todoist_complete_task
Complete (close) a Todoist task by id.
This record as markdown: /tools/io-github-malamutemayhem-unclick-mcp-server/todoist-complete-task.md
What todoist_complete_task does on UnClick
AI agents use todoist_complete_task to create or update resources in UnClick, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your UnClick environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
task_id | string | Yes | Task id to close |
api_token | string | Yes | Todoist API token |
Parameters from the server's own tool schema.
Why todoist_complete_task is rated Medium
Completing a task is a reversible write operation that changes data state. While it modifies a task record, the action can be undone (task can be reopened), distinguishing it from destructive operations. The blast radius is medium because inadvertent completion of tasks could disrupt user workflows, but the operation remains non-destructive and the effect is localized to a single task or small set of tasks.
From the tool's definition Tool name explicitly states 'complete_task' and description confirms it 'Close[s] a Todoist task by id.' This modifies task state from incomplete to complete.
Attacks that exploit this kind of access
The rule that runs todoist_complete_task safely
PolicyLayer is an MCP gateway: it sits between your AI agents and UnClick, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For todoist_complete_task, this is the rule to start with:
todoist_complete_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.
The button opens the PolicyLayer dashboard: create your workspace, connect UnClick, apply this rule, and every todoist_complete_task call is checked against it from then on.
Questions about todoist_complete_task
Complete (close) a Todoist task by id. It is categorised as a Write tool in the UnClick MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
todoist_complete_task accepts 2 parameters: task_id, api_token. Required: task_id, api_token. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for todoist_complete_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 UnClick. Nothing to install.
todoist_complete_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 todoist_complete_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 todoist_complete_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.
todoist_complete_task is provided by the UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on UnClick, and thousands of servers like it.
This server
Across the catalogue