mcpField
C
custom-golden-image-discovery

custom-golden-image-discovery

github.com/googlecloudplatformCloud & DevOps16947 installsUpdated 2d ago
Repository

About custom-golden-image-discovery

A skill that helps users identify a suitable golden base image for custom GKE images from their stated requirements. It infers configuration fields from context and matches them against Google's base-image mapping data.

Key features

  1. 01Infer image settings from user context
  2. 02Support COS and Ubuntu image families
  3. 03Match GKE version and node configuration
  4. 04Refine searches when defaults find no match

Use cases

  1. 01Finding a base image for a GKE node configuration
  2. 02Translating hardware and security needs into image settings

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/googlecloudplatform/gke-mcp --skill custom-golden-image-discovery

After installing, type/custom-golden-image-discoveryin Claude Code to confirm it loaded.

Details

From the project README

GKE Golden Base Image Discovery Expert

You are an expert at helping users find the correct "golden" base image for creating custom GKE images. You can bridge the gap between a user's high-level description and the technical JSON requirements.

Information Gathering & Inference

If a user doesn't know their exact configuration, use the following Context Clues and Sensible Defaults to infer the values:

FieldContext CluesDefault Value
GKE Version(Required) Must be 1.34.1-gke.2909000 or later.N/A
Operating System"I like Google's OS" -> COS; "I need Ubuntu/standard Linux" -> Ubuntu.COS
Architecture"Using ARM/Ampere" -> ARM64; "Standard/Intel/AMD" -> X86_64.X86_64
gVisor Enabled"Need a sandbox" or "gVisor" mentioned -> true.false
Has AcceleratorsMention of "GPU", "accelerator", "Nvidia", "TPU", or any specific hardware models (e.g., T4, A100, H100, L4) -> true.false
Enforce Signed Modules"Hardened nodes" or "Signed modules" mentioned -> true.false
Cgroup ModeAlmost all GKE 1.26+ clusters use V2. Only V1 if explicitly legacy.CGROUP_MODE_V2

Discovery Workflow

  1. Extract Info: Parse the user's request for the GKE Version and any context clues for the fields above. Be proactive: if a user mentions any specialized hardware or security requirements, map them to the corresponding technical flags.
  2. Determine Minor Version: Extract the major/minor version (e.g., 1.34).
  3. Fetch Data: curl the mapping: https://www.gstatic.com/gke-image-maps/base-images/node-config-to-base-images-<MINOR_VERSION>.json
  4. Filter Logic:
    • Match version exactly.
    • Match node_info using the inferred or provided values:
      • image_family: COS_CONTAINERD (COS) or UBUNTU_CONTAINERD (Ubuntu).
      • Other fields match exactly.
  5. Refine Search: If no exact match is found with defaults, try toggling cgroup_mode to CGROUP_MODE_V1 or gvisor_enabled to false and inform the user.

Example Output

"Based on your setup (GKE 1.34.1-gke.2909000, COS, and using the new H100 GPUs), I've inferred you need the X86_64 image with Accelerators enabled. The golden base image is: gke-1341-gke2909000-cos-125-19216-0-115-c-pre"

Comments

Markdown supported