Open or close the water shutoff valve (Phyn Plus only)
AI agents invoke shutoff_valve to trigger actions in Home Controller. 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 directly actuates a physical water shutoff valve in the real world. Closing the valve cuts off water supply to the entire property (high blast radius), and opening it could flood a property if done at the wrong time.
From the tool's definition 'Open or close the water shutoff valve' — triggers a physical actuation of a real-world valve that controls water flow to the premises
Attacks that exploit this kind of access
Open or close the water shutoff valve (Phyn Plus only). It is categorised as a Execute tool in the Home Controller MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Home Controller MCP server in PolicyLayer and add a rule for shutoff_valve: 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 Home Controller. Nothing to install.
shutoff_valve 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 shutoff_valve 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 shutoff_valve. 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.
shutoff_valve is provided by the Home Controller MCP server (winsthuang/home-controller). 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 →