AI agents call describe_pod 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.
The 'describe_pod' operation is a standard Kubernetes read operation that retrieves detailed information about a pod's status, configuration, and events. It has no side effects on cluster state.
From the tool's definition Tool name 'describe_pod' and its position among sibling tools (get_logs, list_pods, list_deployments, list_namespaces, list_nodes, list_services) that are all read-only retrieval operations.
Attacks that exploit this kind of access
describe_pod. 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 describe_pod: 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.
describe_pod 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 describe_pod 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 describe_pod. 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.
describe_pod 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 →