AI agents invoke web_audit to trigger actions in Kali 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.
This tool actively executes security scanning and probing operations against web applications using Kali Linux's penetration testing suite. It triggers external operations (vulnerability scanning, active probing) that go well beyond passive reading — it interacts with target systems, potentially exploiting or stressing them.
From the tool's definition 'Perform a comprehensive web application audit' on a Kali Linux server with 'automated vulnerability scanning' and 'penetration testing tools'
Documented attack patterns abuse exactly the kind of access web_audit gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kali MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for web_audit:
{
"version": "1",
"default": "deny",
"tools": {
"web_audit": {
"limits": [
{
"counter": "web_audit_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}web_audit 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.
Perform a comprehensive web application audit. It is categorised as a Execute tool in the Kali MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Kali MCP Server MCP server in PolicyLayer and add a rule for web_audit: 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 MCP Server. Nothing to install.
web_audit 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 web_audit 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 web_audit. 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.
web_audit is provided by the Kali MCP Server MCP server (k3nn3dy-ai/kali-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kali MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
36 Kali MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.