deAPI MCP Server
Connects Claude to the deAPI platform's 35+ AI tools through a production MCP server. You get audio transcription via Whisper, TTS, music generation from text, OCR, image generation and transformation with Flux models, video generation and editing, plus text embeddings. Handles OAuth 2.0 authentication with PKCE, automatically polls async jobs with adaptive intervals, and includes retry logic with exponential backoff. Each tool has a matching price calculation endpoint so you can estimate costs before running operations. Built on FastMCP with full Pydantic validation. Reach for this when you need Claude to orchestrate multi-modal AI tasks like transcribing a video, generating images from prompts, or converting text to speech without writing API client code yourself.
- GitHub stars
- 1
- tools
- 39
- transport
- HTTP
- last updated
- Nov 6, 2026
Tools
39 toolsPublic tool metadata for what this MCP can expose to an agent.
audio_transcriptionTranscribe audio files to text using Whisper models
Transcribe audio files to text using Whisper models
No parameter schema in public metadata yet.
audio_transcription_priceCalculate transcription cost
Calculate transcription cost
No parameter schema in public metadata yet.
text_to_audioConvert text to natural speech (TTS)
Convert text to natural speech (TTS)
No parameter schema in public metadata yet.
text_to_audio_priceCalculate TTS cost
Calculate TTS cost
No parameter schema in public metadata yet.
text_to_musicGenerate music from text description and lyrics
Generate music from text description and lyrics
No parameter schema in public metadata yet.
text_to_music_priceCalculate music generation cost
Calculate music generation cost
No parameter schema in public metadata yet.
audio_url_transcriptionTranscribe audio from URLs of completed Twitter Spaces
Transcribe audio from URLs of completed Twitter Spaces
No parameter schema in public metadata yet.
audio_url_transcription_priceCalculate Twitter Spaces transcription cost
Calculate Twitter Spaces transcription cost
No parameter schema in public metadata yet.
video_file_transcriptionTranscribe video files to text
Transcribe video files to text
No parameter schema in public metadata yet.
video_file_transcription_priceCalculate video file transcription cost
Calculate video file transcription cost
No parameter schema in public metadata yet.
video_url_transcriptionTranscribe videos from URLs (YouTube, Twitter/X, Twitch, Kick, TikTok)
Transcribe videos from URLs (YouTube, Twitter/X, Twitch, Kick, TikTok)
No parameter schema in public metadata yet.
video_url_transcription_priceCalculate video URL transcription cost
Calculate video URL transcription cost
No parameter schema in public metadata yet.
text_to_imageGenerate images from text prompts
Generate images from text prompts
No parameter schema in public metadata yet.
image_to_imageTransform images with text guidance
Transform images with text guidance
No parameter schema in public metadata yet.
image_to_textExtract text from images (OCR)
Extract text from images (OCR)
No parameter schema in public metadata yet.
image_remove_backgroundRemove background from images
Remove background from images
No parameter schema in public metadata yet.
image_upscaleUpscale images to higher resolution
Upscale images to higher resolution
No parameter schema in public metadata yet.
text_to_image_priceCalculate image generation cost
Calculate image generation cost
No parameter schema in public metadata yet.
image_to_image_priceCalculate image transformation cost
Calculate image transformation cost
No parameter schema in public metadata yet.
image_to_text_priceCalculate OCR cost
Calculate OCR cost
No parameter schema in public metadata yet.
image_remove_background_priceCalculate background removal cost
Calculate background removal cost
No parameter schema in public metadata yet.
image_upscale_priceCalculate upscaling cost
Calculate upscaling cost
No parameter schema in public metadata yet.
text_to_videoGenerate videos from text prompts
Generate videos from text prompts
No parameter schema in public metadata yet.
image_to_videoAnimate static images into videos
Animate static images into videos
No parameter schema in public metadata yet.
audio_to_videoGenerate video conditioned on audio content
Generate video conditioned on audio content
No parameter schema in public metadata yet.
video_descriptionDescribe a video in text (from an uploaded file or a video URL)
Describe a video in text (from an uploaded file or a video URL)
No parameter schema in public metadata yet.
video_upscaleUpscale a video to higher resolution
Upscale a video to higher resolution
No parameter schema in public metadata yet.
text_to_video_priceCalculate text-to-video cost
Calculate text-to-video cost
No parameter schema in public metadata yet.
image_to_video_priceCalculate image-to-video cost
Calculate image-to-video cost
No parameter schema in public metadata yet.
audio_to_video_priceCalculate audio-to-video cost
Calculate audio-to-video cost
No parameter schema in public metadata yet.
video_description_priceCalculate video description cost
Calculate video description cost
No parameter schema in public metadata yet.
video_upscale_priceCalculate video upscaling cost
Calculate video upscaling cost
No parameter schema in public metadata yet.
text_to_embeddingGenerate text embeddings for semantic search
Generate text embeddings for semantic search
No parameter schema in public metadata yet.
text_to_embedding_priceCalculate embedding cost
Calculate embedding cost
No parameter schema in public metadata yet.
prompt_boosterEnhance a prompt for any deAPI inference type using AI guides (synchronous, returns refined prompt directly)
Enhance a prompt for any deAPI inference type using AI guides (synchronous, returns refined prompt directly)
No parameter schema in public metadata yet.
prompt_booster_priceCalculate prompt-enhancement cost
Calculate prompt-enhancement cost
No parameter schema in public metadata yet.
get_balanceCheck account balance
Check account balance
No parameter schema in public metadata yet.
get_available_modelsList available AI models with specifications
List available AI models with specifications
No parameter schema in public metadata yet.
check_job_statusQuery async job status by ID; with wait_seconds it waits for the job and returns the finished result in the original tool's shape
Query async job status by ID; with wait_seconds it waits for the job and returns the finished result in the original tool's shape
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
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/*). API v1 is not supported: the tools send v2 payloads only.
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
Details
- Repository
- github.com/deapi-ai/mcp-server-deapi
- Category
- Media & Entertainment
- Transport
- HTTP
- Registry
- MCP registry, active
Related Media & Entertainment MCP servers
View all
Kie Mcpelibarnett/kie-mcpMCP for kie.ai: 45+ image, 70+ video, 20+ audio models with model intelligence1stars
Botversemkturner74/botverse-mcpTranscode/conform/splice video, convert docs, transcribe audio for AI agents. Free $1 trial.1stars
Multimodalrsmdt/multimodal-mcpMulti-provider media generation — images, video, audio, and transcription via a unified interface1stars
mediasensejoaoestella/mediasenseLet Claude listen to audio and watch video: transcribe, summarize and edit recordings and links.1stars
Rendobarrendobar/mcpTransform video, audio and images, and generate media from prompts. FFmpeg, captions, models.0stars