Delete a project in Todoist
AI agents call delete-project 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 irreversibly deletes data (a project and its contents) from Todoist. Deletion is a destructive operation that cannot be reversed by the tool itself. While the blast radius is limited to a single project rather than system-wide data, the permanent loss of a project's contents constitutes a high-severity destructive action that an AI agent could inadvertently trigger through misunderstanding user intent.
From the tool's definition Tool name is 'delete-project' with description 'Delete a project in Todoist'. The verb 'delete' indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete a project 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-project: 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-project 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-project 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-project. 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-project 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 →