High-risk tools in HomeAssistant MCP
9 of the 13 tools in HomeAssistant MCP are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
alarm_controlExecuteControl alarm systems. Arm (home, away, night), disarm, or trigger alarms.
-
automationExecuteManage Home Assistant automations. List all automations, toggle on/off, or trigger manually.
-
vacuum_controlExecuteControl robot vacuums. Start, pause, stop, return to dock, clean spot, locate.
-
climate_controlExecuteControl climate devices (thermostats, AC) in Home Assistant. List devices, get state, set HVAC mode, temperature, or fan mode.
-
cover_controlExecuteControl covers (blinds, curtains, garage doors). Open, close, stop, or set position.
-
fan_controlExecuteControl fans. Turn on/off, set speed percentage, preset modes, oscillation.
-
lock_controlExecuteControl locks. Lock, unlock, or open (for locks that support unlatching).
-
media_player_controlExecuteControl media players. Play, pause, stop, volume control, and source selection.
-
sceneExecuteManage and activate Home Assistant scenes.
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.