Fal MCP Server

MCP server for fal.ai - Run 600+ AI models for image, video, audio generation and more

Local serverstdio

What is the Fal MCP server?

If you already use Fal, the fal mcp server is the piece that lets your assistant work with it directly. MCP server for fal.ai - Run 600+ AI models for image, video, audio generation and more.

What the server does

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

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • 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

Installation

Installation goes through your MCP client rather than a global install: point it at fal-ai-mcp on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

Credentials and setup notes

Configuration is passed through the environment: FAL_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Where it fits

Among the AI and media services options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Fal's toolset — generate_image, edit_image, generate_video and 5 more — is a fair guide to whether it matches your workflow. It is maintained by enescanguven; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
generate_imageText-to-image generation (FLUX, Recraft, etc.)
edit_imageImage editing, inpainting, upscaling
generate_videoText/image-to-video (Kling, Veo, Sora, LTX)
speech_to_textAudio transcription with Whisper
text_to_speechText-to-speech synthesis
generate_musicMusic generation from text prompts
search_modelsSearch for available models on fal.ai
run_modelRun any fal.ai model with custom parameters

How to install the Fal MCP server

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

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
FAL_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Fal to generate image.
  • Use Fal to edit image.
  • Use Fal to generate video.

Frequently asked questions

It connects Fal to MCP-compatible AI assistants such as Claude and Cursor, exposing 8 tools (generate_image, edit_image, generate_video, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Fal directly.