🌾 CropProphEU — EU Crop Intelligence MCP Server

12 Tools, 5 Crops, 26 EU Countries, 120 NUTS2 Regions — Yield forecasts, market values (€/ha), risk analysis & portfolio optimization for European agriculture. Built for AI agents, by AI agents.

"How will wheat perform in Sachsen-Anhalt this year? What's my best €/ha allocation across 100 ha?"

pip install git+https://github.com/DasClown/CropProphEU.git

Features (12 MCP Tools)

Quick Start

1. Install

pip install git+https://github.com/DasClown/CropProphEU.git

2. Use as MCP Server

CLI (stdio):

crop-mcp

Python API:

from crop_mcp import predict_europe_yield

result = predict_europe_yield("DE11", "DE", crop="wheat", gdd=3050, precip_mm=650)
print(f"Yield: {result['predicted_yield_t_ha']} t/ha")
print(f"Revenue: ~{result['predicted_yield_t_ha'] * 239:.0f} €/ha")

3. Claude Desktop / Cursor

{
  "mcpServers": {
    "crop": {
      "command": "python3",
      "args": ["-m", "crop_mcp.server"]
    }
  }
}

4. HTTP Server (Remote / Smithery)

pip install crop-mcp[http]
crop-mcp --http --port 8080

Connect via SSE: http://your-server:8080/sse

5. Docker

docker build -t crop-mcp .
docker run -p 8080:8080 crop-mcp crop-mcp --http --port 8080

Verified Crops — Data Integrity ✅

Every prediction traces to a verified Eurostat crop code. No hallucinations, no silent wrong-crop training.

⚠️ V5.1d Data Fix: Rapeseed + Sunflower were previously trained on RICE data (wrong Eurostat codes C2000/C2200). Now corrected to Industrial crop codes I1110/I1120. DE rapeseed prediction fell from 7.21t to 2.63t — real, not extrapolated.

Why CropProphEU?

Unique: Only free MCP server covering EU agriculture with soil → yield → market value → portfolio optimization in one pipeline.

Model Accuracy

Most accurate for core EU (DE, FR, BE, NL, AT, CZ) where training data is dense.

Per-Crop Performance (V5.2)

Live Market Prices

Production costs (€/ha): Wheat 650, Corn 700, Barley 600, Rapeseed 780, Sunflower 650

Data Sources

Zero API keys required — all sources are free and public.

Example Output

German (default):

Weizen – Region DEE0 (DE)
Ertrag: 7.35 t/ha (Spanne 6.50–8.20)
Temperatur: warm (2950°C Wärmesumme)
Niederschlag: ausreichend (480 mm)
Bodenfeuchte: feucht (48%)
Modellabweichung: ±11.5% (1603 Samples, 26 Länder)
Vergleich zu 2024: +0.15 t/ha (im Rahmen des Vorjahres)
Marktwert: 1.757 €/ha @ 239 €/t
Kosten: 650 €/ha → Deckungsbeitrag: 1.107 €/ha

English (with language="en"):

Wheat – Region DEE0 (DE)
Yield: 7.35 t/ha (range 6.50–8.20)
Temperature: warm (2950°C GDD)
...

Architecture

crop-mcp/
├── crop_mcp/
│   ├── server.py                 # 12 MCP tools
│   ├── europe_model_api.py       # RF (200 trees) + Yield-at-Risk + NDVI correction
│   ├── ndvi_correction.py        # Sentinel-2 NDVI correction factor (±30%)
│   ├── market_prices.py          # Live CBOT/MATIF via Yahoo Finance
│   ├── feature_cache.py          # Sub-second historical queries
│   ├── simulate_yield.py         # Analog-year matching
│   ├── auto_update.py            # Monthly retrain cron
│   ├── core/regions.py           # 120 NUTS2 regions
│   └── sources/                  # Weather, soil, NDVI, Eurostat, FAOSTAT fetchers
├── models/                       # .pkl files (download from Releases)
├── data/                         # Training data (generated by build)
├── crop_mcp/tools/               # V5.1 tools
│   ├── compare_regions.py        # Batch comparison
│   └── portfolio_optimizer.py    # Investment engine
├── pyproject.toml
└── README.md

Key design principles:

• No hallucination — every yield prediction traces to verified Eurostat data
• Live prices — CBOT wheat/corn via Yahoo Finance, updated hourly
• Self-updating — monthly cron rebuilds models with latest Eurostat data
• Zero API keys — all data sources are free and public
• AI-for-AI — built for agents, no dashboards

Building & Training

# Build training data (25 min per crop)
python3 build_europe.py --crop corn

# Train model (2 min)
python3 train_europe_fast.py --crop corn

# Auto-update monthly (cron: 1st of month at 06:00)

Commercial Use Cases

• Agri-trading desks: "What's wheat worth in Picardie at current MATIF prices?"
• Farm advisory: "How does this season compare to the last 5 years?"
• Insurance / Risk: Yield-at-Risk (P10/P50/P90) per region + crop
• EU policy analysis: Climate scenario impact on national yields
• Investment: Portfolio optimizer for 100+ ha allocation decisions

License

MIT — free to use, modify, and distribute.

Built with ❤️ for AI agents that need real, verifiable crop intelligence.