AI agents invoke control_switch to trigger actions in Plugwise. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | — | Switch model type (default: relay). Options: relay, switch, plug |
state | string | Yes | Desired state: "on" to turn on, "off" to turn off |
appliance_id | string | Yes | ID of the appliance/device to control |
Parameters from the server's own tool schema.
This tool triggers external physical operations (turning devices on/off) whose effects depend on arguments. It controls real-world hardware like smart plugs and relays, which could affect connected appliances, HVAC systems, or other critical devices. This is an Execute action with high severity because misuse could cause unintended physical consequences (e.g., turning off critical equipment).
From the tool's definition Turn a switch or relay on or off... control any switchable device in your Plugwise network
Attacks that exploit this kind of access
Turn a switch or relay on or off. Works with Plugwise switches, relays, and smart plugs. Use this to control any switchable device in your Plugwise network. It is categorised as a Execute tool in the Plugwise MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
control_switch accepts 3 parameters: model, state, appliance_id. Required: state, appliance_id. The full parameter table on this page comes from the server's own tool schema.
Register the Plugwise MCP server in PolicyLayer and add a rule for control_switch: 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 Plugwise. Nothing to install.
control_switch 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 control_switch 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 control_switch. 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.
control_switch is provided by the Plugwise MCP server (plugwise-mcp-server). 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 →