control_device · HC3 MCP Server MCP: Risk & Policy

WHAT IT DOES

What control_device does on HC3 MCP Server

AI agents invoke control_device to trigger actions in HC3 MCP Server. 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_device needs a policy

This tool executes actions on physical devices in a smart home environment. While it's reversible in the sense that you can turn something back on/off, it triggers real-world effects (lights, locks, thermostats, etc.) that could have safety or security implications if misused. It falls under Execute as it runs operations whose effects depend on arguments and affect physical systems.

From the tool's definition 'Control a device by calling an action (e.g., turnOn, turnOff, setValue, setColor)' — triggers external operations on physical smart home devices

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

control_device Rate-limited

control_device 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_device": {
      "limits": [
        {
          "counter": "control_device_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 HC3 MCP Server, so you can run agents against it safely.

FAQ

Questions about control_device

What does the control_device tool do? +

Control a device by calling an action (e.g., turnOn, turnOff, setValue, setColor). It is categorised as a Execute tool in the HC3 MCP Server 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_device? +

Register the HC3 MCP Server MCP server in PolicyLayer and add a rule for control_device: 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 HC3 MCP Server. Nothing to install.

What risk level is control_device? +

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

Can I rate-limit control_device? +

Yes. Add a rate_limit block to the control_device 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_device completely? +

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

control_device is provided by the HC3 MCP Server MCP server (jangabrielsson/hc3_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.