# Clone the repository
git clone https://github.com/admiller/rhoai-mcp-prototype.git
cd rhoai-mcp-prototype

# Install dependencies
uv sync

# Run the server
uv run rhoai-mcp

pip install -e .
rhoai-mcp

# Build the image
make build

# Run with HTTP transport
make run-http

# Run with STDIO transport (interactive)
make run-stdio

# Run with debug logging
make run-dev

# Build
podman build -f Containerfile -t rhoai-mcp:latest .

# Run with HTTP transport
podman run -p 8000:8000 \
  -v ~/.kube/config:/opt/app-root/src/kubeconfig/config:ro \
  -e RHOAI_MCP_AUTH_MODE=kubeconfig \
  -e RHOAI_MCP_KUBECONFIG_PATH=/opt/app-root/src/kubeconfig/config \
  rhoai-mcp:latest --transport sse

# Run with STDIO transport
podman run -it \
  -v ~/.kube/config:/opt/app-root/src/kubeconfig/config:ro \
  -e RHOAI_MCP_AUTH_MODE=kubeconfig \
  -e RHOAI_MCP_KUBECONFIG_PATH=/opt/app-root/src/kubeconfig/config \
  rhoai-mcp:latest --transport stdio

# KIND / local development
kustomize build deploy/kustomize/overlays/kind/ | kubectl apply -f -

# OpenShift production
kustomize build deploy/kustomize/overlays/openshift/ | oc apply -f -

deploy/kustomize/
├── base/                    # Shared resources (all environments)
│   ├── clusterrole.yaml     # RBAC for RHOAI resources
│   ├── deployment.yaml      # Hardened pod spec (non-root, read-only rootfs, probes)
│   ├── configmap.yaml       # Default config (SSE transport, INFO logging)
│   └── ...
└── overlays/
    ├── kind/                # NodePort, DEBUG logging, imagePullPolicy: Never
    └── openshift/           # GHCR image, TLS Route, OpenShift-specific RBAC, NetworkPolicy

# Auto mode (default)
export RHOAI_MCP_AUTH_MODE=auto

# Kubeconfig mode
export RHOAI_MCP_AUTH_MODE=kubeconfig
export RHOAI_MCP_KUBECONFIG_PATH=/path/to/kubeconfig
export RHOAI_MCP_KUBECONFIG_CONTEXT=my-context

# Token mode
export RHOAI_MCP_AUTH_MODE=token
export RHOAI_MCP_API_SERVER=https://api.cluster.example.com:6443
export RHOAI_MCP_API_TOKEN=sha256~xxxxx

# stdio (default) - for Claude Desktop and similar tools
export RHOAI_MCP_TRANSPORT=stdio

# HTTP transports
export RHOAI_MCP_TRANSPORT=sse
export RHOAI_MCP_HOST=127.0.0.1
export RHOAI_MCP_PORT=8000

# Enable delete operations (disabled by default)
export RHOAI_MCP_ENABLE_DANGEROUS_OPERATIONS=true

# Read-only mode (disable all write operations)
export RHOAI_MCP_READ_ONLY_MODE=true

# Set an explicit HMAC secret (recommended for production — tokens survive restarts)
export RHOAI_MCP_WORKFLOW_HMAC_SECRET=my-secret-key

# Adjust token time-to-live (default: 3600 seconds / 1 hour)
export RHOAI_MCP_WORKFLOW_TOKEN_TTL=1800

# Auto-discovery (default) - finds Model Registry in the cluster
export RHOAI_MCP_MODEL_REGISTRY_DISCOVERY_MODE=auto

# Manual - use a specific URL
export RHOAI_MCP_MODEL_REGISTRY_DISCOVERY_MODE=manual
export RHOAI_MCP_MODEL_REGISTRY_URL=https://model-registry.example.com

# No authentication (default) - for in-cluster access
export RHOAI_MCP_MODEL_REGISTRY_AUTH_MODE=none

# OAuth authentication - uses your oc login token
export RHOAI_MCP_MODEL_REGISTRY_AUTH_MODE=oauth

# Explicit token authentication
export RHOAI_MCP_MODEL_REGISTRY_AUTH_MODE=token
export RHOAI_MCP_MODEL_REGISTRY_TOKEN=sha256~xxxxx

# 1. Log in to OpenShift (this stores the OAuth token in kubeconfig)
oc login --server=https://api.cluster.example.com:6443

# 2. Configure the MCP server to use the external route with OAuth
export RHOAI_MCP_MODEL_REGISTRY_URL=https://model-catalog.apps.cluster.example.com
export RHOAI_MCP_MODEL_REGISTRY_DISCOVERY_MODE=manual
export RHOAI_MCP_MODEL_REGISTRY_AUTH_MODE=oauth

# 3. Optional: Skip TLS verification for self-signed certificates (not recommended)
# export RHOAI_MCP_MODEL_REGISTRY_SKIP_TLS_VERIFY=true

# Set up port-forwarding to the Model Registry service
kubectl port-forward -n rhoai-model-registries svc/model-catalog 8080:8443

