Submit decomposed child tasks for a task.
AI agents use tasks_proposal 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 task entities (child tasks) in the persistent task tree, which is a reversible data modification operation. It does not execute arbitrary operations (Execute), permanently delete data (Destructive), or move money (Financial).
From the tool's definition Tool name 'tasks_proposal' and description 'Submit decomposed child tasks for a task' indicate creating or proposing new task records within the hierarchical task tree structure.
Documented attack patterns abuse exactly the kind of access tasks_proposal 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 tasks_proposal:
{
"version": "1",
"default": "deny",
"tools": {
"tasks_proposal": {
"limits": [
{
"counter": "tasks_proposal_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}tasks_proposal 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.
Submit decomposed child tasks for a task. 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 tasks_proposal: 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.
tasks_proposal 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 tasks_proposal 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 tasks_proposal. 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.
tasks_proposal 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.