Delete a comment from a task in Todoist
AI agents call delete-comment to permanently remove resources in Todoist MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a comment, which cannot be undone. While the blast radius is limited to a single comment (not a full task or project), deletion is irreversible and more severe than Write operations. It fits the Destructive category as it removes data that cannot be recovered through normal means.
From the tool's definition Tool name is 'delete-comment' with description 'Delete a comment from a task in Todoist' - the term 'delete' indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete a comment from a task in Todoist. It is categorised as a Destructive tool in the Todoist MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Todoist MCP server in PolicyLayer and add a rule for delete-comment: 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. Nothing to install.
delete-comment 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-comment 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-comment. 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-comment is provided by the Todoist MCP server (jdh747/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 →