graph LR
    A[Train on GPU] --> B[Get artifact_id + model]
    B --> C[5min Cache]
    C --> D[<100ms Predictions]
    B --> E[Download Artifact]
    E --> F[Use Anywhere]

{
  "mcpServers": {
    "warpgbm": {
      "url": "https://warpgbm.ai/mcp/sse"
    }
  }
}

# 1. Train a model
curl -X POST https://warpgbm.ai/train \
  -H "Content-Type: application/json" \
  -d '{
    "X": [[5.1,3.5,1.4,0.2], [6.7,3.1,4.4,1.4], ...],
    "y": [0, 1, 2, ...],
    "model_type": "warpgbm",
    "objective": "multiclass"
  }'

# Response includes artifact_id for fast predictions
# {"artifact_id": "abc-123", "model_artifact_joblib": "H4sIA..."}

# 2. Make fast predictions (cached, <100ms)
curl -X POST https://warpgbm.ai/predict_from_artifact \
  -H "Content-Type: application/json" \
  -d '{
    "artifact_id": "abc-123",
    "X": [[5.0,3.4,1.5,0.2]]
  }'

# 1. Train WarpGBM on Iris (60 samples recommended for proper binning)
curl -X POST https://warpgbm.ai/train \
  -H "Content-Type: application/json" \
  -d '{
  "X": [[5.1,3.5,1.4,0.2], [4.9,3,1.4,0.2], [4.7,3.2,1.3,0.2], [4.6,3.1,1.5,0.2], [5,3.6,1.4,0.2],
        [7,3.2,4.7,1.4], [6.4,3.2,4.5,1.5], [6.9,3.1,4.9,1.5], [5.5,2.3,4,1.3], [6.5,2.8,4.6,1.5],
        [6.3,3.3,6,2.5], [5.8,2.7,5.1,1.9], [7.1,3,5.9,2.1], [6.3,2.9,5.6,1.8], [6.5,3,5.8,2.2],
        [7.6,3,6.6,2.1], [4.9,2.5,4.5,1.7], [7.3,2.9,6.3,1.8], [6.7,2.5,5.8,1.8], [7.2,3.6,6.1,2.5],
        [5.1,3.5,1.4,0.2], [4.9,3,1.4,0.2], [4.7,3.2,1.3,0.2], [4.6,3.1,1.5,0.2], [5,3.6,1.4,0.2],
        [7,3.2,4.7,1.4], [6.4,3.2,4.5,1.5], [6.9,3.1,4.9,1.5], [5.5,2.3,4,1.3], [6.5,2.8,4.6,1.5],
        [6.3,3.3,6,2.5], [5.8,2.7,5.1,1.9], [7.1,3,5.9,2.1], [6.3,2.9,5.6,1.8], [6.5,3,5.8,2.2],
        [7.6,3,6.6,2.1], [4.9,2.5,4.5,1.7], [7.3,2.9,6.3,1.8], [6.7,2.5,5.8,1.8], [7.2,3.6,6.1,2.5],
        [5.1,3.5,1.4,0.2], [4.9,3,1.4,0.2], [4.7,3.2,1.3,0.2], [4.6,3.1,1.5,0.2], [5,3.6,1.4,0.2],
        [7,3.2,4.7,1.4], [6.4,3.2,4.5,1.5], [6.9,3.1,4.9,1.5], [5.5,2.3,4,1.3], [6.5,2.8,4.6,1.5],
        [6.3,3.3,6,2.5], [5.8,2.7,5.1,1.9], [7.1,3,5.9,2.1], [6.3,2.9,5.6,1.8], [6.5,3,5.8,2.2],
        [7.6,3,6.6,2.1], [4.9,2.5,4.5,1.7], [7.3,2.9,6.3,1.8], [6.7,2.5,5.8,1.8], [7.2,3.6,6.1,2.5]],
  "y": [0,0,0,0,0, 1,1,1,1,1, 2,2,2,2,2,2,2,2,2,2,
        0,0,0,0,0, 1,1,1,1,1, 2,2,2,2,2,2,2,2,2,2,
        0,0,0,0,0, 1,1,1,1,1, 2,2,2,2,2,2,2,2,2,2],
  "model_type": "warpgbm",
  "objective": "multiclass",
  "n_estimators": 100
}'

# Response:
{
  "artifact_id": "abc123-def456-ghi789",
  "model_artifact_joblib": "H4sIA...",
  "training_time_seconds": 0.0
}

# 2. Fast inference with cached artifact_id (<100ms)
curl -X POST https://warpgbm.ai/predict_from_artifact \
  -H "Content-Type: application/json" \
  -d '{
  "artifact_id": "abc123-def456-ghi789",
  "X": [[5,3.4,1.5,0.2], [6.7,3.1,4.4,1.4], [7.7,3.8,6.7,2.2]]
}'

# Response: {"predictions": [0, 1, 2], "inference_time_seconds": 0.05}
# Perfect classification! ✨

# Clone repo
git clone https://github.com/jefferythewind/mcp-warpgbm.git
cd mcp-warpgbm

# Setup environment
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

# Run locally (GPU optional for dev)
uvicorn local_dev:app --host 0.0.0.0 --port 8000 --reload

# Test
curl http://localhost:8000/healthz

# Install Modal
pip install modal

# Authenticate
modal token new

# Deploy
modal deploy modal_app.py

# Service will be live at your Modal URL

# Docker (requires GPU)
docker build -t warpgbm-mcp .
docker run --gpus all -p 8000:8000 warpgbm-mcp

# Fly.io, Railway, Render, etc.
# See their respective GPU deployment docs

# Install dev dependencies
pip install -r requirements-dev.txt

# Run all tests
./run_tests.sh

# Or use pytest directly
pytest tests/ -v

# Test specific functionality
pytest tests/test_train.py -v
pytest tests/test_integration.py -v

mcp-warpgmb/
├── app/
│   ├── main.py              # FastAPI app + routes
│   ├── mcp_sse.py           # MCP Server-Sent Events
│   ├── model_registry.py    # Model backend registry
│   ├── models.py            # Pydantic schemas
│   ├── utils.py             # Serialization, caching
│   ├── x402.py              # Payment verification
│   └── feedback_storage.py  # Feedback persistence
├── .well-known/
│   ├── mcp.json             # MCP capability manifest
│   └── x402                 # X402 pricing manifest
├── docs/
│   ├── AGENT_GUIDE.md       # Comprehensive agent docs
│   ├── MODEL_SUPPORT.md     # Model parameter reference
│   └── WARPGBM_PYTHON_GUIDE.md
├── tests/
│   ├── test_train.py
│   ├── test_predict.py
│   ├── test_integration.py
│   └── conftest.py
├── examples/
│   ├── simple_train.py
│   └── compare_models.py
├── modal_app.py             # Modal deployment config
├── local_dev.py             # Local dev server
├── requirements.txt
└── README.md

# Via API
curl -X POST https://warpgbm.ai/feedback \
  -H "Content-Type: application/json" \
  -d '{
    "feedback_type": "feature_request",
    "message": "Add support for XGBoost backend",
    "severity": "medium"
  }'