tuya_send_command · Tuya MCP: Risk & Policy

WHAT IT DOES

What tuya_send_command does on Tuya

AI agents invoke tuya_send_command to trigger actions in Tuya. 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.

WHY IT NEEDS A POLICY

Why tuya_send_command needs a policy

This tool executes arbitrary custom commands on smart home devices. Because commands are fully user-defined JSON, an AI agent could trigger any device function — including potentially dangerous actions (e.g., unlocking smart locks, disabling security cameras, controlling smart appliances).

From the tool's definition Send custom commands to a Tuya device... commands must be a JSON string like: [{"code": "switch_1", "value": true}]

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

tuya_send_command Rate-limited

tuya_send_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "tuya_send_command": {
      "limits": [
        {
          "counter": "tuya_send_command_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Tuya, so you can run agents against it safely.

FAQ

Questions about tuya_send_command

What does the tuya_send_command tool do? +

Send custom commands to a Tuya device by device_id or name (e.g. 'Living Room Light'). commands must be a JSON string like: [{"code": "switch_1", "value": true}]. It is categorised as a Execute tool in the Tuya MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on tuya_send_command? +

Register the Tuya MCP server in PolicyLayer and add a rule for tuya_send_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 Tuya. Nothing to install.

What risk level is tuya_send_command? +

tuya_send_command is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit tuya_send_command? +

Yes. Add a rate_limit block to the tuya_send_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.

How do I block tuya_send_command completely? +

Set action: deny in the PolicyLayer policy for tuya_send_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.

What MCP server provides tuya_send_command? +

tuya_send_command is provided by the Tuya MCP server (juanmartinsantos/mcp-server-tuya). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.