Zabbix API 연결 상태와 버전을 확인합니다.
AI agents call zabbix_health to retrieve information from Zabbix MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool only retrieves and reports Zabbix system health and version metadata. It has no side effects, does not execute arbitrary operations, and does not modify or delete data. This is a straightforward information-retrieval operation typical of monitoring and diagnostic tools, presenting minimal risk.
From the tool's definition Tool description states it 'checks Zabbix API connection status and version' (translated from Korean). This is a read-only query operation that retrieves diagnostic information without modifying any data or triggering external actions.
Attacks that exploit this kind of access
Zabbix API 연결 상태와 버전을 확인합니다. It is categorised as a Read tool in the Zabbix MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Zabbix MCP Server MCP server in PolicyLayer and add a rule for zabbix_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 Zabbix MCP Server. Nothing to install.
zabbix_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 zabbix_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 zabbix_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.
zabbix_health is provided by the Zabbix MCP Server MCP server (mchlkim/zabbix-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 →