# fal.ai MCP Server

MCP (Model Context Protocol) server for [fal.ai](https://fal.ai) — access 600+ AI models for image generation, video creation, speech-to-text, text-to-speech, music generation, and more directly from Claude.

## Tools

| Tool | Description |
|------|-------------|
| `generate_image` | Text-to-image generation (FLUX, Recraft, etc.) |
| `edit_image` | Image editing, inpainting, upscaling |
| `generate_video` | Text/image-to-video (Kling, Veo, Sora, LTX) |
| `speech_to_text` | Audio transcription with Whisper |
| `text_to_speech` | Text-to-speech synthesis |
| `generate_music` | Music generation from text prompts |
| `search_models` | Search for available models on fal.ai |
| `run_model` | Run any fal.ai model with custom parameters |

## Setup

### 1. Get a fal.ai API Key

Sign up at [fal.ai](https://fal.ai) and get your API key from the [dashboard](https://fal.ai/dashboard/keys).

### 2. Configure Claude Desktop

Add to your Claude Desktop config (`~/Library/Application Support/Claude/claude_desktop_config.json` on macOS):

```json
{
  "mcpServers": {
    "fal-ai": {
      "command": "npx",
      "args": ["-y", "fal-ai-mcp"],
      "env": {
        "FAL_KEY": "your-fal-api-key"
      }
    }
  }
}
```

### 3. Configure Claude Code

```bash
claude mcp add fal-ai -e FAL_KEY=your-fal-api-key -- npx -y fal-ai-mcp
```

### Alternative: Install from source

```bash
git clone https://github.com/enescanguven/fal-mcp.git
cd fal-mcp
npm install
npm run build
claude mcp add fal-ai -e FAL_KEY=your-fal-api-key -- node dist/index.js
```

## Usage Examples

### Generate an Image

> "Generate a photorealistic image of a sunset over mountains"

Uses `fal-ai/flux/schnell` by default. You can specify other models:

> "Generate an image of a cat using the fal-ai/flux-pro/v1.1 model"

### Edit an Image

> "Upscale this image: https://example.com/photo.jpg"

### Generate a Video

> "Create a video of waves crashing on a beach"

### Transcribe Audio

> "Transcribe this audio file: https://example.com/recording.mp3"

### Text to Speech

> "Convert this text to speech: Hello, welcome to fal.ai!"

### Generate Music

> "Generate a 30-second lo-fi hip hop beat"

### Run Any Model

> "Run the fal-ai/nano-banana-2 model with prompt 'a beautiful landscape'"

## Available Models

fal.ai hosts 600+ models. Some popular ones:

**Image Generation:**
- `fal-ai/flux/schnell` — Fast FLUX generation (default)
- `fal-ai/flux/dev` — FLUX dev model
- `fal-ai/flux-pro/v1.1` — FLUX Pro
- `fal-ai/recraft/v4/pro/text-to-image` — Recraft V4

**Video Generation:**
- `fal-ai/kling-video/v3/pro/text-to-video` — Kling Video V3
- `fal-ai/veo3.1` — Google Veo 3.1
- `fal-ai/sora-2` — Sora 2

**Audio:**
- `fal-ai/whisper` — Speech-to-text
- `fal-ai/chatterbox/text-to-speech` — Text-to-speech

Browse all models at [fal.ai/models](https://fal.ai/models).

## License

MIT