Manage HomeKit accessories: list all, get details, search by name/room/category, or control (set characteristic values). Returns only accessories visible under the current filter configuration. Defaults to configured home if home_id not specified.
AI agents invoke homekit_accessories to trigger actions in HomeClaw. 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.
While the tool supports read operations (list, get details, search), it also explicitly supports controlling accessories by setting characteristic values. This constitutes executing real-world actions on physical smart home devices. The most severe applicable category is Execute. Severity is high because misuse could affect physical security (locks), safety (alarms, HVAC), or privacy in a home environment.
From the tool's definition 'control (set characteristic values)' — the tool can both query and actively control HomeKit accessories by setting characteristic values, which triggers real-world physical effects (e.g., turning on lights, unlocking doors, adjusting thermostats).
Documented attack patterns abuse exactly the kind of access homekit_accessories gives an agent:
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_accessories:
{
"version": "1",
"default": "deny",
"tools": {
"homekit_accessories": {
"limits": [
{
"counter": "homekit_accessories_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}homekit_accessories 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.
Free to start. No card required.
Manage HomeKit accessories: list all, get details, search by name/room/category, or control (set characteristic values). Returns only accessories visible under the current filter configuration. 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.
Register the HomeClaw MCP server in PolicyLayer and add a rule for homekit_accessories: 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.
homekit_accessories is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the homekit_accessories 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.
Set action: deny in the PolicyLayer policy for homekit_accessories. 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.
homekit_accessories 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.
Deterministic rules across all 10 HomeClaw tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
10 HomeClaw tools catalogued and risk-classified — across an index of 42,500+ MCP servers.