cmd · Linux Network Scanner MCP Server MCP: Risk & Policy

WHAT IT DOES

What cmd does on Linux Network Scanner MCP Server

AI agents invoke cmd to trigger actions in Linux Network Scanner 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.

WHY IT NEEDS A POLICY

Why cmd needs a policy

Arbitrary command execution is Execute category (not Destructive, since destruction depends on which commands are run). Severity is critical because an AI agent could execute any shell command including data exfiltration, system compromise, lateral movement, or destructive operations. The unrestricted nature ('arbitrary') and lack of command whitelisting/sandboxing maximizes blast radius.

From the tool's definition Tool allows running arbitrary shell commands ('Run an arbitrary shell command'). Given the server context of network security scanning with tools like exploitScan, ftpBruteForce, and directCmd, this provides unrestricted code execution capability.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cmd Rate-limited

cmd 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "cmd": {
      "limits": [
        {
          "counter": "cmd_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Linux Network Scanner MCP Server, so you can run agents against it safely.

FAQ

Questions about cmd

What does the cmd tool do? +

Run an arbitrary shell command and stream output (human-friendly). It is categorised as a Execute tool in the Linux Network Scanner MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on cmd? +

Register the Linux Network Scanner MCP Server MCP server in PolicyLayer and add a rule for cmd: 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 Linux Network Scanner MCP Server. Nothing to install.

What risk level is cmd? +

cmd is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit cmd? +

Yes. Add a rate_limit block to the cmd 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.

How do I block cmd completely? +

Set action: deny in the PolicyLayer policy for cmd. 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.

What MCP server provides cmd? +

cmd is provided by the Linux Network Scanner MCP Server MCP server (nibesh0/netsecmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.