Get available API resources
AI agents call api-resources to retrieve information from Kubernetes MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about available Kubernetes API resources (like pods, services, deployments, etc.). It performs no side effects, does not execute commands, does not create, modify, or delete resources. It is strictly a read/query operation with minimal blast radius—knowledge of available APIs cannot be misused to cause harm directly.
From the tool's definition Tool name is 'api-resources' and description states 'Get available API resources' — a pure query operation that retrieves and lists available Kubernetes API resources without modifying any state.
Attacks that exploit this kind of access
Get available API resources. It is categorised as a Read tool in the Kubernetes MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Kubernetes MCP Server MCP server in PolicyLayer and add a rule for api-resources: 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 Kubernetes MCP Server. Nothing to install.
api-resources 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 api-resources 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 api-resources. 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.
api-resources is provided by the Kubernetes MCP Server MCP server (thekaranpargaie/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 →