AI agents invoke scene 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.
Activating a scene triggers external operations — it simultaneously changes the state of multiple smart home devices (lights, climate, switches, etc.). This goes beyond a simple write to a single record; it executes a coordinated action across physical devices. Misuse could affect comfort, security, or energy systems, warranting medium severity.
From the tool's definition Manage and activate Home Assistant scenes
Documented attack patterns abuse exactly the kind of access scene 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 scene:
{
"version": "1",
"default": "deny",
"tools": {
"scene": {
"limits": [
{
"counter": "scene_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}scene 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.
Manage and activate Home Assistant scenes. 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 scene: 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.
scene 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 scene 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 scene. 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.
scene 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.