Mark a Todoist task as completed. This action moves the task to the completed state while preserving all task data and history. Completed tasks can be reopened later if needed. If the task has incomplete subtasks, they will also be marked as completed. Returns confirmation of successful completion.
AI agents use close_task to create or update resources in Todoist MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Todoist MCP Server environment.
close_task modifies task state from active to completed, which is a Write operation (creates or modifies data reversibly). While the action changes task status, it preserves data and can be undone by reopening the task. Severity is medium because incorrect automated completion of many tasks could disrupt a user's workflow, but the action is reversible and affects only task state, not destruction or deletion of data.
From the tool's definition Tool description states 'Mark a Todoist task as completed' and 'moves the task to the completed state while preserving all task data and history' and 'Completed tasks can be reopened later if needed.' This is a reversible state change.
Documented attack patterns abuse exactly the kind of access close_task gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Todoist MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for close_task:
{
"version": "1",
"default": "deny",
"tools": {
"close_task": {
"limits": [
{
"counter": "close_task_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}close_task stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Mark a Todoist task as completed. This action moves the task to the completed state while preserving all task data and history. Completed tasks can be reopened later if needed. If the task has incomplete subtasks, they will also be marked as completed. Returns confirmation of successful completion. It is categorised as a Write tool in the Todoist MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Todoist MCP Server MCP server in PolicyLayer and add a rule for close_task: 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.
close_task is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the close_task 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 close_task. 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.
close_task is provided by the Todoist MCP Server MCP server (koki-develop/todoist-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Todoist MCP Server, 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.
32 Todoist MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.