MCP Server - deAPI

The MCP server is currently in beta. You may encounter occasional issues or unexpected behavior as we continue to refine the service. We actively welcome feedback and bug reports — join the conversation on Discord.

In addition to the HTTP API, deAPI exposes an MCP (Model Context Protocol) server. This allows AI assistants, IDE extensions, and MCP-aware tools to call deAPI capabilities as structured tools instead of manually constructing HTTP requests.

What is MCP?

The Model Context Protocol (MCP) is an open standard that enables AI models and agents to interact with external tools and services in a structured way. Instead of crafting raw HTTP requests, your AI assistant discovers available tools and calls them using a standardized protocol. With deAPI’s MCP server, Claude, ChatGPT, Cursor, and other MCP-compatible clients can:

Generate images, videos, and audio directly within conversations
Transcribe YouTube / X / Twitch / Kick / TikTok videos or audio files
Remove image backgrounds and upscale images and videos
Check pricing before running expensive operations
Access all deAPI capabilities through natural language

New tools and capabilities will be added as the MCP server evolves. Follow our Discord for updates and to share feature requests. The full source code for the MCP server is available on GitHub: github.com/deapi-ai/mcp-server-deapi

Server Details

Property	Value
MCP Server URL	`https://mcp.deapi.ai/mcp`
OAuth Client ID	`deapi-mcp`
OAuth Client Secret	Your deAPI API key
Transport	Streamed HTTP

Available Tools

The deAPI MCP server exposes the following tools:

Image Generation & Manipulation

Tool	Description
`text_to_image`	Generate images from text prompts using AI diffusion models (Flux, Z-Image-Turbo) — uses `/api/v2/images/generations`
`image_to_image`	Transform existing images using text prompts (style transfer, editing) — uses `/api/v2/images/edits`
`image_to_text`	Extract text from images using OCR — uses `/api/v2/images/ocr`
`image_remove_background`	Remove background from images (transparent PNG output) — uses `/api/v2/images/background-removals`
`image_upscale`	Upscale images to higher resolution — uses `/api/v2/images/upscales`
`text_to_image_price`	Calculate price for text-to-image generation
`image_to_image_price`	Calculate price for image transformation
`image_to_text_price`	Calculate price for OCR extraction
`image_remove_background_price`	Calculate price for background removal
`image_upscale_price`	Calculate price for image upscaling

Video Generation & Processing

Tool	Description
`text_to_video`	Generate videos from text prompts — uses `/api/v2/videos/generations`
`image_to_video`	Animate static images into videos — uses `/api/v2/videos/animations`
`audio_to_video`	Generate video conditioned on audio and text prompt — uses `/api/v2/videos/audio-syncs`
`video_replace`	Replace a person in a video with a character image — uses `/api/v2/videos/replacements`
`video_upscale`	Upscale videos to higher resolution — uses `/api/v2/videos/upscales`
`video_file_transcription`	Transcribe uploaded video files to text — uses `/api/v2/audio/transcriptions`
`video_url_transcription`	Transcribe videos from URLs (YouTube, X, Twitch, TikTok, Kick) — uses `/api/v2/audio/transcriptions`
`text_to_video_price`	Calculate price for text-to-video generation
`image_to_video_price`	Calculate price for image-to-video generation
`audio_to_video_price`	Calculate price for audio-to-video generation
`video_replace_price`	Calculate price for video character replacement
`video_upscale_price`	Calculate price for video upscaling
`video_file_transcription_price`	Calculate price for video file transcription
`video_url_transcription_price`	Calculate price for video URL transcription

Audio & Speech

Tool	Description
`text_to_audio`	Convert text to natural-sounding speech (TTS)
`text_to_music`	Generate music tracks from text descriptions
`audio_transcription`	Transcribe uploaded audio files to text using Whisper
`audio_url_transcription`	Transcribe audio from URLs (X/Twitter Spaces)
`text_to_audio_price`	Calculate price for text-to-speech
`text_to_music_price`	Calculate price for music generation
`audio_transcription_price`	Calculate price for audio file transcription
`audio_url_transcription_price`	Calculate price for audio URL transcription

