Create multiple tasks in a single call by providing a map of absolute task IDs to task specs. Use this instead of repeated create_task calls when you want to lay out an entire plan or sub-tree at once. IDs are hierarchical addresses (
AI agents use provision_tasks to create or update resources in Conductor — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Conductor environment.
This tool creates new tasks in a hierarchical task tree structure, which is a reversible data modification (Write category). Severity is high because bulk creation of tasks could cause significant operational overhead, confusion in task tracking, or resource exhaustion if misused by an agent, though the action itself is not destructive or financial.
From the tool's definition Tool description states 'Create multiple tasks in a single call' and 'lay out an entire plan or sub-tree at once'. The action is creational (Write), modifying the persistent task tree structure.
Documented attack patterns abuse exactly the kind of access provision_tasks gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Conductor, and nothing reaches the server without passing your rules. This is the rule we recommend for provision_tasks:
{
"version": "1",
"default": "deny",
"tools": {
"provision_tasks": {
"limits": [
{
"counter": "provision_tasks_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}provision_tasks 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 multiple tasks in a single call by providing a map of absolute task IDs to task specs. Use this instead of repeated create_task calls when you want to lay out an entire plan or sub-tree at once. IDs are hierarchical addresses (. It is categorised as a Write tool in the Conductor MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Conductor MCP server in PolicyLayer and add a rule for provision_tasks: 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 Conductor. Nothing to install.
provision_tasks 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 provision_tasks 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 provision_tasks. 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.
provision_tasks is provided by the Conductor MCP server (shannonbay/conductor). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Conductor, 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.
16 Conductor tools catalogued and risk-classified — across an index of 43,000+ MCP servers.