AI agents use close_task_tool to create or update resources in TaskMaster — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your TaskMaster environment.
Closing a task changes its status in the Todoist system but does not permanently delete or destroy data. The operation is reversible (tasks can be reopened), so it does not qualify as Destructive. It modifies data state rather than merely reading it, placing it in the Write category.
From the tool's definition The tool 'close_task_tool' with description 'Close a task in Todoist' modifies the state of an existing task by marking it as complete/closed. This is a reversible operation—tasks can typically be reopened in Todoist.
Documented attack patterns abuse exactly the kind of access close_task_tool gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and TaskMaster, and nothing reaches the server without passing your rules. This is the rule we recommend for close_task_tool:
{
"version": "1",
"default": "deny",
"tools": {
"close_task_tool": {
"limits": [
{
"counter": "close_task_tool_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}close_task_tool 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.
Close a task in Todoist. It is categorised as a Write tool in the TaskMaster MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the TaskMaster MCP server in PolicyLayer and add a rule for close_task_tool: 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 TaskMaster. Nothing to install.
close_task_tool 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_tool 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_tool. 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_tool is provided by the TaskMaster MCP server (mingolladaniele/taskmaster-todoist-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from TaskMaster, 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.
3 TaskMaster tools catalogued and risk-classified — across an index of 43,000+ MCP servers.