Generate images with FLUX, create videos, remove backgrounds, upscale images, transcribe audio, and generate music using Fal.ai's fast inference platform.
Use with AI AssistantsMCP
Connect Claude, Cursor, or any MCP-compatible client — then call tools directly
① Add This MCP Server
Paste into your AI client config — then all its tools are available instantly.
{
"mcpServers": {
"fal-ai": {
"url": "https://mcp.aerostack.dev/s/aerostack/mcp-fal-ai",
"headers": {
"Authorization": "Bearer YOUR_AEROSTACK_TOKEN"
}
}
}
}Replace YOUR_AEROSTACK_TOKEN with your API token from the dashboard.
② Call a Tool
Ask your AI assistant to call a specific tool, or send raw JSON-RPC:
Natural Language Prompt
“Use the _ping tool to verify fal.ai credentials by calling a lightweight read endpoint. used internally by aerostack to validate credentials”
Using a Workspace?
Add this MCP to your Workspace — your team shares one token, secrets are stored securely, and every AI agent in the workspace can call it without per-user setup.
Generate images with FLUX, create videos, remove backgrounds, upscale images, transcribe audio, and generate music using Fal.ai's fast inference platform.
Live endpoint: https://mcp.aerostack.dev/s/aerostack/mcp-fal-ai
This MCP server gives AI agents access to fal.ai via 12 tools. Connect it to any Aerostack workspace and your agents can interact with fal.ai directly.
| Tool | Description |
|---|---|
generate_image | Generate images from text prompts using FLUX.1 Schnell — ultra-fast 4-step generation |
generate_image_flux_pro | Generate high-quality professional images using FLUX.1 Pro — best quality, slower generation |
generate_video | Generate short animated videos from text prompts using AnimateDiff on Fal.ai |
image_to_image | Transform an existing image using FLUX Dev image-to-image — modify style or content while preserving structure |
remove_background | Remove the background from any image using rembg AI model |
upscale_image | Upscale an image 2x or 4x using ESRGAN AI upscaling |
run_model | Run any Fal.ai model directly with custom input parameters. Use this for models not covered by other tools |
submit_async_job | Submit a Fal.ai model job to the async queue for long-running generation tasks |
get_async_result | Get the result of an async Fal.ai job by request ID |
transcribe_audio | Transcribe or translate audio using Whisper on Fal.ai — supports 99+ languages |
generate_music | Generate music and audio from text descriptions using Stable Audio on Fal.ai |
list_models | List popular Fal.ai models with their IDs, types, and descriptions |
| Variable | Required | Description |
|---|---|---|
FAL_AI_API_KEY | Yes | Fal.ai API key from https://fal.ai/dashboard/keys |
Add the following secrets under Project → Secrets:
FAL_AI_API_KEYOnce added, every AI agent in your workspace can use fal.ai tools automatically.
curl -X POST https://mcp.aerostack.dev/s/aerostack/mcp-fal-ai \
-H 'Content-Type: application/json' \
-H 'X-Mcp-Secret-FAL-AI-API-KEY: your-fal-ai-api-key' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"generate_image","arguments":{}}}'
MIT
Live Endpoint
https://mcp.aerostack.dev/s/aerostack/mcp-fal-ai
Sub-50ms globally · Zero cold start
@aerostack
Pre-built functions for the most common MCP tool patterns. Clone, extend, and deploy.
by @aerostack
Design creation, AI generation, editing, export, assets, brand kits, folders via Canva's official MCP
by @aerostack
Conversations, contacts, tickets, articles via Intercom's official MCP
by @aerostack
Call Claude models directly — run AI conversations, tool-use chains, batch jobs, and model comparisons from any agent.
by @aerostack
Deployments, projects, domains, env vars, logs via Vercel's official MCP
by @aerostack
Read, send, and search Gmail messages — manage labels, drafts, and attachments with full inbox control.
by @aerostack
Manage audiences, campaigns, and subscriber tags in Mailchimp — automate your email marketing with AI.
Yes. The Fal Ai MCP gives Claude tools to send async jobs directly through your Fal Ai account. Just describe what you want to send and Claude handles the Fal Ai API call.
Yes. The Fal Ai MCP includes tools to list and retrieve models from your Fal Ai account. Claude can filter, sort, and summarize models based on your instructions.
Yes. The Fal Ai MCP uses the open Model Context Protocol standard, so it works in Claude, Cursor, Windsurf, and any other MCP-compatible AI tool. All 12 Fal Ai tools are available everywhere you connect it — install once on Aerostack.
Yes. The Fal Ai MCP includes run and trigger tools that let Claude execute Fal Ai actions on demand. This is useful for automating repetitive Fal Ai tasks directly from a Claude or Cursor session.