Run directory enumeration with dirb on whitelisted targets.
AI agents invoke dirb_scan to trigger actions in Kali Pentest 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.
dirb_scan actively runs the dirb penetration testing utility, which sends HTTP requests to enumerate directories and files on a target web server. This is an active operation that triggers external network traffic and interactions with third-party systems, placing it firmly in the Execute category.
From the tool's definition 'Run directory enumeration with dirb on whitelisted targets' — actively executes the dirb tool against a target system
Attacks that exploit this kind of access
Run directory enumeration with dirb on whitelisted targets. It is categorised as a Execute tool in the Kali Pentest MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Kali Pentest MCP Server MCP server in PolicyLayer and add a rule for dirb_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 Pentest MCP Server. Nothing to install.
dirb_scan 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 dirb_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.
Set action: deny in the PolicyLayer policy for dirb_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.
dirb_scan is provided by the Kali Pentest MCP Server MCP server (salmanfaris7/kali-pentest-mcp-server). 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 →