humidifier_control
AI agents invoke humidifier_control to trigger actions in Homeassistant. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool name implies controlling a humidifier device (turning on/off, setting humidity levels), which constitutes executing an action on a physical device. Given the server's purpose of controlling Home Assistant devices, this tool likely triggers real-world hardware actions. Severity is high because misuse could affect physical environment conditions (e.g., excessive humidity causing damage).
From the tool's definition Tool name 'humidifier_control' on a Home Assistant server designed to 'control Home Assistant devices and services'
Attacks that exploit this kind of access
humidifier_control. It is categorised as a Execute tool in the Homeassistant MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Homeassistant MCP server in PolicyLayer and add a rule for humidifier_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.
humidifier_control is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the humidifier_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 humidifier_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.
humidifier_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 →