run_raise_child

What run_raise_child does on Pentester-MCP

AI agents invoke run_raise_child to trigger actions in Pentester-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 run_raise_child is rated High

The tool description is empty, reducing confidence slightly, but the server context and sibling tools strongly indicate this executes external commands or processes. The naming pattern and server purpose classify this as Execute rather than Write, as penetration testing tools typically trigger external operations whose effects depend on attacker-supplied arguments.

From the tool's definition Tool is on Pentester-MCP server which 'enables AI assistants to autonomously execute over 200 open-source penetration testing tools' including 'web exploitation' and 'brute-forcing'; name 'run_raise_child' suggests executing or spawning a process; sibling…

The rule that runs run_raise_child safely

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

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

Questions about run_raise_child