Get detailed information about a pod
AI agents call k8s_describe to retrieve information from MCP Container Tools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The k8s_describe tool is a read-only operation that queries Kubernetes metadata and status information about pods. It has no side effects, does not execute code or commands, does not modify resources, and does not delete data. The blast radius of misuse is minimal—an attacker could only gain visibility into pod details already available to authenticated users in the cluster.
From the tool's definition Tool name 'k8s_describe' and description 'Get detailed information about a pod' indicate a query operation that retrieves and displays information about Kubernetes pod resources without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Get detailed information about a pod. It is categorised as a Read tool in the MCP Container Tools MCP Server, which means it retrieves data without modifying state.
Register the MCP Container Tools MCP server in PolicyLayer and add a rule for k8s_describe: 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 MCP Container Tools. Nothing to install.
k8s_describe 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 k8s_describe 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 k8s_describe. 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.
k8s_describe is provided by the MCP Container Tools MCP server (simseksem/mcp-container-tools). 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 →