Comprehensive task management for Todoist - create, read, update, delete, and query tasks (including completed tasks) with full CRUD operations and batch support
AI agents call todoist_tasks to permanently remove resources in Mcp Todoist — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
While the tool includes Read (query tasks) and Write (create, update) operations, it also explicitly supports delete operations on tasks, which is irreversible. Delete/destroy operations take precedence in the severity hierarchy over reversible modifications. The high severity reflects that an AI agent with this tool could permanently remove user task data without recovery.
From the tool's definition Tool description explicitly states "create, read, update, delete" and "full CRUD operations" including delete capability. The delete operation on tasks is irreversible data destruction.
Documented attack patterns abuse exactly the kind of access todoist_tasks gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Todoist, and nothing reaches the server without passing your rules. This is the rule we recommend for todoist_tasks:
{
"version": "1",
"default": "deny",
"hide": [
"todoist_tasks"
]
} todoist_tasks disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Comprehensive task management for Todoist - create, read, update, delete, and query tasks (including completed tasks) with full CRUD operations and batch support. It is categorised as a Destructive tool in the Mcp Todoist MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Todoist MCP server in PolicyLayer and add a rule for todoist_tasks: 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 Mcp Todoist. Nothing to install.
todoist_tasks 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 todoist_tasks 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 todoist_tasks. 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.
todoist_tasks is provided by the Mcp Todoist MCP server (shayonpal/mcp-todoist). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Todoist, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 Mcp Todoist tools catalogued and risk-classified — across an index of 43,000+ MCP servers.