AI agents call describe_resource to retrieve information from kube-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The describe_resource tool retrieves information about Kubernetes resources (pods, services, deployments, etc.) for inspection and diagnostics. This is functionally equivalent to 'kubectl describe', which is a read-only operation. No data is created, modified, deleted, or executed. The blast radius of misuse is minimal—an attacker gains visibility into cluster configuration but cannot directly harm workloads or data.
From the tool's definition Tool name 'describe_resource' and description 'Describe a Kubernetes resource' indicate a query/inspection operation. The verb 'describe' is a read-only kubectl operation that retrieves and displays resource metadata and status without modifying state.
Attacks that exploit this kind of access
Describe a Kubernetes resource. It is categorised as a Read tool in the kube-MCP MCP Server, which means it retrieves data without modifying state.
Register the kube- MCP server in PolicyLayer and add a rule for describe_resource: 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-MCP. Nothing to install.
describe_resource 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_resource 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_resource. 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_resource is provided by the kube- MCP server (siddjoshi/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 →