# fal.ai MCP by usefulapi

> fal.ai MCP by usefulapi is a freemium MCP server for ai models and llm tooling. Hosted MCP server that lets AI clients run fal.ai image and video models and track their. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Starting price:** $9 a month
- **Platforms:** API, Web, vscode
- **Website:** https://usefulapi.io/falai/
- **Repository:** https://github.com/m190/usefulapi-mcp/tree/HEAD/servers/falai
- **MCP Registry name:** io.usefulapi/falai
- **Categories:** AI models and LLM tooling
- **Listing updated:** 2026-11-18

## About

The README describes it as a hosted endpoint, so there is nothing to install locally. Once connected, an assistant such as Claude or ChatGPT can search the fal.ai model registry, read the input schema of a model before sending anything, and submit a job either as a fire-and-wait run or as a queued request it checks on later.

Jobs that run on the queue return a request id, so you can check whether a request is still waiting, in progress or completed, fetch its output, or cancel it while it has not started. Each call that consumes fal credits is marked as a write action, so clients typically ask for approval before running it.

The server is aimed at developers and creators who already have a fal.ai account and want to drive image and video generation from a chat or coding client. Access is through a fal.ai API key entered at login, and usage is metered per month on the usefulapi side, separate from fal.ai billing.

## Features

- **Model registry search:** Finds fal.ai models by keyword with paginated results.
- **Input schema lookup:** Returns a model's OpenAPI input and output fields before a run.
- **Run and wait:** Submits a model run and returns the result once it completes, or a request id if it takes too long.
- **Queue management:** Submits requests to the queue, checks their status and fetches results.
- **Cancel queued requests:** Cancels requests that have not started yet.
- **Usage and plan tools:** Reports monthly tool-call usage and handles Pro and Pro+ upgrades and cancellation.

## Good for

- Pick an image or short video model by describing the output you need
- Check the required inputs of a fal.ai model before sending a job
- Run image generation from inside Claude, ChatGPT or Cursor
- Queue long-running generations and check their status later
- Cancel a queued fal.ai job that is no longer needed

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http falai https://falai.usefulapi.io/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://falai.usefulapi.io/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "falai": {
      "url": "https://falai.usefulapi.io/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "falai": {
      "type": "http",
      "url": "https://falai.usefulapi.io/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "falai": {
      "serverUrl": "https://falai.usefulapi.io/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "falai": {
      "type": "http",
      "url": "https://falai.usefulapi.io/mcp"
    }
  }
}
```

## Tools

- `falai_list_models`: List or search fal.ai models in the registry (paginated).
- `falai_get_model_schema`: Get the OpenAPI 3 schema for a model, including its input and output fields.
- `falai_get_request_status`: Get the status of a queued request (IN_QUEUE, IN_PROGRESS, COMPLETED).
- `falai_get_request_result`: Get the final output of a completed queued request.
- `falai_submit_request`: Submit an inference request to the queue and return immediately.
- `falai_run_model`: Submit a request, poll until completed, then return the result.
- `falai_cancel_request`: Request cancellation of a queued request that has not started.
- `falai_usage_status`: Report the caller's current usage and plan limit.
- `falai_request_feature`: Send a request for a feature the fal.ai tools cannot yet do.
- `falai_upgrade`: Get a Pro or Pro+ paid plan for fal.ai.
- `falai_cancel_subscription`: Cancel the Pro subscription at the end of the paid period.

## FAQ

### Is this an official fal.ai product?

No. The FAQ says usefulapi is an independent service, not affiliated with or endorsed by fal.ai.

### Which AI clients can connect?

Any client that supports remote MCP servers over Streamable HTTP with OAuth login, including Claude, Claude Code, ChatGPT, Codex, Cursor, VS Code and Windsurf.

### Do I need to put my fal.ai key in the config file?

No. The page says to add only the URL. The server signs you in with OAuth, and the login page asks for your fal.ai API key.

### What does it cost?

The Free plan allows 50 tool calls per month. Pro is $9/month or $90/year for 10,000 calls, and Pro+ is $39/month or $390/year for 100,000 calls.

### Is fal.ai MCP by usefulapi free?

fal.ai MCP by usefulapi has a free plan, with paid plans for more usage or features. Paid plans start at $9 a month.

### How do I add fal.ai MCP by usefulapi to Claude Code?

Run this command in your terminal: claude mcp add --transport http falai https://falai.usefulapi.io/mcp

### What are the best alternatives to fal.ai MCP by usefulapi?

The closest alternatives to fal.ai MCP by usefulapi are Claude Code Ultimate Guide, signafAIde, Toolkien, Lugh and HypePaper.

## Where this comes from

- Description: written from the project's README, the project's website and its MCP Registry entry.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [signafAIde](https://ai-powered.com/mcp/signafaide): signafAIde is a freemium MCP server for security.
- [Toolkien](https://ai-powered.com/mcp/toolkien): Toolkien is an open-source MCP server for ai models and llm tooling.
- [Lugh](https://ai-powered.com/mcp/lugh): Lugh is an open-source MCP server for ai models and llm tooling.
- [HypePaper](https://ai-powered.com/mcp/hypepaper): HypePaper is a freemium MCP server for ai models and llm tooling.
- [Agent Data Tools: Compact (find, describe, run)](https://ai-powered.com/mcp/agent-data-tools-compact-find-describe-run): Agent Data Tools: Compact (find, describe, run) is a freemium MCP server for developer tools.
- [Angel Agent Guard: pre-purchase check + prompt-injection scan](https://ai-powered.com/mcp/angel-agent-guard-pre-purchase-check-prompt-injection-scan): Angel Agent Guard: pre-purchase check + prompt-injection scan is a freemium MCP server for ai models and llm tooling.
- [Mizan Calibration](https://ai-powered.com/mcp/mizan-calibration): Mizan Calibration is a free MCP server for ai models and llm tooling.

---
Source: https://ai-powered.com/mcp/fal-ai-mcp-by-usefulapi
