power_off_alibaba_instance · Cloud Manage MCP Server MCP

WHAT IT DOES

What power_off_alibaba_instance does on Cloud Manage MCP Server

AI agents invoke power_off_alibaba_instance to trigger actions in Cloud Manage 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.

WHY IT NEEDS A POLICY

Why power_off_alibaba_instance needs a policy

Powering off a cloud instance is a disruptive external operation that immediately terminates running workloads on that instance. While not permanently destructive (the instance and data persist), it causes service interruption and cannot be undone in real-time (services go down). The triple-confirmation requirement ('需要三次确认') signals the designers recognize the high blast radius.

From the tool's definition 强制停止阿里云ECS实例 (Force stop Alibaba Cloud ECS instance) — performs a power-off operation on a live cloud instance

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

power_off_alibaba_instance Rate-limited

power_off_alibaba_instance 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": {
    "power_off_alibaba_instance": {
      "limits": [
        {
          "counter": "power_off_alibaba_instance_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 Cloud Manage MCP Server, so you can run agents against it safely.

FAQ

Questions about power_off_alibaba_instance

What does the power_off_alibaba_instance tool do? +

强制停止阿里云ECS实例（需要三次确认）. It is categorised as a Execute tool in the Cloud Manage MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on power_off_alibaba_instance? +

Register the Cloud Manage MCP Server MCP server in PolicyLayer and add a rule for power_off_alibaba_instance: 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 Cloud Manage MCP Server. Nothing to install.

What risk level is power_off_alibaba_instance? +

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

Can I rate-limit power_off_alibaba_instance? +

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

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

power_off_alibaba_instance is provided by the Cloud Manage MCP Server MCP server (rainhan99/cloud_manage_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.