Control alarm systems. Arm (home, away, night), disarm, or trigger alarms.
AI agents invoke alarm_control to trigger actions in HomeAssistant MCP. 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.
This tool executes commands that control a physical security system. While not strictly destructive (alarms can be disarmed), the effects are irreversible in real-time and impact physical security. Triggering an alarm or changing armed state are Execute-category operations because they invoke external system behavior.
From the tool's definition The tool performs actions that trigger external operations: "Arm (home, away, night), disarm, or trigger alarms." These are commands that execute state changes in physical alarm systems whose effects depend on the argument (arm mode or disarm/trigger).
Documented attack patterns abuse exactly the kind of access alarm_control gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and HomeAssistant MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for alarm_control:
{
"version": "1",
"default": "deny",
"tools": {
"alarm_control": {
"limits": [
{
"counter": "alarm_control_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}alarm_control stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Control alarm systems. Arm (home, away, night), disarm, or trigger alarms. It is categorised as a Execute tool in the HomeAssistant MCP 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 alarm_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 MCP. Nothing to install.
alarm_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 alarm_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 alarm_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.
alarm_control is provided by the HomeAssistant MCP server (jango-blockchained/advanced-homeassistant-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from HomeAssistant MCP, 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.
13 HomeAssistant MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.