input_number_control
AI agents use input_number_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.
Based on the name alone, this tool likely sets or adjusts a numeric input helper in Home Assistant (e.g., a slider value), which is a reversible write operation. Sibling tools like 'climate_control' and 'cover_control' follow a similar pattern of modifying device state.
From the tool's definition Tool name 'input_number_control' suggests controlling an input number entity in Home Assistant; description is empty and uninformative.
Attacks that exploit this kind of access
input_number_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_number_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_number_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_number_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_number_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_number_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.
input_number_control is one line of Homeassistant's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →