Turn the controller standby on or off. When disabled, schedules will not run.
AI agents use set_device_enabled to create or update resources in Home Controller — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Home Controller environment.
This tool modifies the enabled/disabled state of a device controller, which is a reversible write operation. Disabling it prevents schedules from running, which could disrupt home automation routines, but the action can be undone by re-enabling it. No data is deleted and no financial transactions occur.
From the tool's definition Turn the controller standby on or off. When disabled, schedules will not run.
Attacks that exploit this kind of access
Turn the controller standby on or off. When disabled, schedules will not run. It is categorised as a Write tool in the Home Controller MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Home Controller MCP server in PolicyLayer and add a rule for set_device_enabled: 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 Home Controller. Nothing to install.
set_device_enabled 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 set_device_enabled 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 set_device_enabled. 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.
set_device_enabled is provided by the Home Controller MCP server (winsthuang/home-controller). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →