Send a command to a device.
AI agents invoke device_command to trigger actions in Matter. 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 commands on physical IoT/Matter devices. The effects depend entirely on what command is sent and to which device (e.g., turning off locks, HVAC, lighting, appliances). This is clearly Execute category. Severity is high because misuse could affect physical-world systems including safety-critical devices like locks, thermostats, or industrial equipment.
From the tool's definition "Send a command to a device" — triggers an external operation on a physical Matter device
Documented attack patterns abuse exactly the kind of access device_command gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Matter, and nothing reaches the server without passing your rules. This is the rule we recommend for device_command:
{
"version": "1",
"default": "deny",
"tools": {
"device_command": {
"limits": [
{
"counter": "device_command_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}device_command 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.
Send a command to a device. It is categorised as a Execute tool in the Matter MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Matter MCP server in PolicyLayer and add a rule for device_command: 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 Matter. Nothing to install.
device_command 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 device_command 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 device_command. 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.
device_command is provided by the Matter MCP server (mattercoder/matter-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Matter, 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.
15 Matter tools catalogued and risk-classified — across an index of 43,000+ MCP servers.