AI agents call top_nodes to retrieve information from K8s without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation that queries the Kubernetes metrics API to display current resource utilization statistics. It has no side effects, does not execute commands, does not modify state, and does not delete resources. The worst-case misuse would be information disclosure about cluster capacity, which is low severity.
From the tool's definition Tool name 'top_nodes' and description 'Show CPU and memory usage for nodes' indicate a query operation that retrieves and displays node metrics without modifying, executing, or deleting any resources.
Attacks that exploit this kind of access
Show CPU and memory usage for nodes (requires metrics-server). It is categorised as a Read tool in the K8s MCP Server, which means it retrieves data without modifying state.
Register the K8s MCP server in PolicyLayer and add a rule for top_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 K8s. Nothing to install.
top_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 top_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 top_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.
top_nodes is provided by the K8s MCP server (jingyanjiang/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 →