Route a natural-language-like smart-home request to the best product tool.
AI agents invoke control_by_intent 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 interprets natural language commands and routes them to device control tools, effectively executing arbitrary smart home actions (turning devices on/off, changing settings, triggering scenes). Since it can invoke any available tool including control_device and execute_scene, its blast radius is high — a misrouted or malicious command could affect multiple devices across the home.
From the tool's definition 'Route a natural-language-like smart-home request to the best product tool' — executes actions on smart home devices based on interpreted intent
Documented attack patterns abuse exactly the kind of access control_by_intent 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 control_by_intent:
{
"version": "1",
"default": "deny",
"tools": {
"control_by_intent": {
"limits": [
{
"counter": "control_by_intent_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}control_by_intent 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.
Route a natural-language-like smart-home request to the best product tool. 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 control_by_intent: 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.
control_by_intent 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 control_by_intent 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 control_by_intent. 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.
control_by_intent 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.