Create a new plan and open it as the active context. Use this at the start of any goal that has multiple steps, unknown complexity, or may require backtracking — before doing any work. A plan is the container for a persistent task tree that survives across sessions, so create one even if you expe...
AI agents use create_plan 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 data structures (plans) that persist and affect subsequent operations. It is reversible (plans can be deleted or archived as evidenced by the sibling tool 'archive_plan'), so it is Write rather than Destructive. The severity is medium because misuse could pollute the task tree with unnecessary plans, consume storage, or confuse the agent's workflow, but the impact is bounded and reversible.
From the tool's definition The tool description states it will 'Create a new plan' and 'open it as the active context', which are data creation and modification operations. The plan becomes a persistent container that 'survives across sessions', indicating durable state changes.
Documented attack patterns abuse exactly the kind of access create_plan 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 create_plan:
{
"version": "1",
"default": "deny",
"tools": {
"create_plan": {
"limits": [
{
"counter": "create_plan_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_plan 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 plan and open it as the active context. Use this at the start of any goal that has multiple steps, unknown complexity, or may require backtracking — before doing any work. A plan is the container for a persistent task tree that survives across sessions, so create one even if you expect to finish in a single session. 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 create_plan: 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.
create_plan 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_plan 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_plan. 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_plan 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.