AI agents call list_namespaces to retrieve information from Kube without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Listing namespaces is a non-destructive query operation that retrieves metadata about cluster namespaces without modifying, creating, or deleting any resources. No side effects or irreversible actions are involved. The tool fits the Read category—it gathers information to enable informed decision-making about other cluster operations.
From the tool's definition Tool name is 'list_namespaces' which follows the 'list_*' pattern; it retrieves Kubernetes namespace information with no described side effects. Sibling tools include 'list_pods', 'list_deployments', 'list_nodes', 'list_services' which are all Read operations.
Attacks that exploit this kind of access
list_namespaces. It is categorised as a Read tool in the Kube MCP Server, which means it retrieves data without modifying state.
Register the Kube MCP server in PolicyLayer and add a rule for list_namespaces: 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 Kube. Nothing to install.
list_namespaces is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_namespaces 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 list_namespaces. 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.
list_namespaces is provided by the Kube MCP server (lochgeo/kube-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 →