KCC MCP Server

Model Context Protocol (MCP) server for contributing to Google Cloud Platform's k8s-config-connector.

This MCP server provides AI assistants with tools to:

• Add fields to existing direct controller resources
• Migrate resources from Terraform-based to direct controller architecture
• Create commits with enforced attribution rules (NO AI attribution)

Features

✅ 12 MCP Tools for k8s-config-connector contributions ✅ Universal AI Attribution Blocking - enforces human-only commit authorship ✅ Resource Detection - automatically determines controller type ✅ Migration Planning - 7-phase workflow for Terraform → Direct migration ✅ Code Scaffolding - generates boilerplate for types, controller, MockGCP ✅ Proto Annotations - maintains KRM ↔ GCP proto mappings

Quick Start

Installation with Gemini CLI (Recommended)

# Install from GitHub
npx @google/gemini-cli extensions install https://github.com/fkc1e100/kcc-mcp-server.git

# Run setup
cd ~/.gemini/extensions/kcc-contributor
./setup-config.sh

# Start using it
npx @google/gemini-cli chat

Manual Installation

# Clone or copy this repository
cd kcc-mcp-server

# Install dependencies
npm install

# Build
npm run build

Configuration

Option 1: Interactive Setup (Easiest)

Run the setup script after installation:

./setup-config.sh

This creates ~/.config/kcc-mcp-server/config.json with your settings.

Option 2: Manual Config File

Create ~/.config/kcc-mcp-server/config.json:

{
  "git": {
    "author_name": "Your Name",
    "author_email": "you@example.com"
  },
  "kcc_repo_path": "/path/to/k8s-config-connector"
}

Option 3: Environment Variables

export KCC_REPO_PATH="/path/to/k8s-config-connector"
export KCC_AUTHOR_NAME="Your Name"
export KCC_AUTHOR_EMAIL="you@example.com"

Usage with Gemini CLI

# Start chat session
npx @google/gemini-cli chat
# or
gemini --yolo

# Check MCP server status
/mcp list

# Should show:
# 🟢 kccServer (from kcc-contributor) - Ready (12 tools)

Example prompts:

Check if ComputeURLMap needs migration

Find the EdgeCacheService resource files

Add a new field called routeMethods to EdgeCacheService

See GEMINI_CLI_USAGE.md for more examples.

Verifying Installation

After installation, verify the MCP server is connected:

npx @google/gemini-cli chat

Then in the chat:

/mcp list

You should see:

🟢 kccServer (from kcc-contributor) - Ready (12 tools)
  Tools:
  - kcc_add_field
  - kcc_detect_controller_type
  - kcc_find_resource
  - kcc_generate_mapper
  - kcc_git_commit
  - kcc_git_status
  - kcc_migration_status
  - kcc_plan_migration
  - kcc_scaffold_controller
  - kcc_scaffold_identity
  - kcc_scaffold_mockgcp
  - kcc_scaffold_types

If you see 🔴 kccServer - Disconnected, see Troubleshooting below.

Usage with Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):

{
  "mcpServers": {
    "kcc-contributor": {
      "command": "node",
      "args": ["/path/to/kcc-mcp-server/dist/index.js"],
      "env": {
        "KCC_REPO_PATH": "/path/to/k8s-config-connector"
      }
    }
  }
}

Available Tools

Resource Detection (3 tools)

kcc_find_resource

Locate files for a KCC resource (types, controller, mapper, test fixtures).

Parameters:

• resource (string): Resource name (e.g., "EdgeCacheService")

kcc_detect_controller_type

Detect if a resource uses direct controller or Terraform-based controller.

Parameters:

• resource (string): Resource name

Returns:

{
  "type": "terraform",
  "migration_needed": true,
  "service": "compute",
  "version": "v1beta1"
}

kcc_migration_status

Get migration status for a resource (shows wh

... View full README on GitHub