Decompose a large task into smaller subtasks. This tool helps break down complex tasks into manageable subtasks. Subtasks can be linked with sequential dependencies and grouped by tag. Note: Taskdog does not have parent-child relationships. Instead, use dependencies + tags + notes to express rela...
AI agents use decompose_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.
This tool creates multiple new data records (subtasks) as a result of decomposing an existing task. While the operation is reversible (subtasks can be deleted via delete_task), it modifies the task structure by adding new entities to the database. This is characteristic of Write category operations.
From the tool's definition Tool description states it 'helps break down complex tasks into manageable subtasks' and takes a task_id to decompose along with a list of subtask definitions to create.
Documented attack patterns abuse exactly the kind of access decompose_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 decompose_task:
{
"version": "1",
"default": "deny",
"tools": {
"decompose_task": {
"limits": [
{
"counter": "decompose_task_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}decompose_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.
Decompose a large task into smaller subtasks. This tool helps break down complex tasks into manageable subtasks. Subtasks can be linked with sequential dependencies and grouped by tag. Note: Taskdog does not have parent-child relationships. Instead, use dependencies + tags + notes to express relationships. Args: task_id: ID of the original task to decompose subtasks: List of subtask definitions, each with: - name: Subtask name (required) - estimated_duration: Hours to complete (required) - priority: Priority level (optional, inherits from original) - tags: Additional tags (optional) group_tag: Tag to add to all subtasks for grouping (e.g., 'feature-x') create_dependencies: If True, create sequential dependencies archive_original: If True, archive the original task after decomposition Returns: Decomposition result with created subtask IDs. 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 decompose_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.
decompose_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 decompose_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 decompose_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.
decompose_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.