🛡️ Hass Guard
Limits the agents behind Hassonic and the Octo MCP (hassonic and external) to an allowlist of Home Assistant actions, and blocks any action their decision model doesn’t rate safe.
Configuration Schema
| Field | Type | Required | Description |
|---|---|---|---|
agents | string[] | Optional | Agent IDs to guard. Defaults to ["hassonic"]. |
alertTarget | string | Optional | Where to post blocked calls, as <channel>:<target>, e.g. "discord:channel:<id>". Unset means no alerts. |
Example config
"plugins": { "entries": { "hass-guard": { "enabled": true, "config": { "agents": ["hassonic", "external"], "alertTarget": "discord:channel:<id>" } } } }
The safety check uses each guarded agent’s own decisionModel.