katana_crawl · Bug Bounty MCP Server MCP: Risk & Policy

WHAT IT DOES

What katana_crawl does on Bug Bounty MCP Server

AI agents invoke katana_crawl to trigger actions in Bug Bounty MCP 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 katana_crawl needs a policy

This tool executes an external spider/crawler application (Katana) against targets, making it Execute rather than Read. While crawling itself is non-destructive, it constitutes running external code/operations whose effects depend on the target argument and Katana's behavior. It could cause performance issues, trigger WAF blocks, or generate suspicious traffic on targets.

From the tool's definition Tool performs 'crawling and spidering' on targets with external operational effects. Katana is a real web crawler/spider tool that makes HTTP requests, discovers endpoints, and gathers reconnaissance data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

katana_crawl Rate-limited

katana_crawl 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_crawl": {
      "limits": [
        {
          "counter": "katana_crawl_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 Bug Bounty MCP Server, so you can run agents against it safely.

FAQ

Questions about katana_crawl

What does the katana_crawl tool do? +

Run Katana for next-generation crawling and spidering with logging. It is categorised as a Execute tool in the Bug Bounty MCP 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 katana_crawl? +

Register the Bug Bounty MCP Server MCP server in PolicyLayer and add a rule for katana_crawl: 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 Bug Bounty MCP Server. Nothing to install.

What risk level is katana_crawl? +

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

Can I rate-limit katana_crawl? +

Yes. Add a rate_limit block to the katana_crawl 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_crawl completely? +

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

katana_crawl is provided by the Bug Bounty MCP Server MCP server (slanycukr/bugbounty-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.