Medium Risk

scene_adjust_light

PREFERRED for controlling lights. Turn on/off, set brightness (0-100%), RGB color, color temperature (Kelvin), or effects. IMPORTANT: This only changes the light's current state - it does NOT save to any scene. REQUIRES user_confirmed=true - user must explicitly request the change.

Part of the Ha server.

scene_adjust_light can modify Ha data, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE HA →

Free to start. No card required.

AI agents use scene_adjust_light to create or modify resources in Ha. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call scene_adjust_light repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Ha.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

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

See the full Ha policy for all 11 tools.

Get this rule live on your own Ha server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY HA →

View all 11 tools →

These attack patterns abuse exactly the kind of access scene_adjust_light gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so scene_adjust_light only ever does what you allow.

SECURE HA →

Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the scene_adjust_light tool do? +

PREFERRED for controlling lights. Turn on/off, set brightness (0-100%), RGB color, color temperature (Kelvin), or effects. IMPORTANT: This only changes the light's current state - it does NOT save to any scene. REQUIRES user_confirmed=true - user must explicitly request the change.. It is categorised as a Write tool in the Ha MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on scene_adjust_light? +

Register the Ha MCP server in PolicyLayer and add a rule for scene_adjust_light: 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 Ha. Nothing to install.

What risk level is scene_adjust_light? +

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

Can I rate-limit scene_adjust_light? +

Yes. Add a rate_limit block to the scene_adjust_light 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 scene_adjust_light completely? +

Set action: deny in the PolicyLayer policy for scene_adjust_light. 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 scene_adjust_light? +

scene_adjust_light is provided by the Ha MCP server (ha-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Ha tool call.

Deterministic rules across all 11 Ha tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.