fal MCP ServerConnect your AI to 1,000+ models
A hosted endpoint that lets any AI assistant search, run, and chain more than 1,000 generative AI models directly from a conversation — image, video, audio, 3D, upscaling, and more. One command. No SDK. No docs to read.
Up and running in three steps
The fal MCP Server is hosted — there is nothing to install and nothing to run locally. Point your client at mcp.fal.ai and start generating.
1. Get your fal API key
Every request your assistant makes is authorized with your own fal API key. Create one in the dashboard — it takes a few seconds.
Get your API key →2. Add the fal MCP server to your client
Run this in your terminal:
claude mcp add --transport http fal-ai \
https://mcp.fal.ai/mcp \
--header "Authorization: Bearer $FAL_KEY"
3. Ask for anything
That's it. Your assistant now has access to every model on fal — it searches the catalog, checks pricing, picks the right model, and runs it, all in one turn.
Read the MCP docs
Setup guides for every client, the full tool reference, and troubleshooting tips.
Open the Docs →Manage your API keys
Create, rotate, and scope the keys your assistant uses to run models on fal.
Open Dashboard →Join the fal Discord
Share what you build, get help from the team, and see what others are running through MCP.
Join Discord →
9 tools, zero configuration
The MCP server exposes nine tools that your assistant picks automatically. You never call them directly — you just describe what you want.
search_modelsSearch 1,000+ models by keyword or category.
get_model_schemaGet full input/output parameters for any model.
get_pricingCheck costs before running.
search_docsSearch fal documentation for guides and examples.
run_modelRun any model and return the result.
submit_jobSubmit long-running jobs — video, 3D, training.
check_jobCheck status, get results, or cancel.
upload_fileUpload files to fal's CDN for model input.
recommend_modelDescribe what you want and get model recommendations.
What can you do with it?
Real prompts, straight from a conversation. Copy one into your assistant and watch it pick the models, run them, and hand back the results.
Generate images with the best model
Your assistant searches the catalog, finds the most suitable model, checks the parameters, and runs it — all in one turn. The assistant picks the model. You describe the result.
Chain LLM + image generation
An LLM writes a detailed prompt with lighting, camera angle, and mood — then the image model generates with it. Dramatically better than a simple prompt.
Turn a photo into a video
Upload → model selection → queue management → result. All handled automatically.
Run a full creative pipeline
Three models chained in one conversation: an LLM writes the copy, an image model generates the visual, a TTS model reads the tagline. You get all the URLs back.
Compare models side by side
Run both, see both results. Model benchmarking in one sentence.
Check pricing before you run
Know the cost before you spend.
Chain complex workflows
Chain generation → upscaling → analysis in a single conversation.
Stateless, isolated, and free to use
Your assistant sends a request to mcp.fal.ai with your API key, the server calls the fal Platform API on your behalf, and the results come straight back to your conversation.
Hosted and stateless
The server is fully stateless and hosted on Vercel. No sessions, no state — each request is completely isolated.
Your key is never stored
Your fal API key is sent per-request in the Authorization header and is never stored. The server has no access to anything beyond what the public fal API provides with your key.
Free to use
The MCP server is free. You only pay for the model runs you trigger, at standard fal pricing.
Common questions about the fal MCP Server
What is the fal MCP Server?
The fal MCP Server is a hosted endpoint at mcp.fal.ai that lets any AI assistant search, run, and chain 1,000+ generative AI models on fal directly from a conversation. It is built on the Model Context Protocol (MCP), an open standard that lets AI assistants use external tools. Your assistant doesn't just generate code that calls fal — it actually calls fal.
Which AI assistants are supported?
Any MCP-compatible client works. Claude Code connects with a single terminal command, and Claude Desktop, Cursor, and Windsurf connect with a short JSON config pointing at https://mcp.fal.ai/mcp.
How much does it cost?
The MCP server itself is free. You only pay for the model runs your assistant triggers, at standard fal pricing — the same rates as calling the API directly. Your assistant can even check the price of a model with the get_pricing tool before running it.
Is my API key stored anywhere?
No. Your API key is sent per-request in the Authorization header and is never stored. The server is fully stateless — no sessions, no state — and each request is isolated. It has no access to anything beyond what the public fal API provides with your key.
What tools does the server expose?
Nine tools that your assistant picks automatically: search_models, get_model_schema, get_pricing, and search_docs for discovery; run_model, submit_job, and check_job for execution; upload_file and recommend_model as utilities. You never call them directly — you just describe what you want.
What kinds of models can I run?
The entire fal catalog: image generation, video generation, audio and text-to-speech, 3D, upscaling, LLMs, vision models, and more — over 1,000 models in total.
Can my assistant chain multiple models together?
Yes — that's one of the biggest advantages. A single request like "generate a futuristic Tokyo street, upscale it to 4K, and describe what's in it" chains generation, upscaling, and analysis in one conversation. The assistant handles uploads, queueing, and passing results between models.
Where do I get a fal API key?
Create one in the fal dashboard at fal.ai/dashboard/keys. It takes a few seconds, and the same key works for the MCP server and the regular fal API.
Ready to transform your enterprise with AI?
Take the first step towards AI-driven innovation. Our team of ML engineers is ready to help you prototype, develop, and scale your AI solutions.