unlock_door · Home Controller MCP: Risk & Policy

WHAT IT DOES

What unlock_door does on Home Controller

AI agents invoke unlock_door 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 unlock_door needs a policy

Unlocking a door is an irreversible physical action (at least momentarily) that directly compromises home security. It triggers an external operation on a physical device, granting physical access to premises. Misuse by an AI agent could allow unauthorized entry, making this critical severity. It fits Execute because it triggers an external physical operation whose effect depends on which door is targeted.

From the tool's definition 'Unlock a specific door' — triggers a physical security action on a smart home device

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

unlock_door Rate-limited

unlock_door 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": {
    "unlock_door": {
      "limits": [
        {
          "counter": "unlock_door_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 unlock_door

What does the unlock_door tool do? +

Unlock a specific door. 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 unlock_door? +

Register the Home Controller MCP server in PolicyLayer and add a rule for unlock_door: 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 unlock_door? +

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

Can I rate-limit unlock_door? +

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

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

unlock_door 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.