start

What start does on Vultr MCP

AI agents invoke start to trigger actions in Vultr 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 start is rated High

Starting a stopped instance is an Execute-category action because it triggers external infrastructure operations with side effects. While not Destructive (reversible via stop), it goes beyond Read/Write data operations—it executes commands that change system state. Severity is high due to potential blast radius: starting unintended instances could incur costs, affect production services, or expose security surfaces.

From the tool's definition Tool name 'start' with description 'Start a stopped instance' indicates execution of a state-change operation on cloud infrastructure. The action triggers external effects (VM startup) whose consequences depend on the instance targeted.

The rule that runs start safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Vultr MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For start, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "start": {
      "limits": [
        {
          "counter": "start_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

Questions about start