AI agents invoke stop 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.
Stopping an instance is an executable operation that triggers an external action on cloud infrastructure. While not destructive (the instance is not deleted), it is disruptive and changes the operational state of a system. This is Execute rather than Write because it invokes an action on infrastructure whose effects (service downtime, workflow interruption) depend on which instance is targeted.
From the tool's definition Tool name: 'stop'; description: 'Stop a running instance.' Stops a computational instance, which is an operational action that changes the state of infrastructure.
Documented attack patterns abuse exactly the kind of access stop gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Vultr MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for stop:
{
"version": "1",
"default": "deny",
"tools": {
"stop": {
"limits": [
{
"counter": "stop_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}stop 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.
Free to start. No card required.
Stop a running instance. It is categorised as a Execute tool in the Vultr MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Vultr MCP server in PolicyLayer and add a rule for stop: 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 Vultr MCP. Nothing to install.
stop is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the stop 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.
Set action: deny in the PolicyLayer policy for stop. 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.
stop is provided by the Vultr MCP server (rsp2k/mcp-vultr). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Vultr MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
284 Vultr MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.