# Configure the MCP server to use localhost
export RHOAI_MCP_MODEL_REGISTRY_URL=http://localhost:8080
export RHOAI_MCP_MODEL_REGISTRY_DISCOVERY_MODE=manual

{
  "mcpServers": {
    "rhoai": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/opendatahub-io/rhoai-mcp", "rhoai-mcp"],
      "env": {
        "RHOAI_MCP_KUBECONFIG_PATH": "/home/user/.kube/config"
      }
    }
  }
}

{
  "mcpServers": {
    "rhoai": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/opendatahub-io/rhoai-mcp", "rhoai-mcp"],
      "env": {
        "RHOAI_MCP_KUBECONFIG_PATH": "/home/user/.kube/config"
      }
    }
  }
}

{
  "mcpServers": {
    "rhoai": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/rhoai-mcp", "rhoai-mcp"],
      "env": {
        "RHOAI_MCP_KUBECONFIG_PATH": "/home/user/.kube/config"
      }
    }
  }
}

make build

{
  "mcpServers": {
    "rhoai": {
      "command": "podman",
      "args": [
        "run", "-i", "--rm",
        "--userns=keep-id",
        "-v", "${HOME}/.kube/config:/opt/app-root/src/kubeconfig/config:ro",
        "-e", "RHOAI_MCP_AUTH_MODE=kubeconfig",
        "-e", "RHOAI_MCP_KUBECONFIG_PATH=/opt/app-root/src/kubeconfig/config",
        "rhoai-mcp:latest"
      ]
    }
  }
}

{
  "mcpServers": {
    "rhoai": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-v", "${HOME}/.kube/config:/opt/app-root/src/kubeconfig/config:ro",
        "-e", "RHOAI_MCP_AUTH_MODE=kubeconfig",
        "-e", "RHOAI_MCP_KUBECONFIG_PATH=/opt/app-root/src/kubeconfig/config",
        "rhoai-mcp:latest"
      ]
    }
  }
}

User: Create a new data science project called "fraud-detection" for my ML experiments
Agent: I'll create that project for you with a descriptive display name.
[Calls create_data_science_project with name="fraud-detection", 
 display_name="Fraud Detection ML", description="Machine learning experiments for fraud detection"]

Result: Project 'fraud-detection' created successfully

User: Deploy my trained fraud model from S3 to the fraud-detection project

Agent: I'll deploy your model. First, let me check available serving runtimes.
[Calls list_serving_runtimes with namespace="fraud-detection"]
[Calls deploy_model with name="fraud-model", namespace="fraud-detection",
 runtime="ovms", model_format="onnx", 
 storage_uri="s3://models/fraud-detection/model.onnx"]

Result: Model 'fraud-model' deployment initiated. It may take a few minutes to become ready.

User: What's the status of my fraud-detection project?

Agent: [Calls get_project_status with namespace="fraud-detection"]

Result:
- Project: fraud-detection (Fraud Detection ML)
- Workbenches: 2 total, 1 running
- Models: 1 deployed, 1 ready
- Pipeline Server: Ready
- Data Connections: 1
- Storage: 3 PVCs

# Install dev dependencies
uv sync --extra dev

# Run tests
uv run pytest

# Run with coverage
uv run pytest --cov=rhoai_mcp

# Format code
uv run ruff format

# Lint
uv run ruff check

# Type check
uv run mypy src/rhoai_mcp

┌─────────────────────────────────────────────────────────────────┐
│                MCP Transport Layer (stdio/SSE/HTTP)             │
├─────────────────────────────────────────────────────────────────┤
│  FastMCP Server (server.py)                                     │
│  - Tool registration     - Resource registration                │
│  - Prompt registration   - Lifecycle management                 │
├───────────────────┬─────────────────────┬───────────────────────┤
│  Tools Layer      │  Resources Layer    │  Prompts Layer        │
│  - projects       │  - cluster.py       │  - training (3)       │
│  - notebooks      │  - projects.py      │  - exploration (4)    │
│  - inference      │                     │  - troubleshooting (4)│
│  - connections    │                     │  - project setup (3)  │
│  - storage        │                     │  - deployment (4)     │
│  - pipelines      │                     │                       │
│  - training       │                     │                       │
├───────────────────┴─────────────────────┴───────────────────────┤
│  Clients Layer (clients/) - Business Logic                      │
│  - base.py (K8sClient)   - projects.py    - notebooks.py        │
│  - inference.py          - connections.py - storage.py          │
│  - pipelines.py          - training.py                          │
├─────────────────────────────────────────────────────────────────┤
│  Models Layer (models/) - Pydantic Data Structures              │
│  - common.py (shared)    - Domain-specific models per resource  │
├─────────────────────────────────────────────────────────────────┤
│  Infrastructure Layer                                           │
│  - K8sClient: Kubernetes API abstraction (Core + CRDs)          │
│  - Configuration: Environment-based settings                    │
│  - Plugin Manager: Pluggy-based plugin system                   │
└─────────────────────────────────────────────────────────────────┘

AI Agent Request → MCP Transport → Tool Handler → Domain Client
                                                       ↓
AI Agent Response ← Pydantic Model ← K8s Response ← K8sClient → Kubernetes API