AI agents invoke detect-os to trigger actions in Nmap. 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.
OS fingerprinting via nmap requires sending crafted network packets to remote hosts, which constitutes an active external operation (Execute category). This can trigger IDS/IPS alerts, be legally sensitive without authorization, and exposes network topology information. The empty description lowers confidence slightly, but the server context makes the function clear.
From the tool's definition Tool name 'detect-os' on an nmap-based server described as enabling 'OS fingerprinting' among other network security assessment capabilities.
Documented attack patterns abuse exactly the kind of access detect-os gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Nmap, and nothing reaches the server without passing your rules. This is the rule we recommend for detect-os:
{
"version": "1",
"default": "deny",
"tools": {
"detect-os": {
"limits": [
{
"counter": "detect-os_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}detect-os 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.
detect-os. It is categorised as a Execute tool in the Nmap MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Nmap MCP server in PolicyLayer and add a rule for detect-os: 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 Nmap. Nothing to install.
detect-os 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 detect-os 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 detect-os. 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.
detect-os is provided by the Nmap MCP server (vorota-ai/nmap-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Nmap, 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.
6 Nmap tools catalogued and risk-classified — across an index of 43,000+ MCP servers.