Scan a network/IP range for open ports (top 100 ports). If mulitple targets are provided and they are not in CIDR format, they should be space-separated.
AI agents invoke scan_network 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.
Network scanning actively sends packets to target systems, which constitutes executing an external operation. It can be misused to perform reconnaissance against unauthorized networks, has legal and security implications, and the blast radius is high since it can scan arbitrary IP ranges. It is not merely reading local data but actively probing remote systems.
From the tool's definition 'Scan a network/IP range for open ports' — actively sends network probes to external hosts/ranges, triggering external operations whose effects depend on the provided IP arguments
Documented attack patterns abuse exactly the kind of access scan_network 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 scan_network:
{
"version": "1",
"default": "deny",
"tools": {
"scan_network": {
"limits": [
{
"counter": "scan_network_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}scan_network 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.
Scan a network/IP range for open ports (top 100 ports). If mulitple targets are provided and they are not in CIDR format, they should be space-separated. 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 scan_network: 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.
scan_network 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 scan_network 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 scan_network. 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.
scan_network is provided by the Nmap MCP server (jarrodcoulter/nmap-mcp-server). 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.
5 Nmap tools catalogued and risk-classified — across an index of 43,000+ MCP servers.