AI agents call list_nodes to retrieve information from Kubernetes Read Only MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves cluster node information without modifying, executing on, or deleting any resources. It is a pure query operation with no destructive or state-changing capabilities. The read-only nature of the server and the naming convention ('list_') further confirm it belongs in the Read category with low severity risk.
From the tool's definition Tool name 'list_nodes' combined with server description 'read-only interaction with Kubernetes clusters, allowing users to list resources' and sibling tools (list_deployments, list_namespaces, list_pods, list_services) all confirm this is a listing/retrieval…
Documented attack patterns abuse exactly the kind of access list_nodes gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kubernetes Read Only MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for list_nodes:
{
"version": "1",
"default": "deny",
"tools": {
"list_nodes": {}
}
}list_nodes is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List all nodes in the cluster. It is categorised as a Read tool in the Kubernetes Read Only MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Kubernetes Read Only MCP Server MCP server in PolicyLayer and add a rule for list_nodes: 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 Read Only MCP Server. Nothing to install.
list_nodes 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_nodes 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_nodes. 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_nodes is provided by the Kubernetes Read Only MCP Server MCP server (vijaykodam/kubernetes-readonly-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kubernetes Read Only 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.
8 Kubernetes Read Only MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.