Embeddings

Tool	Description
`text_to_embedding`	Generate text embeddings for semantic search
`text_to_embedding_price`	Calculate price for embedding generation

Utility

Tool	Description
`get_available_models`	List all available AI models with specifications
`get_balance`	Check your deAPI account balance
`check_job_status`	Check status of submitted jobs

How to Connect

Claude (claude.ai)

To use deAPI MCP tools directly in Claude conversations: Step 1. Get your API key from the deAPI Dashboard Step 2. Add the MCP connector in Claude settings:

Go to Settings → Connectors
Click Add Connector or Add MCP Server
Select New OAuth Connector
Enter the following credentials:

Field	Value
OAuth Client ID	`deapi-mcp`
OAuth Client Secret	Your deAPI API key
Server URL	`https://mcp.deapi.ai/mcp`

Step 3. Grant permissions — After adding the connector, Claude will ask you to authorize the connection. Click Allow to enable deAPI MCP tools in your conversations. Step 4. Start using deAPI MCP by asking Claude to generate images, transcribe videos, or use any other capability. Make sure to mention “deAPI MCP” in your prompt so Claude knows to use the MCP tools. Example prompts:

“Using deAPI MCP, generate an image of a futuristic city at sunset”
“With deAPI MCP, transcribe this YouTube video: [URL]”
“With deAPI MCP, transcribe this Twitch video: [URL]”
“Check my deAPI MCP balance”
“Using deAPI MCP, create a video of waves crashing on a beach”

Claude Desktop

To use deAPI MCP in the Claude Desktop app, configure it via the config file with a Bearer token. This is the recommended approach for desktop — no OAuth setup required. Config file setup: Edit your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "deapi": {
      "url": "https://mcp.deapi.ai/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Replace YOUR_API_KEY with your actual deAPI key. Save the file and restart Claude Desktop.

Cursor IDE

To integrate deAPI MCP into Cursor for AI-assisted development:

Quick setup: Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux), type “MCP Settings” and press Enter — this opens the MCP configuration file directly.

Step 1. Get your API key from the deAPI Dashboard Step 2. Open Cursor Settings:

Press Cmd/Ctrl + Shift + P
Search for “Cursor Settings” or navigate to Settings → Cursor Settings

Step 3. Add MCP Configuration:

Find the MCP or Model Context Protocol section
Add a custom MCP server configuration
Paste the following JSON (replace YOUR_API_KEY with your actual key):

{
  "mcpServers": {
    "deapi": {
      "name": "DEAPI MCP",
      "url": "https://mcp.deapi.ai/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Step 4. Restart Cursor to apply the configuration. Step 5. Invoke deAPI MCP in chat by using phrases like:

“Using deAPI MCP, generate an image of…”
“With deAPI MCP, transcribe this audio…”
“Via deAPI MCP, check my balance”

Cursor recognizes deAPI MCP tools when you mention keywords like “using deAPI MCP”, “with deAPI MCP”, or “via MCP” in your prompts.

ChatGPT

To use deAPI MCP tools in ChatGPT conversations:

MCP is available in beta to Pro, Plus, Business, Enterprise, and Education accounts. The MCP apps work on both web and desktop, but Developer mode settings are only accessible in the web version at chatgpt.com.

Step 1. Get your API key from the deAPI Dashboard Step 2. Enable Developer mode:

Go to Settings → Apps & Connectors
Scroll to Advanced settings at the bottom
Enable Developer mode
Go back — a Create App button will appear next to Advanced settings

Step 3. Create a new MCP App:

Click Create App
Fill in the following details:

Field	Value
Name	`deAPI` (or any name you prefer)
Description	`deAPI MCP` (optional)
MCP Server URL	`https://mcp.deapi.ai/mcp`
Authentication	`OAuth`
OAuth Client ID	`deapi-mcp`
OAuth Client Secret	Your deAPI API key

Step 4. Check the risk acknowledgment checkbox (“I understand and want to continue”) Step 5. Click Create Step 6. Start using deAPI MCP by asking ChatGPT to generate images, transcribe videos, or use any other capability. Example prompts:

