katana_scan · Kali MCP: Risk & Policy

WHAT IT DOES

What katana_scan does on Kali

AI agents invoke katana_scan to trigger actions in Kali. 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 katana_scan needs a policy

Katana is a web crawling and attack surface discovery tool used in penetration testing. The tool executes katana with arbitrary user-provided parameters on a Kali Linux server. This constitutes code/tool execution with potentially broad scope — crawling external or internal targets. The blast radius is high as it can be directed at unintended targets or used to map infrastructure aggressively.

From the tool's definition 'Execute katana with the provided parameters' on a Kali Linux MCP server supporting 'network scanning, web scanning, password attacks'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

katana_scan Rate-limited

katana_scan 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": {
    "katana_scan": {
      "limits": [
        {
          "counter": "katana_scan_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 Kali, so you can run agents against it safely.

FAQ

Questions about katana_scan

What does the katana_scan tool do? +

Execute katana with the provided parameters. It is categorised as a Execute tool in the Kali MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on katana_scan? +

Register the Kali MCP server in PolicyLayer and add a rule for katana_scan: 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 Kali. Nothing to install.

What risk level is katana_scan? +

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

Can I rate-limit katana_scan? +

Yes. Add a rate_limit block to the katana_scan 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 katana_scan completely? +

Set action: deny in the PolicyLayer policy for katana_scan. 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 katana_scan? +

katana_scan is provided by the Kali MCP server (pentestt00ls/kali-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.