start_interactive | PolicyLayer

WHAT IT DOES

What start_interactive does on K-MCP: Kali Model Context Protocol Server

AI agents invoke start_interactive to trigger actions in K-MCP: Kali Model Context Protocol 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 IT NEEDS A POLICY

Why start_interactive needs a policy

This tool allows starting interactive shell sessions on a Kali Linux system, which is fundamentally an Execute operation. In the context of a penetration testing platform with attack-focused siblings (WinRM connections, credential cracking, brute force attacks), this represents critical risk: an AI agent could execute arbitrary system commands, launch attacks, modify system state, or chain exploits.

From the tool's definition Tool name 'start_interactive' and description 'Start an interactive session for a command that requires continuous interaction' combined with sibling tools like 'evil_winrm_connect', 'hydra_attack', 'john_crack', and 'execute_command' on a Kali Linux…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_interactive Rate-limited

start_interactive stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches K-MCP: Kali Model Context Protocol Server, so you can run agents against it safely.

FAQ

Questions about start_interactive

What does the start_interactive tool do? +

Start an interactive session for a command that requires continuous interaction. It is categorised as a Execute tool in the K-MCP: Kali Model Context Protocol Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_interactive? +

Register the K-MCP: Kali Model Context Protocol Server MCP server in PolicyLayer and add a rule for start_interactive: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches K-MCP: Kali Model Context Protocol Server. Nothing to install.

What risk level is start_interactive? +

start_interactive is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit start_interactive? +

Yes. Add a rate_limit block to the start_interactive rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block start_interactive completely? +

Set action: deny in the PolicyLayer policy for start_interactive. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides start_interactive? +

start_interactive is provided by the K-MCP: Kali Model Context Protocol Server MCP server (stoicmehedi/k-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.