AI agents invoke execute_scene 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 runs pre-defined automation routines on real smart home devices, which can have significant physical consequences (e.g., unlocking doors, turning off lights/heating, triggering alarms). The outcome depends entirely on what scene is invoked.
From the tool's definition Tool name is "execute_scene" and description states "Execute a scene" — this directly triggers external operations (smart home automation sequences).
Documented attack patterns abuse exactly the kind of access execute_scene 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 execute_scene:
{
"version": "1",
"default": "deny",
"tools": {
"execute_scene": {
"limits": [
{
"counter": "execute_scene_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute_scene 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.
Execute a scene by friendly name or scene id. 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 execute_scene: 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.
execute_scene 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 execute_scene 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 execute_scene. 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.
execute_scene 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.