system_run_command

What system_run_command does on Container-MCP

AI agents invoke system_run_command to trigger actions in Container-MCP. 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 system_run_command is rated High

system_run_command permits execution of shell commands with effects that depend entirely on the arguments provided. This is a classic Execute category tool. Given the absence of a description, confidence is slightly below 1.0, but the explicit function (run_command) and server context make this classification high confidence.

From the tool's definition Tool name 'system_run_command' indicates execution of arbitrary system commands. No description provided, but the name alone and the context of a container-based MCP server with explicit mention of 'safely execute code, run commands' establishes this as a…

Risk signalsAdmin/system-level operation

The rule that runs system_run_command safely

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

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

Questions about system_run_command