Run vulnerability detection scripts
AI agents invoke nmap_vulnerability_scan to trigger actions in Nmap MCP Server. 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 executes network-facing scripts that probe remote systems for vulnerabilities. It triggers external operations (active scanning with NSE scripts) whose effects depend on the target arguments. While it is primarily a read/reconnaissance activity, it actively runs code/scripts against external systems, which fits Execute.
From the tool's definition 'Run vulnerability detection scripts' — actively executes Nmap NSE vulnerability scripts against target hosts
Attacks that exploit this kind of access
Run vulnerability detection scripts. It is categorised as a Execute tool in the Nmap MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Nmap MCP Server MCP server in PolicyLayer and add a rule for nmap_vulnerability_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 Nmap MCP Server. Nothing to install.
nmap_vulnerability_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 nmap_vulnerability_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 nmap_vulnerability_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.
nmap_vulnerability_scan is provided by the Nmap MCP Server MCP server (mohdhaji87/nmap-mcp-server). 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 →