Turn off a Switcher device
AI agents invoke turn_off to trigger actions in Switcher MCP Server. 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 controls a physical IoT device by turning it off, which constitutes triggering an external operation with real-world consequences (e.g., cutting power to appliances like water heaters or other connected equipment). It falls under Execute as it performs an action on an external system.
From the tool's definition Turn off a Switcher device — triggers an external physical operation on a KIS device (cutting power to a connected appliance)
Attacks that exploit this kind of access
Turn off a Switcher device. It is categorised as a Execute tool in the Switcher MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Switcher MCP Server MCP server in PolicyLayer and add a rule for turn_off: 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 Switcher MCP Server. Nothing to install.
turn_off 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 turn_off 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 turn_off. 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.
turn_off is provided by the Switcher MCP Server MCP server (liebstein/switcher-mcp). 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 →