start_process

What start_process does on Allcanuse

AI agents invoke start_process to trigger actions in Allcanuse. 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 start_process is rated High

Starting processes is a direct code/command execution action that can trigger any external operation with unpredictable side effects depending on arguments. An AI agent given this tool could execute malicious, destructive, or unintended commands. This is critical severity due to unrestricted system-level process spawning capability and high blast radius on Windows/Linux systems.

From the tool's definition Tool name 'start_process' indicates execution of arbitrary processes on the system. Server description mentions 'command execution' and 'systematically manage local systems.' No description provided for this specific tool, but context from sibling tools…

The rule that runs start_process safely

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

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

Questions about start_process