AI agents invoke whatweb_scan to trigger actions in Redteam. 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.
Although WhatWeb is a reconnaissance/fingerprinting tool (closer to Read), it runs as part of a penetration testing framework that executes active scans against external targets inside a Kali Linux container. This constitutes triggering external operations whose effects depend on arguments (the target URL).
From the tool's definition Tool runs inside a 'Kali Linux Docker container' and is part of a suite that enables 'execute security scans and attacks'; 'whatweb_scan' actively probes web applications to identify technologies, constituting an external operation against a target system.
Attacks that exploit this kind of access
Identify technologies used by a web application. It is categorised as a Execute tool in the Redteam MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Redteam MCP server in PolicyLayer and add a rule for whatweb_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 Redteam. Nothing to install.
whatweb_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 whatweb_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 whatweb_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.
whatweb_scan is provided by the Redteam MCP server (samirjani03/redteam-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 →