deAPI MCP Server

deAPI MCP Server

Production-ready Model Context Protocol (MCP) server for the deAPI REST API. This server exposes all deAPI AI capabilities as MCP tools, enabling LLMs to perform audio transcription, image generation, OCR, video generation, text-to-speech, and more.

deAPI v2 — this server targets the deAPI v2 client API (OpenAI-aligned noun paths under /api/v2/). Set DEAPIAPI_VERSION=v1 if you need to point at the legacy v1 endpoints.

Features

• Complete API Coverage: 39 deAPI tools exposed via MCP, covering every v2 client endpoint
• Smart Adaptive Polling: Automatically polls async jobs with optimized intervals based on job type
• OAuth 2.0 Authentication: Secure token exchange via OAuth Authorization Code flow with PKCE
• Error Recovery: Automatic retry logic with exponential backoff
• Progress Reporting: Real-time progress updates to MCP clients
• Type Safety: Full Pydantic schema validation
• Production Ready: Built with FastMCP framework for reliability

Available Tools

Audio Tools

• audio_transcription - Transcribe audio files to text using Whisper models
• audiotranscriptionprice - Calculate transcription cost
• texttoaudio - Convert text to natural speech (TTS)
• texttoaudio_price - Calculate TTS cost
• texttomusic - Generate music from text description and lyrics
• texttomusic_price - Calculate music generation cost
• audiourltranscription - Transcribe audio from URLs of completed Twitter Spaces
• audiourltranscription_price - Calculate Twitter Spaces transcription cost

Video Transcription Tools

• videofiletranscription - Transcribe video files to text
• videofiletranscription_price - Calculate video file transcription cost
• videourltranscription - Transcribe videos from URLs (YouTube, Twitter/X, Twitch, Kick)
• videourltranscription_price - Calculate video URL transcription cost

Image Tools

• texttoimage - Generate images from text prompts
• imagetoimage - Transform images with text guidance
• imagetotext - Extract text from images (OCR)
• imageremovebackground - Remove background from images
• image_upscale - Upscale images to higher resolution
• texttoimage_price - Calculate image generation cost
• imagetoimage_price - Calculate image transformation cost
• imagetotext_price - Calculate OCR cost
• imageremovebackground_price - Calculate background removal cost
• imageupscaleprice - Calculate upscaling cost

Video Tools

• texttovideo - Generate videos from text prompts
• imagetovideo - Animate static images into videos
• audiotovideo - Generate video conditioned on audio content
• video_replace - Replace a person in a video with a character from a reference image
• videoremovebackground - Remove the background from a video
• video_upscale - Upscale a video to higher resolution
• texttovideo_price - Calculate text-to-video cost
• imagetovideo_price - Calculate image-to-video cost
• audiotovideo_price - Calculate audio-to-video cost
• videoreplaceprice - Calculate video character replacement cost
• videoremovebackground_price - Calculate video background-removal cost
• videoupscaleprice - Calculate video upscaling cost

Embedding Tools

• texttoembedding - Generate text embeddings for semantic search
• texttoembedding_price - Calculate embedding cost

Prompt Tools

• prompt_booster - Enhance a prompt for any deAPI inference type using AI guides (synchronous, returns refined prompt directly)
• promptboosterprice - Calculate prompt-enhancement cost

Utility Tools

• get_balance - Check account balance
• getavailablemodels - List available AI models with specifications
• checkjobstatus - Query async job status by ID

Installation

Prerequisites

For running the MCP server:

• Python 3.10 or higher
• uv, pip, or conda for package management

Shortened. The full README is on GitHub.