Toggle the light bulb ON/OFF.
AI agents invoke light_bulb_toggle to trigger actions in Dual MCP Server for IoT & Memory. 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 triggers an external physical operation on an IoT device (toggling a light bulb), which is an execution of an action on real-world hardware. The effect is reversible (can be toggled back), so it's Execute rather than Destructive. Severity is low as the blast radius is limited to a light bulb state change.
From the tool's definition Toggle the light bulb ON/OFF
Attacks that exploit this kind of access
Toggle the light bulb ON/OFF. It is categorised as a Execute tool in the Dual MCP Server for IoT & Memory MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Dual MCP Server for IoT & Memory MCP server in PolicyLayer and add a rule for light_bulb_toggle: 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 Dual MCP Server for IoT & Memory. Nothing to install.
light_bulb_toggle 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 light_bulb_toggle 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 light_bulb_toggle. 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.
light_bulb_toggle is provided by the Dual MCP Server for IoT & Memory MCP server (jordy33/iot_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 →