Delete a task by searching for it by name. Uses partial name matching.
AI agents call delete_task_by_name to permanently remove resources in Todoist MCP Helper — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of task data is a destructive action with no rollback capability. While the blast radius is limited to individual tasks rather than entire projects/sections, the irreversible nature and potential for accidental deletion via partial name matching (matching wrong task) places this in the Destructive category at high severity.
From the tool's definition Tool name 'delete_task_by_name' explicitly performs deletion. Description states 'Delete a task' which is an irreversible operation that cannot be undone.
Attacks that exploit this kind of access
Delete a task by searching for it by name. Uses partial name matching. It is categorised as a Destructive tool in the Todoist MCP Helper MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Todoist MCP Helper MCP server in PolicyLayer and add a rule for delete_task_by_name: 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 Helper. Nothing to install.
delete_task_by_name 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_by_name 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_by_name. 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_by_name is provided by the Todoist MCP Helper MCP server (littlepeter52012/todoist-mcp-helper). 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 →