start_interactsh_server

What start_interactsh_server does on Pentester-MCP

AI agents invoke start_interactsh_server 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 start_interactsh_server is rated High

This tool initiates an external service (Interactsh) that facilitates command execution and data exfiltration—core Execute-category behaviors. While the description is empty, the name combined with server context (penetration testing infrastructure) and sibling tools (execute_weevely_module, launch_xsser_gui, generate_weevely_agent) strongly indicate this triggers autonomous execution of network-based attack…

From the tool's definition Tool name 'start_interactsh_server' indicates launching an interactive shell server; Interactsh is a tool for out-of-band (OOB) command execution and data exfiltration commonly used in penetration testing.

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

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

Questions about start_interactsh_server