AI agents invoke gobuster_dir to trigger actions in Gobuster. 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 runs Gobuster on a remote Kali Linux host via SSH to perform brute-force enumeration of directories and files on web servers. It triggers an external operation (network scanning/brute forcing) whose effects depend on the target and wordlist arguments.
From the tool's definition 'wordlist-based brute forcing', 'Executes on remote Kali host via SSH'
Attacks that exploit this kind of access
Directory/file enumeration mode - discovers hidden directories and files on web servers using wordlist-based brute forcing. Executes on remote Kali host via SSH. It is categorised as a Execute tool in the Gobuster MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Gobuster MCP server in PolicyLayer and add a rule for gobuster_dir: 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 Gobuster. Nothing to install.
gobuster_dir 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 gobuster_dir 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 gobuster_dir. 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.
gobuster_dir is provided by the Gobuster MCP server (schwarztim/sec-gobuster-mcp). 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 →