AI agents invoke stop_virtual_machine to trigger actions in CloudStack MCP Server. 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.
This tool executes a command against cloud infrastructure to stop a running virtual machine. While not destructive (the VM and data persist), it is an Execute-category action because it triggers external operations with real-world effects on cloud resources.
From the tool's definition Tool name 'stop_virtual_machine' and description 'Stop a virtual machine' indicate an action that triggers external cloud infrastructure operations whose effects depend on arguments (the target VM).
Documented attack patterns abuse exactly the kind of access stop_virtual_machine gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CloudStack MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for stop_virtual_machine:
{
"version": "1",
"default": "deny",
"tools": {
"stop_virtual_machine": {
"limits": [
{
"counter": "stop_virtual_machine_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}stop_virtual_machine 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 virtual machine. It is categorised as a Execute tool in the CloudStack MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the CloudStack MCP Server MCP server in PolicyLayer and add a rule for stop_virtual_machine: 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 CloudStack MCP Server. Nothing to install.
stop_virtual_machine 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_virtual_machine 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_virtual_machine. 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_virtual_machine is provided by the CloudStack MCP Server MCP server (phantosmax/cloudstack-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from CloudStack MCP Server, 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.
45 CloudStack MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.