stop_vpn · VPN As A Service MCP: Risk & Policy

WHAT IT DOES

What stop_vpn does on VPN As A Service MCP

AI agents invoke stop_vpn to trigger actions in VPN As A Service 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 stop_vpn needs a policy

While stopping a VPN is theoretically reversible (via start_vpn), it constitutes an Execute action because it triggers an external operation with immediate side effects on infrastructure state and active network connections. It is not Destructive because the tunnel can be restarted without data loss. It is not Read (no data retrieval), Write (no persistent data creation/modification), or Financial.

From the tool's definition The tool 'stop_vpn' performs an immediate operational action that disrupts network connectivity. The description 'Stop the VPN tunnel' indicates it triggers an external operation (terminating an active VPN tunnel) whose effects depend on which VPN is…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

stop_vpn Rate-limited

stop_vpn 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": {
    "stop_vpn": {
      "limits": [
        {
          "counter": "stop_vpn_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 VPN As A Service MCP, so you can run agents against it safely.

FAQ

Questions about stop_vpn

What does the stop_vpn tool do? +

Stop the VPN tunnel. It is categorised as a Execute tool in the VPN As A Service 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 stop_vpn? +

Register the VPN As A Service MCP server in PolicyLayer and add a rule for stop_vpn: 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 VPN As A Service MCP. Nothing to install.

What risk level is stop_vpn? +

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

Can I rate-limit stop_vpn? +

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

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

stop_vpn is provided by the VPN As A Service MCP server (nolaan/ai_vpn_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.