AI agents invoke turn_on_device to trigger actions in 米家 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.
This tool executes a real-world action by powering on a physical IoT device. It is not merely reading data or writing a record; it triggers an external operation with physical effects (activating appliances, lighting, etc.). While reversible (device can be turned off), it falls under Execute due to triggering external device operations.
From the tool's definition 'Turn on a device' — triggers an external physical operation on a Xiaomi smart home device
Documented attack patterns abuse exactly the kind of access turn_on_device gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and 米家 MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for turn_on_device:
{
"version": "1",
"default": "deny",
"tools": {
"turn_on_device": {
"limits": [
{
"counter": "turn_on_device_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}turn_on_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.
Free to start. No card required.
Turn on a device. It is categorised as a Execute tool in the 米家 MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the 米家 MCP Server MCP server in PolicyLayer and add a rule for turn_on_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 米家 MCP Server. Nothing to install.
turn_on_device 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 turn_on_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.
Set action: deny in the PolicyLayer policy for turn_on_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.
turn_on_device is provided by the 米家 MCP Server MCP server (javen-yan/miot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from 米家 MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
26 米家 MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.