Health check
AI agents call unifi_health_check to retrieve information from Garza Home MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Health checks are monitoring operations that report on system state. They retrieve data about UniFi infrastructure health (sensors, cameras, network status) with no capacity to modify settings, execute actions, or cause harm. This is a non-intrusive read operation typical of diagnostic/observability tools.
From the tool's definition Tool name 'unifi_health_check' and description 'Health check' indicate a diagnostic query that retrieves system status without modification or side effects.
Attacks that exploit this kind of access
Health check. It is categorised as a Read tool in the Garza Home MCP MCP Server, which means it retrieves data without modifying state.
Register the Garza Home MCP server in PolicyLayer and add a rule for unifi_health_check: 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 Garza Home MCP. Nothing to install.
unifi_health_check 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 unifi_health_check 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 unifi_health_check. 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.
unifi_health_check is provided by the Garza Home MCP server (itsablabla/garza-home-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 →