uv add ray-mcp

# Job operations
ray: "submit job with script train.py"
ray: "list all running jobs"
ray: "get logs for job raysubmit_123"

# Service operations
ray: "deploy service with inference model serve.py"
ray: "list all services"
ray: "scale service model-api to 3 replicas"

# Cloud providers
ray: "authenticate with GCP project ml-experiments"
ray: "list all GKE clusters"
ray: "authenticate with AWS region us-west-2"
ray: "list all EKS clusters"
ray: "connect to cluster production-cluster"

# Install with GKE support
uv add "ray-mcp[gke]"

# Set up authentication
export GOOGLE_APPLICATION_CREDENTIALS="/path/to/service-account.json"

# Install with EKS support
uv add "ray-mcp[eks]"

# Set up authentication
export AWS_ACCESS_KEY_ID="your_access_key"
export AWS_SECRET_ACCESS_KEY="your_secret_key"
export AWS_DEFAULT_REGION="us-west-2"

# Install KubeRay operator
kubectl apply -f https://raw.githubusercontent.com/ray-project/kuberay/release-0.8/deploy/kuberay-operator.yaml

# LLM Processing Configuration (Required)
export OPENAI_API_KEY="your_api_key_here"       # Required for natural language parsing

# LLM Processing Configuration (Optional)
export LLM_MODEL="gpt-3.5-turbo"                # OpenAI model for prompt processing

# Output and Logging
export RAY_MCP_ENHANCED_OUTPUT=true             # Enhanced LLM-friendly responses
export RAY_MCP_LOG_LEVEL=INFO                   # Logging level (DEBUG, INFO, WARNING, ERROR)

# Ray Configuration
export RAY_DISABLE_USAGE_STATS=1                # Disable Ray usage statistics

# Install development dependencies
make dev-install

# Run tests
make test-fast      # Unit tests with mocking
make test           # Complete test suite

# Code quality
make lint           # Run linting
make format         # Format code

# Submit a job
ray: "submit job with script train.py"

# Submit job with resources
ray: "submit job with script train.py requiring 2 CPUs and 1 GPU"

# Submit job with runtime environment
ray: "submit job with script train.py and pip packages pandas numpy"

# List jobs
ray: "list all running jobs"
ray: "list jobs in namespace production"

# Get job status and logs
ray: "get status for job raysubmit_123"
ray: "get logs for job raysubmit_123"

# Cancel job
ray: "cancel job raysubmit_123"

# Deploy a service
ray: "deploy service with inference model serve.py"

# Deploy named service
ray: "create service named image-classifier with model classifier.py"

# List services
ray: "list all services"
ray: "list services in namespace production"

# Manage services
ray: "get status of service image-classifier"
ray: "scale service model-api to 5 replicas"
ray: "get logs for service text-analyzer"
ray: "delete service old-model-service"

# Google Cloud (GKE)
ray: "authenticate with GCP project ml-experiments"
ray: "authenticate with GCP"

# Amazon Web Services (EKS)
ray: "authenticate with AWS region us-west-2"
ray: "authenticate with AWS"

# Azure (AKS)
ray: "authenticate with Azure"

# List clusters
ray: "list all GKE clusters"
ray: "list all EKS clusters"
ray: "list all AKS clusters"

# Connect to clusters
ray: "connect to GKE cluster production-cluster in us-west1-c"
ray: "connect to EKS cluster training-cluster in us-west-2"
ray: "connect to AKS cluster ml-cluster in eastus2"

# Check environment
ray: "check environment setup"

# 1. Authenticate
ray: "authenticate with GCP project my-ml-project"

# 2. Connect to cluster
ray: "connect to cluster dev-cluster in us-central1-a"

# 3. Submit test job
ray: "submit job with script test_model.py"

# 4. Check results
ray: "get logs for job raysubmit_123"

# 1. Connect to production cluster
ray: "connect to cluster production-cluster in us-west1-c"

# 2. Deploy service
ray: "create service named prod-inference with model production_model.py in namespace production"

# 3. Scale for load
ray: "scale service prod-inference to 10 replicas"

# 4. Monitor
ray: "get status of service prod-inference"

# 1. Connect to compute cluster
ray: "connect to cluster batch-cluster"

# 2. Submit batch job
ray: "submit job with script batch_processing.py requiring 8 CPUs"

# 3. Monitor progress
ray: "get status for job batch-processing-job"

# 4. Get results
ray: "get logs for job batch-processing-job"

# Development
ray: "authenticate with GCP project dev-project"
ray: "connect to cluster dev-cluster"
ray: "submit job with script experiment.py"

# Staging
ray: "authenticate with AWS region us-east-1"
ray: "connect to cluster staging-cluster"
ray: "submit job with script validation.py"

# Production
ray: "authenticate with GCP project prod-project"
ray: "connect to cluster prod-cluster"
ray: "deploy service with model final_model.py"

# CPU-intensive job
ray: "submit job with script data_processing.py requiring 4 CPUs"

# GPU training job
ray: "submit job with script gpu_training.py requiring 2 GPUs"

# Mixed workload
ray: "submit job with script hybrid_task.py requiring 2 CPUs and 1 GPU"

# Check cluster status
ray: "check environment setup"

# Get detailed logs
ray: "get error logs for job raysubmit_456"

# List failed jobs
ray: "list failed jobs"

# Restart failed job
ray: "cancel job raysubmit_456"
ray: "submit job with script fixed_model.py"