send_command · Network Device Assistant MCP: Risk & Policy

WHAT IT DOES

What send_command does on Network Device Assistant

AI agents invoke send_command to trigger actions in Network Device Assistant. 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 send_command needs a policy

Sending arbitrary CLI commands to network devices can have wide-ranging effects depending on the command: configuration changes, service disruptions, security policy modifications, or destructive operations. The tool itself is an execution primitive with blast radius spanning the entire network device and potentially the network it controls.

From the tool's definition 'Send a CLI command to a connected device and return the output' — executes arbitrary CLI commands on network devices over serial/SSH

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_command Rate-limited

send_command 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": {
    "send_command": {
      "limits": [
        {
          "counter": "send_command_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 Network Device Assistant, so you can run agents against it safely.

FAQ

Questions about send_command

What does the send_command tool do? +

Send a CLI command to a connected device and return the output.\n\n. It is categorised as a Execute tool in the Network Device Assistant MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on send_command? +

Register the Network Device Assistant MCP server in PolicyLayer and add a rule for send_command: 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 Network Device Assistant. Nothing to install.

What risk level is send_command? +

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

Can I rate-limit send_command? +

Yes. Add a rate_limit block to the send_command 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 send_command completely? +

Set action: deny in the PolicyLayer policy for send_command. 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 send_command? +

send_command is provided by the Network Device Assistant MCP server (mgarabito/network-device-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.