input_select_control
AI agents use input_select_control to create or update resources in Homeassistant — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Homeassistant environment.
In Home Assistant, input_select entities are user-defined option lists used to drive automations and logic. Controlling one likely means setting/changing its selected option, which is a reversible write operation. However, the empty description prevents certainty about the full scope of the tool. Misuse could trigger unintended automations, hence medium severity.
From the tool's definition Tool name 'input_select_control' suggests controlling an input_select entity in Home Assistant (a dropdown/option selector). Description is empty, lowering confidence.
Attacks that exploit this kind of access
input_select_control. It is categorised as a Write tool in the Homeassistant MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Homeassistant MCP server in PolicyLayer and add a rule for input_select_control: 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 Homeassistant. Nothing to install.
input_select_control 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 input_select_control 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 input_select_control. 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.
input_select_control is provided by the Homeassistant MCP server (robbrad/homeassistant-mcp). 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 →