Medium Risk

lights_control

Control lights in Home Assistant. List all lights, get state of a specific light, turn lights on with brightness/color settings, or turn lights off.

How to control lights_control ↓

What lights_control does on HomeAssistant MCP

AI agents use lights_control to create or update resources in HomeAssistant MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your HomeAssistant MCP environment.

Medium Risk

Why lights_control needs a policy

This tool modifies the state of smart light devices (on/off, brightness, color). These are reversible state changes — no data is permanently deleted and no financial transactions occur. The blast radius is medium: an AI agent could disrupt lighting in a home environment, but effects are easily reversed.

From the tool's definition Control lights in Home Assistant... turn lights on with brightness/color settings, or turn lights off

Documented attack patterns abuse exactly the kind of access lights_control gives an agent:

How to control lights_control

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 lights_control:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "lights_control": {
      "limits": [
        {
          "counter": "lights_control_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

lights_control stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register HomeAssistant MCP — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about lights_control

What does the lights_control tool do? +

Control lights in Home Assistant. List all lights, get state of a specific light, turn lights on with brightness/color settings, or turn lights off. It is categorised as a Write tool in the HomeAssistant MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on lights_control? +

Register the HomeAssistant MCP server in PolicyLayer and add a rule for lights_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.

What risk level is lights_control? +

lights_control is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit lights_control? +

Yes. Add a rate_limit block to the lights_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.

How do I block lights_control completely? +

Set action: deny in the PolicyLayer policy for lights_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.

What MCP server provides lights_control? +

lights_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.

Enforce policy on every HomeAssistant MCP tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.