Alterna el estado de una luz (encendida ↔ apagada).
AI agents use alternar_luz to create or update resources in MCP Domotica Backend — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Domotica Backend environment.
This tool toggles a smart home light between on and off states. It modifies the state of a device reversibly (the action can be undone by toggling again), placing it in the Write category. The blast radius is low as it only affects a single light in the smart home environment.
From the tool's definition Alterna el estado de una luz (encendida ↔ apagada) — toggles a light on or off
Attacks that exploit this kind of access
Alterna el estado de una luz (encendida ↔ apagada). It is categorised as a Write tool in the MCP Domotica Backend MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Domotica Backend MCP server in PolicyLayer and add a rule for alternar_luz: 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 MCP Domotica Backend. Nothing to install.
alternar_luz 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 alternar_luz 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 alternar_luz. 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.
alternar_luz is provided by the MCP Domotica Backend MCP server (mcp-domotica/mcp-domotica-backend). 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 →