run_device_cli_commands

What run_device_cli_commands does on Fortimanager

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.

Why run_device_cli_commands is rated High

This tool executes commands on managed FortiManager devices, which are security appliances controlling network traffic, policies, and configurations. The absence of a formal description increases risk as the command scope is unconstrained. Execution of arbitrary CLI commands on security devices can bypass policies, enable attacks, compromise network integrity, or disable protections.

From the tool's definition Tool name 'run_device_cli_commands' indicates execution of CLI commands on devices. The sibling tools (add_device_to_group, add_interface_to_zone, add_policies_to_block, add_real_device, etc.) all perform configuration and policy management on…

The rule that runs run_device_cli_commands safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Fortimanager, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For run_device_cli_commands, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_device_cli_commands": {
      "limits": [
        {
          "counter": "run_device_cli_commands_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

Questions about run_device_cli_commands