Create Kubernetes resources using various methods (from file or using subcommands)
AI agents use kubectl_create to create or update resources in Kubernetes — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kubernetes environment.
This tool creates new Kubernetes resources (deployments, services, configmaps, etc.), which is a Write operation. However, 'subcommands' could include destructive or execute-level operations depending on what kubectl subcommands are exposed.
From the tool's definition 'Create Kubernetes resources using various methods (from file or using subcommands)'
Attacks that exploit this kind of access
Create Kubernetes resources using various methods (from file or using subcommands). It is categorised as a Write tool in the Kubernetes MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kubernetes MCP server in PolicyLayer and add a rule for kubectl_create: 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 Kubernetes. Nothing to install.
kubectl_create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the kubectl_create 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 kubectl_create. 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.
kubectl_create is provided by the Kubernetes MCP server (mcp-server-kubernetes). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →