# Fal

Create and edit high-quality media across various formats including images, videos, audio, and 3D models. Enhance creative workflows by performing advanced tasks like background removal, image upscal…

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y smithery mcp add aiamindennapokban/fal-ai-mcp

# Browse available tools
npx -y smithery tool list aiamindennapokban/fal-ai-mcp

# Get full schema for a tool
npx -y smithery tool get aiamindennapokban/fal-ai-mcp generate-image

# Call a tool
npx -y smithery tool call aiamindennapokban/fal-ai-mcp generate-image '{}'
```

## Direct MCP Connection

Endpoint: `https://fal-ai-mcp--aiamindennapokban.run.tools`

**Required config:**
- `FAL_KEY` (query) — fal.ai API key (get it from fal.ai/dashboard/keys)

## Tools (9)

- `generate-image` — Generate images from a text prompt. Models: flux-dev (balanced), flux-schnell (fast), flux-pro (best quality), recraft-…
- `edit-image` — Edit or transform an existing image using AI. Models: flux-kontext (default), nano-banana-2-edit (Gemini 3.1 Flash, fas…
- `generate-video` — Generate a video from text and/or an image. Models: kling-v3-pro (best), sora-2-t2v, sora-2-i2v, ltx-2 (fast), wan-v2
- `generate-audio` — Generate audio: speech, music, or sound effects. Models: chatterbox-tts (TTS), minimax-speech (HD TTS), beatoven-music …
- `generate-3d` — Generate a 3D model from an image. Models: meshy-v6, trellis-2 (fast)
- `remove-background` — Remove the background from an image
- `upscale-image` — Upscale an image to higher resolution (4x by default)
- `run-model` — Run any fal.ai model directly with custom arguments. Use for models not in the catalog or for advanced parameter contro…
- `list-models` — List available fal.ai models from the built-in catalog. Filter by category: "image", "image_edit", "video", "audio", "3…

```bash
# Get full input/output schema for a tool
npx -y smithery tool get aiamindennapokban/fal-ai-mcp <tool-name>
```

## Prompts (3)

- `generate-image` (description, model) — Generate an image from a text description
- `edit-image` (image_url, instructions) — Edit an existing image with AI
- `generate-video` (description, model) — Generate a video from a text description