Machine Learning

FAL AI MCP Server

Use Studio chat to drive this server — credentials stay in your workspace.

FAL AI is a machine learning platform specializing in image and video generation through AI models. Access state-of-the-art generative AI models for creating visual content, including text-to-image, image-to-image, and video generation with fast, scalable API infrastructure.

22 tools
Agent guide included
API Key
Start Chatting

Opens MCPBundles Studio with this server selected. After sign-in, chat and run tools from the same thread.

Browse all tools

AI Skill
SKILL.md

Domain knowledge for FAL AI — workflow patterns, data models, and gotchas for your AI agent.

FAL AI (REST bundle)

Same dashboard API key as the fal website. This bundle uses the queue HTTP API with Authorization: Key {api_key} and the fal Platform HTTP API (api.fal.ai/v1) for catalog and pricing.

Capabilities

  • Curated generators: ready-made flows for common image and video models with typed parameters.
  • Live catalog: search and filter models by text and category; inspect one endpoint's metadata, optional OpenAPI 3.0 expand for argument shapes, and list pricing.
  • Cost: list unit prices and POST structured estimates to the platform pricing API when you need batch or historical projections.
  • Generic execution: run any endpoint with a JSON argument object (blocking), or submit async jobs and poll status, fetch final JSON, or cancel.
  • Streaming: SSE collection for endpoints that support a stream subpath.
  • Files: upload local or MCP resources, pull a public URL down and push bytes to fal's CDN for model inputs.
  • History: list recent requests and fetch one by id from the REST activity API.
  • Docs index: search the published docs link list (llms.txt) for topics.

Data model

  • Queue: async jobs return request_id; use status then result (or a blocking run helper) depending on latency.
  • Platform catalog rows include endpoint_id, display metadata, and links to the model landing page.

Gotchas

  • Long video or training: prefer async submit + status/result over blocking run defaults.
  • For full request/response shapes on REST, request OpenAPI 3.0 expansion on catalog/model-info calls (fal expand=openapi-3.0); payloads are large — use a small limit when listing models.
  • Hosted MCP at mcp.fal.ai uses Bearer auth and overlapping capabilities; enable both if you want MCP-native clients and this REST bundle side by side.

Tools in this Server (22)

Cancel Fal Endpoint

Cancel a fal queue job for endpoint_id + request_id.

Estimate Fal Pricing

Estimate run cost via fal platform pricing API. Pass request_body_json: a JSON object per OpenAPI (e.g. {"estimate_type":"historical_api_price","endpo...

Generate Fal Image

Generate image using FAL AI FLUX model

Generate Fal Image To Video

Generate video from image using FAL AI Veo3 Image-to-Video model

Generate Fal Video

Generate video using FAL AI Veo3 model

Generate Image

Generate image using FAL AI Nano Banana model from text prompt only

Generate Image From Images

Generate new image from multiple input images using FAL AI Nano Banana model

Get Fal Endpoint Result

Wait until the fal queue job completes (if needed) and return the final JSON result for endpoint_id + request_id.

Get Fal Endpoint Status

Poll fal queue status for a given endpoint_id and request_id (from submit_fal_endpoint).

Get Fal Model Info

Get catalog metadata and unit pricing for a single fal endpoint_id (e.g. fal-ai/flux/dev). Returns description, category, model URL, and price rows. S...

Get Fal Model Pricing

Return fal list pricing for a model endpoint_id (USD per billing unit).

Get Fal Request

Get detailed information about a specific FAL request

List Fal Requests

List all FAL requests from remote API

Recommend Fal Models

Pass a natural-language task; searches the fal catalog and returns ranked models with metadata (same search backend as the hosted MCP recommend tool)....

Run Fal Endpoint

Run any fal model endpoint_id with a JSON arguments object; waits until completion and returns the result. Prefer submit_fal_endpoint + status helpers...

Search Fal Documentation

Search fal's public documentation index (llms.txt) and return matching doc links. Does not run full-text search inside each page.

Search Fal Models

Search fal's live model catalog by free-text query and/or category. Returns endpoint IDs, display names, descriptions, and model URLs. Use pagination ...

Stream Fal Endpoint

Stream SSE events from a fal endpoint (POST .../stream). Only some models support streaming; max_events caps how many events are collected.

Submit Fal Endpoint

Submit a fal endpoint job without waiting. Returns request_id and fal queue URLs; use get_fal_endpoint_status / get_fal_endpoint_result / cancel_fal_e...

Upload Fal File

Upload a file to FAL storage from the characters directory

Upload Fal Resource

Upload a resource://files/{user}/{name} to FAL via MCP resource read

Upload Fal Url

Download a file from a public HTTP(S) URL and upload it to fal's CDN. Returns access_url suitable for image_url / video_url parameters on models.

Frequently Asked Questions

What is the FAL AI MCP server?

FAL AI is a machine learning platform specializing in image and video generation through AI models. Access state-of-the-art generative AI models for creating visual content, including text-to-image, image-to-image, and video generation with fast, scalable API infrastructure. It provides 22 tools that AI agents can use through the Model Context Protocol (MCP).

How do I connect FAL AI to my AI agent?

Add the MCPBundles server URL to your MCP client configuration (Claude Desktop, Cursor, VS Code, etc.). The URL format is: https://mcp.mcpbundles.com/bundle/fal. Authentication is handled automatically.

How many tools does FAL AI provide?

FAL AI provides 22 tools that can be called by AI agents, along with a SKILL.md that gives your AI agent domain knowledge about when and how to use them.

What authentication does FAL AI require?

FAL AI uses API Key. FAL AI requires credentials. Connect via MCPBundles and authentication is handled automatically.

Setup Instructions

Connect FAL AI to any MCP client in minutes

https://mcp.mcpbundles.com/bundle/fal

What is MCP?

Model Context Protocol lets AI tools call external capabilities securely through a single URL. This bundle groups tools behind an MCP endpoint that many clients can use.

Use this bundle in 3 steps

  1. Copy the MCP URL above
  2. Open your AI tool and add a new MCP/connector
  3. Paste the URL and follow any auth prompts

Claude Desktop Users

Skip the manual setup! Use the .mcpb file format for one-click installation. Check the Claude Desktop tab for setup instructions.

Pick your tool tab for exact steps

Select ChatGPT, Cursor, Claude Code, or another tab for copy-paste config.

Ready to chat with FAL AI?

Same flow: Studio opens on this server after sign-in. Keep chatting to call tools from the conversation.

FAL AI MCP Server & Skill — 22 Tools