# WindAI MCP Server

AI-powered wind resource assessment tools for Claude, ChatGPT, Cursor, and other AI assistants via the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/).

Get wind speed estimates, compare sites, and run full ML-powered wind farm assessments from any MCP-compatible AI assistant.

**Website:** [windai.tech](https://windai.tech?utm_source=mcp-readme)

## Quick Start

### Claude Desktop

Add to your Claude Desktop configuration (`~/Library/Application Support/Claude/claude_desktop_config.json` on macOS or `%APPDATA%\Claude\claude_desktop_config.json` on Windows):

```json
{
  "mcpServers": {
    "windai": {
      "command": "npx",
      "args": ["-y", "windai-mcp"]
    }
  }
}
```

Restart Claude Desktop, then ask:

> "What's the wind potential at latitude 40.5, longitude -105.2?"

### Claude Code

```bash
claude mcp add windai -- npx -y windai-mcp
```

### Cursor / Other MCP Clients

Add a similar configuration using `npx -y windai-mcp` as the command.

### Global Install

```bash
npm install -g windai-mcp
windai-mcp
```

## Tools

### `get_wind_estimate` (Free)

Get an approximate wind resource estimate for any location on Earth. No API key required.

**Input:**
- `latitude` (required): Latitude (-90 to 90)
- `longitude` (required): Longitude (-180 to 180)
- `hub_height` (optional): Hub height in meters (default: 100)

**Returns:** Mean wind speed, IEC wind class, wind quality assessment, monthly breakdown, wind power density.

**Example prompt:** "Estimate the wind resource at 52.5N, 1.8E at 120m hub height"

### `get_wind_farm_assessment` (Requires API Key)

Run a full AI-powered wind resource assessment using WindAI's deep learning model (391-feature neural network trained on 10M+ hourly observations from 289 wind farms).

**Input:**
- `latitude` (required): Latitude
- `longitude` (required): Longitude
- `api_key` (required): WindAI API key (starts with `wai_`)
- `hub_height` (optional): Hub height in meters
- `rated_power` (optional): Turbine rated power in kW
- `rotor_diameter` (optional): Rotor diameter in meters
- `turbines_count` (optional): Number of turbines
- Plus: `swept_area`, `total_power`

**Returns:** 8,760+ hourly capacity factors, AEP, P50/P90, monthly and diurnal profiles.

**Get an API key:** [windai.tech/account](https://windai.tech/account)

### `compare_wind_sites` (Free)

Compare wind potential at multiple locations side by side. Up to 5 locations.

**Input:**
- `locations` (required): Array of `{ latitude, longitude, name? }` objects (2-5 sites)

**Returns:** Ranked comparison table sorted by wind quality.

**Example prompt:** "Compare wind potential at these sites: Denver CO (39.7, -105.0), Amarillo TX (35.2, -101.8), and Cheyenne WY (41.1, -104.8)"

### `get_windai_pricing` (Free)

Get current pricing information for WindAI assessments.

**Returns:** Credit packages, per-site pricing, what's included, and signup links.

### `get_windai_model_info` (Free)

Get information about WindAI's ML model, training data, and accuracy metrics.

**Returns:** Architecture details, training data stats, accuracy metrics, validation methodology.

## Pricing

| Package | Credits | Total | Per Site | Savings |
|---------|---------|-------|----------|---------|
| Single | 1 | $49.99 | $49.99 | -- |
| Starter | 10 | $449.90 | $44.99 | 10% |
| Pro | 25 | $999.75 | $39.99 | 20% |
| Enterprise | 100 | $3,499.00 | $34.99 | 30% |

Buy credits at [windai.tech/credits](https://windai.tech/credits).

## Data Sources

- **Free tools:** Open-Meteo ERA5 Historical Reanalysis (2021-2023), no API key needed
- **Paid assessments:** WindAI's proprietary deep learning model using ERA5, MERRA2, Copernicus DEM, and turbine specs

## Development

```bash
git clone <repo-url>
cd windai-mcp
npm install
npm run dev
```

Build for production:

```bash
npm run build
npm start
```

## Links

- [WindAI Website](https://windai.tech)
- [API Documentation](https://windai.tech/api-docs)
- [Research & Methodology](https://windai.tech/research)
- [Free Wind Tools](https://windai.tech/tools)
- [Blog](https://windai.tech/blog)

## License

MIT