“Using deAPI MCP, generate an image of a cyberpunk cat”
“With deAPI MCP, transcribe this YouTube video: [URL]”
“Check my deAPI MCP balance”
“With deAPI MCP, transcribe this Kick video: [URL]“

Claude Code

To use deAPI MCP in Claude Code, open a terminal in your project directory and run:

claude mcp add deapi -s user -t http https://mcp.deapi.ai/mcp --header "Authorization: Bearer YOUR_API_KEY"

Replace YOUR_API_KEY with your actual deAPI key. The server will be available in all your Claude Code sessions.

Codex

To use deAPI MCP in Codex, add the server to your configuration file. Edit ~/.codex/config.toml (user-level) or .codex/config.toml (project-level) and add:

[mcp_servers.deapi]
url = "https://mcp.deapi.ai/mcp"
bearer_token_env_var = "DEAPI_TOKEN"

Then set the environment variable with your deAPI key:

export DEAPI_TOKEN="YOUR_API_KEY"

Replace YOUR_API_KEY with your actual deAPI key.

Gemini CLI

To use deAPI MCP in Gemini CLI, open a terminal in your project directory and run:

gemini mcp add --transport http --header "Authorization: Bearer YOUR_API_KEY" deapi https://mcp.deapi.ai/mcp

Replace YOUR_API_KEY with your actual deAPI key.

Self-Hosting

You can run the MCP server on your own infrastructure. The full source code is available at github.com/deapi-ai/mcp-server-deapi under the MIT license.

Prerequisites

Python 3.10 or higher
uv, pip, or conda for package management
A deAPI API key from the Dashboard

Quick Start

git clone https://github.com/deapi-ai/mcp-server-deapi.git
cd mcp-server-deapi

# Install dependencies (uv recommended)
uv pip install -e .

# Start the server
python -m src.server_remote

The server will start on http://localhost:8000 by default. For external access:

MCP_HOST=0.0.0.0 MCP_PORT=8000 python -m src.server_remote

Docker Deployment

# Build and run
docker build -t mcp-server-deapi .
docker run -d -p 8000:8000 --name mcp-server-deapi mcp-server-deapi

# Or with Docker Compose
docker-compose up -d

Cloud Deployment Options

The server can be deployed to any platform that supports Python or Docker containers: Railway, Fly.io, Heroku, DigitalOcean App Platform, AWS ECS, GCP Cloud Run, and others. Detailed deployment instructions are available in DEPLOYMENT.md in the repository.

Connecting a Self-Hosted Server

Point your MCP client to your server URL instead of the default https://mcp.deapi.ai/mcp:

{
  "mcpServers": {
    "deapi": {
      "url": "http://your-server-ip:8000/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Supported Models

The MCP server provides access to all deAPI models. Use the get_available_models tool to retrieve the full list with current specifications and limits.

Usage Examples

Generate an Image

Ask your AI assistant:

“Using deAPI MCP, generate an image of an astronaut riding a horse on Mars, photorealistic style”

The assistant will call text_to_image with appropriate parameters and return the generated image URL.

Transcribe a YouTube Video

“With deAPI MCP, transcribe this YouTube video with timestamps: https://www.youtube.com/watch?v=7qaiNfoMRts”

The assistant calls video_url_transcription and returns the full transcript.

Convert Text to Speech

“Using deAPI MCP, convert this text to speech with a British female voice: ‘Welcome to our platform’”

The assistant calls text_to_audio with the Kokoro model and appropriate voice settings.

Remove Background from Image

“Using deAPI MCP, remove the background from this product photo”

The assistant calls image_remove_background and returns a transparent PNG.

Transcribe X/Twitter Spaces

“With deAPI MCP, transcribe this Twitter Space: https://twitter.com/i/spaces/…”

The assistant calls audio_url_transcription and returns the full transcript.

