exec_command

What exec_command does on 1Panel MCP Server

AI agents invoke exec_command to trigger actions in 1Panel 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.

Why exec_command is rated High

This tool permits execution of arbitrary shell commands on server infrastructure, which is the highest-risk Execute category operation. Misuse could compromise the entire system, modify configurations, exfiltrate data, or pivot to other systems. The blast radius is critical—an AI agent given this tool with unsafe prompting could destroy the server, install malware, or expose sensitive data.

From the tool's definition Tool name 'exec_command' with description 'Execute command' directly indicates arbitrary command execution capability. In the context of a server infrastructure management tool (1Panel), this allows running shell commands on the underlying system.

The rule that runs exec_command safely

PolicyLayer is an MCP gateway: it sits between your AI agents and 1Panel MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For exec_command, this is the rule to start with:

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

Questions about exec_command