AI agents invoke shutdown_instance to trigger actions in Linode 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.
Powering off a cloud instance is an operational action with significant blast radius (service disruption, downtime) but is reversible (instance can be powered back on), placing it in Execute rather than Destructive. Misuse by an AI agent could take critical workloads offline.
From the tool's definition 'Power off a Linode instance' — shuts down a running compute instance, an external operational effect that disrupts running workloads but does not delete data.
Documented attack patterns abuse exactly the kind of access shutdown_instance gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Linode MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for shutdown_instance:
{
"version": "1",
"default": "deny",
"tools": {
"shutdown_instance": {
"limits": [
{
"counter": "shutdown_instance_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}shutdown_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.
Free to start. No card required.
Power off a Linode instance. It is categorised as a Execute tool in the Linode MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Linode MCP Server MCP server in PolicyLayer and add a rule for shutdown_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 Linode MCP Server. Nothing to install.
shutdown_instance 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 shutdown_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.
Set action: deny in the PolicyLayer policy for shutdown_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.
shutdown_instance is provided by the Linode MCP Server MCP server (takashito/linode-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Linode 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.
416 Linode MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.