run_kiterunner

What run_kiterunner does on Pentester-MCP

AI agents invoke run_kiterunner 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_kiterunner is rated High

Kiterunner is an API enumeration and exploitation tool that discovers and tests API endpoints. Running it autonomously means the MCP can execute external tools whose effects (API scanning, fuzzing, potential exploitation attempts) depend entirely on the arguments and configuration provided. This is a classic Execute pattern: code/tool invocation with argument-dependent side effects.

From the tool's definition Server description explicitly states this MCP enables 'autonomously execute over 200 open-source penetration testing tools' including 'web exploitation' and 'brute-forcing.' The tool 'run_kiterunner' is a penetration testing tool name (Kiterunner is used for…

The rule that runs run_kiterunner 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_kiterunner, this is the rule to start with:

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

Questions about run_kiterunner