Get a custom resource definition
AI agents call get-crd 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 and displays metadata about custom resource definitions (CRDs) in a Kubernetes cluster. Reading CRD definitions has no side effects—it only queries cluster configuration. While CRDs are sensitive cluster configuration, merely reading them does not modify or delete anything, nor does it execute code or incur financial costs.
From the tool's definition Tool name 'get-crd' and description 'Get a custom resource definition' indicate a retrieval operation with no modification or deletion of resources.
Attacks that exploit this kind of access
Get a custom resource definition. 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 get-crd: 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.
get-crd 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 get-crd 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 get-crd. 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.
get-crd 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 →