# fal (MCP Server)

> Search and run fal's image, video and audio generation models from chat

- Type: MCP server
- Publisher: fal (official)
- Categories: AI & ML, Design, Media & Entertainment
- Website: https://fal.ai/docs/model-apis/mcp
- Transport: streamable-http
- Server URL: https://mcp.fal.ai/mcp-relay
- Sign-in: oauth
- Listed: 2025-10-01

## About

fal's remote MCP server lets agents search its catalog of generative media models, inspect schemas and pricing, run models or submit long-running jobs, and upload input files. It uses Streamable HTTP with OAuth sign-in in the browser. fal also hosts a separate docs-only MCP server that needs no account.

## Install

1. **Connect it in ChatGPT** Turn on Developer mode in ChatGPT (Settings → Security and login), open Plugins, select + and paste https://mcp.fal.ai/mcp-relay as the MCP server URL, then sign in with OAuth. Add it to a chat from the composer's tools menu.

2. **Or add it to Codex or the API**

   Codex CLI:

   ```bash
   codex mcp add fal --url https://mcp.fal.ai/mcp-relay
   codex mcp login fal
   ```

   config.toml:

   ```toml
   [mcp_servers.fal]
   url = "https://mcp.fal.ai/mcp-relay"
   ```

   Responses API:

   ```python
   import os
   from openai import OpenAI
   
   client = OpenAI()
   
   response = client.responses.create(
       model="gpt-6-astra",
       tools=[{
           "type": "mcp",
           "server_label": "fal",
           "server_url": "https://mcp.fal.ai/mcp-relay",
           "authorization": os.environ["FAL_API_KEY"],
           "require_approval": "never",
       }],
       input="Generate a product photo of a ceramic mug on a wooden table",
   )
   print(response.output_text)
   ```

## Tools

- `search_models`
- `get_model_schema`
- `get_pricing`
- `search_docs`
- `recommend_model`
- `run_model`
- `submit_job`
- `check_job`
- `get_job_result`
- `cancel_job`
- `upload_file`

## Example prompts

- "Generate a product photo of a ceramic mug on a wooden table"
- "Which video models can do image-to-video, and what do they cost?"
- "Upscale this image to 4x"
- "Turn this script into a 10-second video clip"

## Also available as

- app: [fal](https://chatgptplugins.directory/apps/fal.md)

## Related

- [Excalidraw](https://chatgptplugins.directory/mcp/excalidraw.md): Draw hand-drawn Excalidraw diagrams live inside ChatGPT, Claude and VS Code
- [Browser Use](https://chatgptplugins.directory/mcp/browser-use.md): Run Browser Use cloud browser agents or control a local browser over MCP
- [Memory](https://chatgptplugins.directory/mcp/memory.md): Knowledge graph-based persistent memory across conversations
- [Mem0](https://chatgptplugins.directory/mcp/mem0.md): Hosted long-term memory for AI agents and clients
- [shadcn/ui](https://chatgptplugins.directory/mcp/shadcn-ui.md): Browse, search and install shadcn/ui components and registry blocks
- [Sequential Thinking](https://chatgptplugins.directory/mcp/sequential-thinking.md): Structured, reflective step-by-step problem solving for LLMs

---
Source: https://chatgptplugins.directory/mcp/fal · Index: https://chatgptplugins.directory/llms.txt · Independent and community-run. Not affiliated with or endorsed by OpenAI. ChatGPT is a trademark of OpenAI.
