AI agents invoke discover-hosts 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.
Based on the server context, this tool almost certainly runs Nmap host discovery scans (e.g., ping sweeps, ARP scans) against network ranges. This constitutes active network reconnaissance — an external operation whose effects depend on arguments (target network/IP range). Even though it is read-like in intent, it actively sends packets to external systems, which classifies it as Execute.
From the tool's definition Tool name 'discover-hosts' on an nmap-based server described as enabling 'host discovery' for 'automated network security assessments'
Documented attack patterns abuse exactly the kind of access discover-hosts 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 discover-hosts:
{
"version": "1",
"default": "deny",
"tools": {
"discover-hosts": {
"limits": [
{
"counter": "discover-hosts_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}discover-hosts 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.
discover-hosts. 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 discover-hosts: 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.
discover-hosts 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 discover-hosts 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 discover-hosts. 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.
discover-hosts 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.