AI agents invoke run_device_cli_commands to trigger actions in Fortimanager. 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.
Running device CLI commands on production network security appliances (FortiManager manages Fortinet firewalls and security infrastructure) represents critical risk: commands could disable security policies, exfiltrate data, reconfigure network routing, compromise network segmentation, or create persistence backdoors. The blast radius encompasses entire enterprise network security posture.
From the tool's definition Tool name 'run_device_cli_commands' indicates execution of arbitrary CLI commands on network devices managed by FortiManager.
Documented attack patterns abuse exactly the kind of access run_device_cli_commands gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Fortimanager, and nothing reaches the server without passing your rules. This is the rule we recommend for run_device_cli_commands:
{
"version": "1",
"default": "deny",
"tools": {
"run_device_cli_commands": {
"limits": [
{
"counter": "run_device_cli_commands_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_device_cli_commands 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.
run_device_cli_commands. It is categorised as a Execute tool in the Fortimanager MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Fortimanager MCP server in PolicyLayer and add a rule for run_device_cli_commands: 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 Fortimanager. Nothing to install.
run_device_cli_commands 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 run_device_cli_commands 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 run_device_cli_commands. 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.
run_device_cli_commands is provided by the Fortimanager MCP server (jmpijll/fortimanager-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Fortimanager, 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.
584 Fortimanager tools catalogued and risk-classified — across an index of 43,000+ MCP servers.