vps_run · ML Lab MCP: Risk & Policy

WHAT IT DOES

What vps_run does on ML Lab MCP

AI agents invoke vps_run 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_run needs a policy

This tool executes arbitrary shell commands on a remote VPS, which is an Execute-category action with critical severity. An AI agent with access to this tool could run any command on the connected VPS (data exfiltration, malware deployment, lateral movement, resource hijacking, etc.). The blast radius is maximal because VPS access typically grants broad system-level permissions.

From the tool's definition Tool name 'vps_run' combined with description 'Run a command on a VPS' directly indicates arbitrary command execution on a remote virtual private server.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

vps_run Rate-limited

vps_run 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_run": {
      "limits": [
        {
          "counter": "vps_run_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_run

What does the vps_run tool do? +

Run a command on a VPS. 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_run? +

Register the ML Lab MCP server in PolicyLayer and add a rule for vps_run: 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_run? +

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

Can I rate-limit vps_run? +

Yes. Add a rate_limit block to the vps_run 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_run completely? +

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

vps_run 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.