Architecture

Smart Adaptive Polling

For async jobs, the server automatically polls for results with optimized intervals based on job type:

Job Type	Initial Delay	Max Delay	Timeout
Audio	1s	5s	5 min
Image	2s	8s	5 min
Video	5s	30s	15 min

Polling uses exponential backoff (1.5× multiplier by default), so jobs receive fast initial checks while heavier workloads avoid unnecessary load.

Token Security

The MCP server does not store your API token. Authentication works at the connection level:

Remote hosted server: OAuth 2.0 Authorization Code with PKCE, or Bearer token in HTTP headers
Self-hosted server: Bearer token forwarded per-request to the deAPI API
Tokens are never persisted or logged; tools do not accept deapi_api_token as a parameter

When to Use MCP vs HTTP API

Use Case	Recommended
AI assistants & chatbots	MCP Server
IDE integrations (Cursor, VS Code)	MCP Server
Terminal AI tools (Claude Code, Codex, Gemini CLI)	MCP Server
Backend services & workers	HTTP API
Batch processing	HTTP API
Direct programmatic control	HTTP API
Agent-driven workflows	MCP Server

Use the MCP server when you want an AI agent to decide which tools to call, with which parameters, and in what order. Use the HTTP API + queue for typical backend integrations where you directly manage requests and results.

Troubleshooting

Connection Issues

Verify your API key is valid and has sufficient balance
Check the server URL is exactly https://mcp.deapi.ai/mcp
For Claude: Ensure OAuth Client ID is deapi-mcp and Secret is your API key
For Cursor / Claude Desktop: Ensure Bearer token format — the Authorization header should be Bearer YOUR_API_KEY

Tools Not Appearing

Restart your MCP client (Claude, ChatGPT, Cursor) after configuration changes
In Claude: Make sure you clicked Allow when prompted to grant permissions
In ChatGPT: Ensure Developer mode is enabled in Advanced settings
Verify JSON syntax in configuration files (Cursor, Claude Desktop)
Check that your API key has the necessary permissions

Jobs Stuck in Processing

Use check_job_status tool with the job ID to monitor progress
Large video generation or transcription jobs may take several minutes
Check status.deapi.ai for system status

Remote Connection Issues (Self-Hosted)

Test the endpoint: curl -N http://your-server:8000/mcp
Check server logs: docker logs mcp-server-deapi or journalctl -u mcp-server-deapi
Verify firewall rules allow the configured port
For SSL issues, confirm certificates are valid and paths are correct in your proxy config

​What is MCP?

​Server Details

​Available Tools

​Image Generation & Manipulation

​Video Generation & Processing

​Audio & Speech

​Embeddings

​Utility

​How to Connect

​Claude (claude.ai)

​Claude Desktop

​Cursor IDE

​ChatGPT

​Claude Code

​Codex

​Gemini CLI

​Self-Hosting

​Prerequisites

​Quick Start

​Docker Deployment

​Cloud Deployment Options

​Connecting a Self-Hosted Server

​Supported Models

​Usage Examples

​Generate an Image

​Transcribe a YouTube Video

​Convert Text to Speech

​Remove Background from Image

​Transcribe X/Twitter Spaces

​Architecture

​Smart Adaptive Polling

​Token Security

​When to Use MCP vs HTTP API

​Troubleshooting

​Connection Issues

​Tools Not Appearing

​Jobs Stuck in Processing

​Remote Connection Issues (Self-Hosted)

What is MCP?

Server Details

Available Tools

Image Generation & Manipulation

Video Generation & Processing

Audio & Speech

Embeddings

Utility

How to Connect

Claude (claude.ai)

Claude Desktop

Cursor IDE

ChatGPT

Claude Code

Codex

Gemini CLI

Self-Hosting

Prerequisites

Quick Start

Docker Deployment

Cloud Deployment Options

Connecting a Self-Hosted Server

Supported Models

Usage Examples

Generate an Image

Transcribe a YouTube Video

Convert Text to Speech

Remove Background from Image

Transcribe X/Twitter Spaces

Architecture

Smart Adaptive Polling

Token Security

When to Use MCP vs HTTP API

Troubleshooting

Connection Issues

Tools Not Appearing

Jobs Stuck in Processing

Remote Connection Issues (Self-Hosted)