AI agents invoke tools_katana to trigger actions in Zebbern Kali 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.
Despite an empty description, the server context makes clear this is an offensive security tool. 'Katana' in the Kali Linux ecosystem refers to a fast web crawler/attack surface discovery tool. Given the sibling tools (credential dumping, password spraying, remote execution), this tool likely executes active reconnaissance or attack operations against target systems.
From the tool's definition Tool is part of 'Zebbern Kali MCP', a Kali Linux penetration testing toolkit. Katana is a well-known offensive security tool (fast web crawler/scanner by ProjectDiscovery, or the katana framework).
Documented attack patterns abuse exactly the kind of access tools_katana gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Zebbern Kali MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for tools_katana:
{
"version": "1",
"default": "deny",
"tools": {
"tools_katana": {
"limits": [
{
"counter": "tools_katana_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}tools_katana 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.
Free to start. No card required.
tools_katana. It is categorised as a Execute tool in the Zebbern Kali MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Zebbern Kali MCP server in PolicyLayer and add a rule for tools_katana: 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 Zebbern Kali MCP. Nothing to install.
tools_katana is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the tools_katana 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.
Set action: deny in the PolicyLayer policy for tools_katana. 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.
tools_katana is provided by the Zebbern Kali MCP server (zebbern/zebbern-kali-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 128 Zebbern Kali MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
128 Zebbern Kali MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.