start_schedule · Home Controller MCP: Risk & Policy

WHAT IT DOES

What start_schedule does on Home Controller

AI agents invoke start_schedule to trigger actions in Home Controller. 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 start_schedule needs a policy

This tool executes external operations on smart home devices (Miele appliances, LG ThinQ, HUUM saunas, Phyn monitors) by triggering predefined automation rules. While not destructive in itself, it performs actions whose consequences cannot be easily predicted or reversed without knowing the schedule's contents, and misuse could cause unintended device state changes, energy waste, or operational disruptions.

From the tool's definition Tool description states 'Manually trigger a schedule rule to run now' — this initiates external operations (appliance actions, device state changes) whose effects depend on which schedule rule is executed and what devices it controls.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_schedule Rate-limited

start_schedule 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": {
    "start_schedule": {
      "limits": [
        {
          "counter": "start_schedule_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 Home Controller, so you can run agents against it safely.

FAQ

Questions about start_schedule

What does the start_schedule tool do? +

Manually trigger a schedule rule to run now. It is categorised as a Execute tool in the Home Controller MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_schedule? +

Register the Home Controller MCP server in PolicyLayer and add a rule for start_schedule: 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 Home Controller. Nothing to install.

What risk level is start_schedule? +

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

Can I rate-limit start_schedule? +

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

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

start_schedule is provided by the Home Controller MCP server (winsthuang/home-controller). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.