AI agents use set_brightness to create or update resources in 米家 MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your 米家 MCP Server environment.
This tool modifies a device property (brightness) on a smart home device. It creates a reversible change to device state — brightness can be changed back. No code execution, deletion, or financial transaction is involved. Severity is medium because misuse could affect home lighting environments, but the impact is reversible and limited.
From the tool's definition Set device brightness
Documented attack patterns abuse exactly the kind of access set_brightness 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 set_brightness:
{
"version": "1",
"default": "deny",
"tools": {
"set_brightness": {
"limits": [
{
"counter": "set_brightness_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}set_brightness stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Set device brightness. It is categorised as a Write tool in the 米家 MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the 米家 MCP Server MCP server in PolicyLayer and add a rule for set_brightness: 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.
set_brightness is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_brightness 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 set_brightness. 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.
set_brightness 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.