Permanently delete a label (tasks will keep their other labels)
AI agents call delete_label to permanently remove resources in Todoist MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes a label from the Todoist system. Although individual tasks retain their other labels, the label itself cannot be recovered once deleted. This is a destructive operation that cannot be undone, making it Destructive rather than Write.
From the tool's definition Tool name is 'delete_label' and description states 'Permanently delete a label' — the word 'Permanently' indicates irreversible data deletion.
Attacks that exploit this kind of access
Permanently delete a label (tasks will keep their other labels). It is categorised as a Destructive tool in the Todoist MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Todoist MCP Server MCP server in PolicyLayer and add a rule for delete_label: 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 Todoist MCP Server. Nothing to install.
delete_label 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_label 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_label. 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_label is provided by the Todoist MCP Server MCP server (rauf543/todoist-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 →