# deAPI MCP Server

> deAPI MCP Server is an MCP server for design and media. 39 tools for transcription, image and video generation, OCR, speech and music via deAPI. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Platforms:** API, self-hosted
- **Repository:** https://github.com/deapi-ai/mcp-server-deapi
- **MCP Registry name:** io.github.deapi-ai/mcp-server-deapi
- **Categories:** [design and media](https://ai-powered.com/categories/design-and-media), [AI models and LLM tooling](https://ai-powered.com/categories/ai-and-llm)
- **Listing updated:** 2026-11-18

## About

The server wraps deAPI's v2 client API so an assistant can run media jobs on deAPI's models. Tools cover audio transcription with Whisper models, transcribing videos from YouTube, Twitter/X, Twitch, Kick and TikTok, text-to-speech, music from a description and lyrics, text-to-image, image-to-image, OCR, background removal, upscaling, text-to-video, image-to-video and audio-to-video.

Most generation tools have a matching `_price` tool that reports the cost before you run it, and `get_balance` shows the account balance. Jobs are asynchronous; the server polls with adaptive intervals, and `check_job_status` can wait and return the finished result, reporting error reason, retryability and refund state on failure. Generation tools accept a signed webhook URL.

Parameters such as width, steps and fps default to the chosen model's own values, which `get_available_models` lists. It is built with FastMCP and Python 3.11+, authenticates with a deAPI token via OAuth or bearer header, and also runs as a hosted remote endpoint.

## Features

- **Cost lookups:** Each generation tool has a price tool to check cost first.
- **Adaptive polling:** Async jobs are polled at intervals suited to the job type.
- **Signed webhooks:** Generation tools can notify an HTTPS URL when finished.
- **Model-driven defaults:** Unset parameters follow the selected model's own values.
- **Error recovery:** Retries with exponential backoff and refund reporting.
- **OAuth with PKCE:** Token exchange for Claude Desktop and Claude.ai connectors.

## Good for

- Transcribe a YouTube video or audio file
- Generate an image or short video from a prompt
- Extract text from a screenshot with OCR
- Remove an image background or upscale a photo
- Compare costs before running a job

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http mcp-server-deapi https://mcp.deapi.ai/mcp
```

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

```sh
https://mcp.deapi.ai/mcp
```

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

```json
{
  "mcpServers": {
    "mcp-server-deapi": {
      "url": "https://mcp.deapi.ai/mcp"
    }
  }
}
```

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

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

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

```json
{
  "mcpServers": {
    "mcp-server-deapi": {
      "serverUrl": "https://mcp.deapi.ai/mcp"
    }
  }
}
```

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

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

## Tools

- `audio_transcription`: Transcribe audio files using Whisper models.
- `text_to_audio`: Convert text to speech.
- `text_to_music`: Generate music from a description and lyrics.
- `audio_url_transcription`: Transcribe completed Twitter Spaces from a URL.
- `video_file_transcription`: Transcribe a video file.
- `video_url_transcription`: Transcribe videos from YouTube, Twitter/X, Twitch, Kick or TikTok.
- `text_to_image`: Generate images from text prompts.
- `image_to_image`: Transform an image with text guidance.
- `image_to_text`: Extract text from images (OCR).
- `image_remove_background`: Remove an image background.
- `image_upscale`: Upscale an image.
- `text_to_video`: Generate video from a text prompt.
- `image_to_video`: Animate a still image.
- `audio_to_video`: Generate video conditioned on audio.
- `video_description`: Describe a video in text.
- `video_upscale`: Upscale a video.
- `text_to_embedding`: Generate text embeddings.
- `prompt_booster`: Enhance a prompt for a deAPI inference type.
- `get_balance`: Check account balance.
- `get_available_models`: List models and their limits.
- `check_job_status`: Query or wait on an async job.

## FAQ

### What do I need to use it?

A deAPI account and API token; to self-host, Python 3.11 or newer.

### Can I check cost first?

Yes. The _price tools report the cost of each job type.

### How do I connect Claude?

Add a connector with the server URL and your deAPI token as the OAuth client secret, per the README.

### Does it support deAPI v1?

No. It targets the v2 client API only.

### How do I add deAPI MCP Server to Claude Code?

Run this command in your terminal: claude mcp add --transport http mcp-server-deapi https://mcp.deapi.ai/mcp

### What are the best alternatives to deAPI MCP Server?

The closest alternatives to deAPI MCP Server are HyperFrames by HeyGen, headroom, omniget, next-ai-draw-io and mcp-for-blender.

## Where this comes from

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

## Alternatives

- [HyperFrames by HeyGen](https://ai-powered.com/mcp/hyperframes-by-heygen): HyperFrames by HeyGen is a freemium MCP server for design and media.
- [headroom](https://ai-powered.com/mcp/headroom-3): headroom is an open-source MCP server for ai models and llm tooling.
- [omniget](https://ai-powered.com/mcp/omniget): omniget is an open-source MCP server for ai models and llm tooling.
- [next-ai-draw-io](https://ai-powered.com/mcp/next-ai-draw-io-2): next-ai-draw-io is an open-source MCP server for ai models and llm tooling.
- [mcp-for-blender](https://ai-powered.com/mcp/mcp-for-blender): mcp-for-blender is an open-source MCP server for design and media.
- [ffmpeg-skill](https://ai-powered.com/mcp/ffmpeg-skill): ffmpeg-skill is an open-source MCP server for design and media.
- [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.
- [unity-mcp](https://ai-powered.com/mcp/unity-mcp-2): unity-mcp is an open-source MCP server for ai models and llm tooling.

---
Source: https://ai-powered.com/mcp/deapi-mcp-server
