Get detailed status of a specific water heater (temperature, mode, online status)
AI agents call get_device_status to retrieve information from Home Controller without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves current operational information about a water heater device (temperature, mode, online status) without performing any actions, triggering operations, or modifying state. It is a straightforward query operation with no side effects, fitting the 'Read' category.
From the tool's definition Tool name 'get_device_status' and description 'Get detailed status of a specific water heater (temperature, mode, online status)' indicate pure data retrieval with no modification or execution capability.
Attacks that exploit this kind of access
Get detailed status of a specific water heater (temperature, mode, online status). It is categorised as a Read tool in the Home Controller MCP Server, which means it retrieves data without modifying state.
Register the Home Controller MCP server in PolicyLayer and add a rule for get_device_status: 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.
get_device_status is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_device_status 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 get_device_status. 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.
get_device_status 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 →