Install fal.ai MCP Server

Pick your client, copy the command, done.

claude mcp add -e "FAL_KEY=${FAL_KEY}" fal-ai -- npx -y fal-ai-mcp

Required:FAL_KEY

Environment Variables

Set these before running fal.ai MCP Server.

VariableDescriptionRequired

FAL_KEYYour fal.ai API key obtained from the dashboardYes

Once configured, fal.ai MCP Server gives your AI agent access to:

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

After setup, try these prompts with your AI agent:

→Generate a photorealistic image of a sunset over mountains

→Create a video of waves crashing on a beach

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

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

→Generate a 30-second lo-fi hip hop beat

Prerequisites & system requirements

An MCP-compatible client (Claude Code, Cursor, Windsurf, Claude Desktop, or Codex)
Node.js 18+ with npm/npx installed
FAL_KEY — Your fal.ai API key obtained from the dashboard

Alternative installation methods

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

git clone https://github.com/enescanguven/fal-mcp.git && cd fal-mcp && npm install && npm run build

Save the docs, env vars, and workflow around fal.ai MCP Server in Conare so Claude Code, Codex, and Cursor remember it next time.