Create a new task. Args: name: Task name (required) priority: Task priority (higher = more important, default from config) deadline: Deadline in ISO format with time (e.g., '2025-12-11T18:00:00') estimated_duration: Estimated duration in hours (e.g., 0.5 = 30min, 1.5 = 1h30m) tags: List of tags f...
AI agents use create_task to create or update resources in Taskdog — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Taskdog environment.
Creating a task is a reversible write operation—it adds new data to the system without modifying or deleting existing data. The blast radius is low because task creation itself does not execute code, move money, or irreversibly destroy data. If an AI agent were to misuse this by creating excessive tasks or tasks with malicious metadata, the impact would be contained and the tasks could be deleted.
From the tool's definition Tool creates a new task with parameters like name, priority, deadline, tags, and planned times. The description explicitly states 'Create a new task,' which is a write operation that adds data to the task management system.
Documented attack patterns abuse exactly the kind of access create_task gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Taskdog, and nothing reaches the server without passing your rules. This is the rule we recommend for create_task:
{
"version": "1",
"default": "deny",
"tools": {
"create_task": {
"limits": [
{
"counter": "create_task_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_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.
Create a new task. Args: name: Task name (required) priority: Task priority (higher = more important, default from config) deadline: Deadline in ISO format with time (e.g., '2025-12-11T18:00:00') estimated_duration: Estimated duration in hours (e.g., 0.5 = 30min, 1.5 = 1h30m) tags: List of tags for categorization is_fixed: Whether schedule is fixed (won't be moved by optimizer) planned_start: Planned start datetime in ISO format (e.g., '2025-12-11T09:00:00') planned_end: Planned end datetime in ISO format (e.g., '2025-12-11T17:00:00') Returns: Created task data with ID. It is categorised as a Write tool in the Taskdog MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Taskdog MCP server in PolicyLayer and add a rule for create_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 Taskdog. Nothing to install.
create_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 create_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 create_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.
create_task is provided by the Taskdog MCP server (kohei-wada/taskdog). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Taskdog, 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.
26 Taskdog tools catalogued and risk-classified — across an index of 43,000+ MCP servers.