AI agents invoke zabbix_execute_script to trigger actions in Zabbix MCP Server. 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 triggers code execution on monitored infrastructure via the Zabbix API. Scripts can have side effects dependent on arguments (what script runs, with what parameters, on which host). The blast radius is high: a compromised AI agent could execute malicious scripts across monitored infrastructure, potentially compromising systems, exfiltrating data, or disrupting operations.
From the tool's definition Tool name 'zabbix_execute_script' and description 'Execute a script on a host in Zabbix' explicitly indicate execution of arbitrary scripts on remote hosts.
Documented attack patterns abuse exactly the kind of access zabbix_execute_script gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Zabbix MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for zabbix_execute_script:
{
"version": "1",
"default": "deny",
"tools": {
"zabbix_execute_script": {
"limits": [
{
"counter": "zabbix_execute_script_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}zabbix_execute_script stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute a script on a host in Zabbix. It is categorised as a Execute tool in the Zabbix MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Zabbix MCP Server MCP server in PolicyLayer and add a rule for zabbix_execute_script: 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_execute_script 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 zabbix_execute_script 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_execute_script. 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_execute_script is provided by the Zabbix MCP Server MCP server (leroylim/zabbix-mcp-server-nodejs). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Zabbix MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
102 Zabbix MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.