AI agents use tuya_set_color to create or update resources in Tuya — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tuya environment.
This tool creates or modifies device state reversibly without deleting data or executing arbitrary code. Color changes can be undone by setting different values. While it affects physical smart home devices, the operation is Write-class (state modification) rather than Execute (arbitrary operations).
From the tool's definition The tool modifies device state by setting color parameters (hue, saturation, value) on Tuya RGB lights. The description explicitly states 'Set the color' which is a reversible state change operation.
Attacks that exploit this kind of access
Set the color of a Tuya RGB light by device_id or name (e.g. 'Living Room Light') using HSV values. hue: 0-360, saturation: 0-255, value: 0-255. It is categorised as a Write tool in the Tuya MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tuya MCP server in PolicyLayer and add a rule for tuya_set_color: 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.
tuya_set_color 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 tuya_set_color 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 tuya_set_color. 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.
tuya_set_color 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →