add a rule for delete_task: 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 Calendar Mcp. Nothing to install.
delete_task 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_task 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_task. 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_task is provided by the Calendar MCP server (ydrogen/calendar-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 →