vps_setup · ML Lab MCP: Risk & Policy

WHAT IT DOES

What vps_setup does on ML Lab MCP

AI agents invoke vps_setup to trigger actions in ML Lab MCP. 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 vps_setup needs a policy

This tool executes commands on a remote VPS to install dependencies and configure a training environment. It triggers external operations (package installation, system configuration) on a live server. The blast radius is high because an AI agent could install malicious packages, misconfigure the system, or disrupt existing workloads on the VPS.

From the tool's definition 'Set up training environment on a VPS (installs dependencies)' — installs software and configures a remote system

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

vps_setup Rate-limited

vps_setup 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": {
    "vps_setup": {
      "limits": [
        {
          "counter": "vps_setup_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 ML Lab MCP, so you can run agents against it safely.

FAQ

Questions about vps_setup

What does the vps_setup tool do? +

Set up training environment on a VPS (installs dependencies). It is categorised as a Execute tool in the ML Lab MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on vps_setup? +

Register the ML Lab MCP server in PolicyLayer and add a rule for vps_setup: 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 ML Lab MCP. Nothing to install.

What risk level is vps_setup? +

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

Can I rate-limit vps_setup? +

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

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

vps_setup is provided by the ML Lab MCP server (pushpullcommitpush/ml-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.