Web content scanner looking for hidden web objects.
AI agents call dirb to retrieve information from MCP Kali Pentest without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
DIRB is a web scanner that sends HTTP requests to discover hidden directories and files on web servers. It performs reconnaissance by querying a target and analyzing responses, with no ability to modify, delete, or execute code on the target. While it could be misused for unauthorized reconnaissance, the tool itself is read-only.
From the tool's definition Tool name 'dirb' and description 'Web content scanner looking for hidden web objects' indicates directory/path enumeration via HTTP requests without modifying target systems.
Attacks that exploit this kind of access
Web content scanner looking for hidden web objects. It is categorised as a Read tool in the MCP Kali Pentest MCP Server, which means it retrieves data without modifying state.
Register the MCP Kali Pentest MCP server in PolicyLayer and add a rule for dirb: 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 MCP Kali Pentest. Nothing to install.
dirb is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the dirb 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 dirb. 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.
dirb is provided by the MCP Kali Pentest MCP server (root1856/mcpkali). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →