Resolve one device and return its summary, capabilities, and common state.
AI agents call get_device to retrieve information from 米家 MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries information about a smart home device without triggering any control actions, modifications, or side effects. It falls squarely into the Read category as a data retrieval operation. Severity is low because unauthorized access to device status information poses minimal risk compared to tools that execute commands or delete data.
From the tool's definition Tool description states 'Resolve one device and return its summary, capabilities, and common state' — a retrieval operation with no modification, creation, or execution of commands.
Documented attack patterns abuse exactly the kind of access get_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 get_device:
{
"version": "1",
"default": "deny",
"tools": {
"get_device": {}
}
}get_device is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Resolve one device and return its summary, capabilities, and common state. It is categorised as a Read tool in the 米家 MCP Server MCP Server, which means it retrieves data without modifying state.
Register the 米家 MCP Server MCP server in PolicyLayer and add a rule for get_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.
get_device is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_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 get_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.
get_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.