AI agents use create_namespace to create or update resources in K8s MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your K8s MCP environment.
This tool creates a new namespace in a Kubernetes cluster, which is a reversible write operation. Namespaces are organizational units that can be deleted, making this a Write rather than Destructive action. While namespace creation has organizational consequences, the severity is medium because it doesn't directly compromise running workloads, expose sensitive data, or delete resources.
From the tool's definition Tool name: 'create_namespace'; description: 'Create a new namespace.' The verb 'Create' indicates a write operation that adds a new Kubernetes namespace resource.
Attacks that exploit this kind of access
Create a new namespace. It is categorised as a Write tool in the K8s MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the K8s MCP server in PolicyLayer and add a rule for create_namespace: 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 K8s MCP. Nothing to install.
create_namespace 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 create_namespace 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 create_namespace. 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.
create_namespace is provided by the K8s MCP server (rahul007-bit/k8s-mcp). 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 →