graph TB
    subgraph Clients
        A[🤖 AI Agent / LLM]
        B[👩‍💻 Engineer / Script / CI]
        C[🔧 Coding Agent - Claude Code / Kiro]
    end

    subgraph "Kubeflow Spark AI Toolkit"
        D[⚡ MCP Server]
        E[🛠️ CLI - shs]
    end

    subgraph "Spark History Servers"
        F[🔥 Production]
        G[🔥 Staging / Dev]
    end

    A -->|MCP Protocol| D
    B -->|Terminal commands| E
    C -->|shs skill file| E

    D -->|REST API| F
    D -->|REST API| G
    E -->|REST API| F
    E -->|REST API| G

# Auto-detect latest version, OS, and architecture
VERSION=$(curl -s https://api.github.com/repos/kubeflow/mcp-apache-spark-history-server/releases | grep -m1 '"tag_name": "cli/' | cut -d'"' -f4 | sed 's|cli/||')
OS=$(uname -s | tr '[:upper:]' '[:lower:]')
ARCH=$(uname -m)
[ "$ARCH" = "x86_64" ] && ARCH="amd64"
[ "$ARCH" = "aarch64" ] && ARCH="arm64"

curl -sSL "https://github.com/kubeflow/mcp-apache-spark-history-server/releases/download/cli%2F${VERSION}/shs-${VERSION}-${OS}-${ARCH}.tar.gz" | tar xz
sudo mv shs /usr/local/bin/

# Generate a config file
shs setup config > config.yaml   # then set your Spark History Server URL

# Explore applications
shs apps
shs jobs -a APP_ID --status failed
shs stages -a APP_ID --sort duration
shs compare apps --app-a APP1 --app-b APP2

# Use as a skill with Claude Code or Kiro
shs setup skill > ~/.claude/skills/spark-history.md

# Run directly with uvx (no install needed)
uvx --from mcp-apache-spark-history-server spark-mcp

# Or install with pip
uv tool install mcp-apache-spark-history-server
spark-mcp

servers:
  local:
    default: true
    url: "http://your-spark-history-server:18080"
    auth:            # optional
      username: "user"
      password: "pass"
    include_plan_description: false   # include SQL plans by default (default: false)
mcp:
  transports:
    - streamable-http   # or: stdio
  port: "18888"
  debug: false

SHS_MCP_PORT          Port for MCP server (default: 18888)
SHS_MCP_TRANSPORT     Transport mode: streamable-http or stdio
SHS_MCP_DEBUG         Enable debug mode (default: false)
SHS_MCP_ADDRESS       Bind address (default: localhost)
SHS_SERVERS_*_URL     URL for a specific server
SHS_SERVERS_*_AUTH_USERNAME
SHS_SERVERS_*_AUTH_PASSWORD
SHS_SERVERS_*_AUTH_TOKEN
SHS_SERVERS_*_VERIFY_SSL
SHS_SERVERS_*_TIMEOUT
SHS_SERVERS_*_EMR_CLUSTER_ARN
SHS_SERVERS_*_INCLUDE_PLAN_DESCRIPTION

servers:
  production:
    default: true
    url: "http://prod-spark-history:18080"
    auth:
      username: "user"
      password: "pass"
  staging:
    url: "http://staging-spark-history:18080"

helm install spark-history-mcp ./deploy/kubernetes/helm/mcp-apache-spark-history-server/

# Production configuration
helm install spark-history-mcp ./deploy/kubernetes/helm/mcp-apache-spark-history-server/ \
  --set replicaCount=3 \
  --set autoscaling.enabled=true

kubectl port-forward svc/mcp-apache-spark-history-server 18888:18888

git clone https://github.com/kubeflow/mcp-apache-spark-history-server.git
cd mcp-apache-spark-history-server

# Install Task runner
brew install go-task   # macOS; see https://taskfile.dev/installation/ for others

# MCP Server
task install           # install Python dependencies
task start-spark-bg    # start Spark History Server with sample data
task start-mcp-bg      # start MCP server
task start-inspector-bg  # open MCP Inspector at http://localhost:6274
task stop-all

# CLI
cd skills/cli
task build             # build ./bin/shs
task test              # unit tests
task test-e2e          # e2e tests (starts/stops Docker SHS automatically)
task start-shs         # start SHS with CLI e2e sample data