show_command · Sros MCP: Risk & Policy

WHAT IT DOES

What show_command does on Sros

AI agents invoke show_command to trigger actions in Sros. 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 show_command needs a policy

This tool runs arbitrary CLI commands on network devices. CLI commands on Nokia SR OS can read state, modify configuration, or cause destructive changes (e.g., interface shutdowns, route deletions). Since the tool executes arbitrary commands whose effects depend on the arguments provided, Execute is the correct category. The blast radius is high because misuse could disrupt network operations on production routers.

From the tool's definition "Execute a CLI command on a Nokia SROS device and return the output"

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

show_command Rate-limited

show_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": {
    "show_command": {
      "limits": [
        {
          "counter": "show_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 Sros, so you can run agents against it safely.

FAQ

Questions about show_command

What does the show_command tool do? +

Execute a CLI command on a Nokia SROS device and return the output. It is categorised as a Execute tool in the Sros MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on show_command? +

Register the Sros MCP server in PolicyLayer and add a rule for show_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 Sros. Nothing to install.

What risk level is show_command? +

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

Can I rate-limit show_command? +

Yes. Add a rate_limit block to the show_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 show_command completely? +

Set action: deny in the PolicyLayer policy for show_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 show_command? +

show_command is provided by the Sros MCP server (mohamedhafez87/mcp-server-sros). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.