control_light · Zencontrol Cloud MCP: Risk & Policy

WHAT IT DOES

What control_light does on Zencontrol Cloud

AI agents invoke control_light to trigger actions in Zencontrol Cloud. 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.

WHY IT NEEDS A POLICY

Why control_light needs a policy

The tool name strongly implies it sends commands to physical lighting hardware (DALI-2 systems), which is an external operation with real-world effects. This falls under Execute as it triggers external operations on physical devices. Severity is high because misuse could affect lighting in buildings (safety, operations). Confidence is reduced due to the empty description.

From the tool's definition Tool name 'control_light' on a server described as enabling control of ZenControl DALI-2 lighting systems; description is empty.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

control_light Rate-limited

control_light 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "control_light": {
      "limits": [
        {
          "counter": "control_light_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Zencontrol Cloud, so you can run agents against it safely.

FAQ

Questions about control_light

What does the control_light tool do? +

control_light. It is categorised as a Execute tool in the Zencontrol Cloud MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on control_light? +

Register the Zencontrol Cloud MCP server in PolicyLayer and add a rule for control_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 Zencontrol Cloud. Nothing to install.

What risk level is control_light? +

control_light is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit control_light? +

Yes. Add a rate_limit block to the control_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 control_light completely? +

Set action: deny in the PolicyLayer policy for control_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 control_light? +

control_light is provided by the Zencontrol Cloud MCP server (owretch/zencontrol-cloud-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.