# fal MCP server

> Find generative media models, check schemas and pricing, upload inputs and run image, video and audio generations on fal.

- Listing: https://mcp.tc/i/fal
- Connect: use the server's own URL `https://mcp.fal.ai/mcp-relay` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: OAuth sign-in
- Category: [AI & Machine Learning](https://mcp.tc/c/ai-ml)
- Vendor: fal
- Homepage: <https://fal.ai/docs/documentation/setting-up/mcp>

## About

Connects an assistant to fal's generative media platform. It can search for models, read their input schemas and pricing, upload input files and run image, video and audio generations, then return the results with download links.

It runs as a hosted Streamable HTTP endpoint at https://mcp.fal.ai/mcp-relay. Authentication is OAuth through the browser, so no API key or authorization header is needed. Generations use fal credits. A separate Platform MCP covers account operations and a documentation MCP covers public docs.

## What it can do

- Search fal's generative media models
- Read model input schemas
- Check estimated pricing before running
- Upload input files for generations
- Run image, video and audio generations
- Return finished results with download links

## Example prompts

- "Use fal to search for image generation models. Do not run a model."
- "Use fal to create a minimal image for a coffee subscription website and show the cost first."
- "Use fal to make a short cinematic video of ocean waves at sunset."
- "Upload this photo to fal and show which models accept it as input."

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport http fal https://mcp.fal.ai/mcp-relay
```

2. Start Claude Code, type `/mcp`, pick **fal** and choose **Authenticate**. A browser window opens for the fal sign-in.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Settings → Connectors** and click **Add custom connector**.

2. Name it **fal** and paste this URL:

```url
https://mcp.fal.ai/mcp-relay
```

3. Click **Add**, then **Connect**, and sign in when fal asks.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=fal&connectorUrl=https%3A%2F%2Fmcp.fal.ai%2Fmcp-relay>) (opens connector settings)

2. Check that the URL reads `https://mcp.fal.ai/mcp-relay` and click **Add**.

3. Click **Connect** and sign in when fal asks.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, open **Settings → Security and login** and turn on **Developer mode**.

2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server.

3. Paste `https://mcp.fal.ai/mcp-relay` as the server URL and choose **OAuth**. ChatGPT sends you to fal to sign in.

Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts.

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=fal&config=eyJ1cmwiOiJodHRwczovL21jcC5mYWwuYWkvbWNwLXJlbGF5In0%3D>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "fal": {
      "url": "https://mcp.fal.ai/mcp-relay"
    }
  }
}
```

Cursor shows **Needs login** next to the server. Click it to sign in.

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=fal&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fmcp.fal.ai%2Fmcp-relay%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"fal","type":"http","url":"https://mcp.fal.ai/mcp-relay"}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "fal": {
      "type": "http",
      "url": "https://mcp.fal.ai/mcp-relay"
    }
  }
}
```

VS Code asks you to sign in the first time the server starts.

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "fal": {
      "serverUrl": "https://mcp.fal.ai/mcp-relay"
    }
  }
}
```

2. Refresh the MCP server list in Cascade and sign in when asked.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

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

Or edit `~/.codex/config.toml` directly:

`config.toml`:

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

### Gemini CLI

```bash
gemini mcp add --transport http fal https://mcp.fal.ai/mcp-relay
```

Then, inside Gemini CLI, run `/mcp auth fal` to sign in.

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

```json
{
  "mcpServers": {
    "fal": {
      "type": "http",
      "url": "https://mcp.fal.ai/mcp-relay"
    }
  }
}
```

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://mcp.fal.ai/mcp-relay`.

## Details

- Last checked: 2026-10-03 (reachable, asks for credentials)
- Listed: 2026-10-03
- Updated: 2026-10-03

---
Source: https://mcp.tc/i/fal (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report