Create a subtask linked to a parent task. Agents call this to decompose their current work into subtasks during execution. The parent task is automatically transitioned to WAITING_FOR_SUBTASKS status. Args: parent_task_id: ID of the parent task that this subtask belongs to. goal: Description of w...
AI agents use bernstein_create_subtask to create or update resources in Bernstein - Multi-agent orchestration — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Bernstein - Multi-agent orchestration environment.
bernstein_create_subtask performs task creation and modifies parent task state, which are write operations. While it affects workflow orchestration, the operations are reversible (subtasks can be deleted or updated). Severity is medium because misuse could disrupt development workflows or create misleading task hierarchies, but doesn't execute code, delete data irreversibly, or move money.
From the tool's definition Tool creates a subtask linked to a parent task and transitions parent task status to WAITING_FOR_SUBTASKS - these are reversible data creation operations
Documented attack patterns abuse exactly the kind of access bernstein_create_subtask gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Bernstein - Multi-agent orchestration, and nothing reaches the server without passing your rules. This is the rule we recommend for bernstein_create_subtask:
{
"version": "1",
"default": "deny",
"tools": {
"bernstein_create_subtask": {
"limits": [
{
"counter": "bernstein_create_subtask_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}bernstein_create_subtask 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 subtask linked to a parent task. Agents call this to decompose their current work into subtasks during execution. The parent task is automatically transitioned to WAITING_FOR_SUBTASKS status. Args: parent_task_id: ID of the parent task that this subtask belongs to. goal: Description of what the subtask should accomplish. role: Specialist role to assign (backend, frontend, qa, …). priority: 1=critical, 2=normal, 3=nice-to-have. scope: Task scope - small, medium, or large. complexity: Task complexity - low, medium, or high. estimated_minutes: Rough time estimate in minutes. Returns: JSON with the created subtask ID, parent_task_id, title, and status. It is categorised as a Write tool in the Bernstein - Multi-agent orchestration MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Bernstein - Multi-agent orchestration MCP server in PolicyLayer and add a rule for bernstein_create_subtask: 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 Bernstein - Multi-agent orchestration. Nothing to install.
bernstein_create_subtask 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 bernstein_create_subtask 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 bernstein_create_subtask. 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.
bernstein_create_subtask is provided by the Bernstein - Multi-agent orchestration MCP server (sipyourdrink-ltd/bernstein). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 12 Bernstein - Multi-agent orchestration tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
12 Bernstein - Multi-agent orchestration tools catalogued and risk-classified — across an index of 42,500+ MCP servers.