AI agents call top_pods 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.
The name 'top_pods' indicates this displays resource usage (CPU/memory) metrics for pods, analogous to the 'top' command in Unix. This is a read-only operation that queries and reports current pod statistics.
From the tool's definition Tool name 'top_pods' and its position among sibling tools (describe_resource, diagnose_pod, get_configmap) suggests a querying/inspection function that retrieves pod resource metrics without modifying state.
Attacks that exploit this kind of access
top_pods. 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_pods: 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_pods 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_pods 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_pods. 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_pods 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 →