stop_kubernetes_cluster
Stop a running Kubernetes cluster
This record as markdown: /tools/mozg31337-cloudstack-mcp-server/stop-kubernetes-cluster.md
What stop_kubernetes_cluster does on CloudStack MCP Server
AI agents invoke stop_kubernetes_cluster 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.
Why stop_kubernetes_cluster is rated High
This tool triggers an external operation (stopping a Kubernetes cluster) whose effects depend on which cluster is targeted. While not permanently destructive (the cluster can be restarted), it causes immediate operational disruption and service interruption. It is Execute rather than Destructive because the action is reversible (the cluster can be started again).
From the tool's definition Tool name: 'stop_kubernetes_cluster'; Description: 'Stop a running Kubernetes cluster' — stopping a cluster is an operational action that halts running services and workloads with immediate effects.
Attacks that exploit this kind of access
The rule that runs stop_kubernetes_cluster safely
PolicyLayer is an MCP gateway: it sits between your AI agents and CloudStack MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For stop_kubernetes_cluster, this is the rule to start with:
stop_kubernetes_cluster 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.
The button opens the PolicyLayer dashboard: create your workspace, connect CloudStack MCP Server, apply this rule, and every stop_kubernetes_cluster call is checked against it from then on.
Questions about stop_kubernetes_cluster
Stop a running Kubernetes cluster. 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_kubernetes_cluster: 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_kubernetes_cluster 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_kubernetes_cluster 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_kubernetes_cluster. 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_kubernetes_cluster is provided by the CloudStack MCP Server MCP server (mozg31337/cloudstack-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on CloudStack MCP Server, and thousands of servers like it.
Across the catalogue