homekit_scenes

THE RISK

High Risk

While the tool also supports read operations (list and get details), the capability to trigger scenes makes this primarily an Execute tool. Triggering a scene causes the smart home system to perform actions whose effects depend on the scene's configuration—potentially affecting security (unlocking doors), comfort (changing temperature), or convenience.

From the tool's definition The tool can 'trigger HomeKit scenes,' which executes predefined action sets that may control multiple smart home devices (lights, locks, thermostats, etc.) simultaneously. Triggering scenes causes immediate external effects on physical devices.

Documented attack patterns abuse exactly the kind of access homekit_scenes gives an agent:

HOW TO CONTROL HOMEKIT_SCENES

PolicyLayer is an MCP gateway — it sits between your AI agents and HomeClaw, and nothing reaches the server without passing your rules. This is the rule we recommend for homekit_scenes:

policy.json

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

homekit_scenes 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.

Create a free account and register HomeClaw — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

More HomeClaw tools

Destructive homekit_webhook Manage webhook configuration for pushing HomeKit events to OpenClaw or other services. Act Execute homekit_automations Manage HomeKit automations. List existing automations, inspect their events and linked sce Execute homekit_accessories Manage HomeKit accessories: list all, get details, search by name/room/category, or contro Write homekit_config View or update HomeClaw configuration. Set a default home, or configure device filtering t Write homekit_manage Manage HomeKit structure: rename accessories, assign rooms (with UUID support for duplicat Read homekit_device_map Get an LLM-optimized device map organized by home/zone/room with semantic types, auto-gene Read homekit_events Get recent HomeKit events — characteristic changes, scene triggers, and accessory control Read homekit_rooms List HomeKit rooms and their accessories. Defaults to configured home if home_id not speci

All 10 HomeClaw tools →

Execute tools on other servers

Frida Game Hacking MCP remove_breakpoint Procmon request_elevation WireMCP capture_packets Pentest Ai run_probe

Go deeper

High-risk tools in HomeClaw → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

What does the homekit_scenes tool do? +

List, get details of, or trigger HomeKit scenes (action sets). Defaults to configured home if home_id not specified. It is categorised as a Execute tool in the HomeClaw MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on homekit_scenes? +

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

What risk level is homekit_scenes? +

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

Can I rate-limit homekit_scenes? +

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

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

homekit_scenes is provided by the HomeClaw MCP server (omarshahine/homeclaw). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every HomeClaw tool call.

Deterministic rules across all 10 HomeClaw tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

GOVERN HOMECLAW →

Free to start. No card required.

10 HomeClaw tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// WHAT HOMEKIT_SCENES ON HOMECLAW DOES

// THE RISK

// HOW TO CONTROL HOMEKIT_SCENES

// EXPLORE