get_device_health
AI agents call get_device_health to retrieve information from Zencontrol Cloud without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries device health status information from a DALI-2 lighting system. Even if health monitoring involved remote operations, 'get_device_health' indicates passive status retrieval rather than control. A health query has minimal blast radius if misused by an AI agent—it would only retrieve status information without modifying system state.
From the tool's definition Tool name 'get_device_health' follows a 'get_' prefix pattern consistent with other Read operations on the server (get_live_light_levels, get_scope, get_sensor_readings, get_site_details, get_system_variables).
Attacks that exploit this kind of access
get_device_health. It is categorised as a Read tool in the Zencontrol Cloud MCP Server, which means it retrieves data without modifying state.
Register the Zencontrol Cloud MCP server in PolicyLayer and add a rule for get_device_health: 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 Zencontrol Cloud. Nothing to install.
get_device_health 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_health 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_health. 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_health is provided by the Zencontrol Cloud MCP server (owretch/zencontrol-cloud-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 →