Skip to content
Agentmart
Submit a tool

deAPI MCP Server

35 AI tools for image/video generation, TTS, transcription, OCR & embeddings via deAPI

Connector by deapi-ai · GitHub account verified by the MCP Registry

IndexedMITRemote (HTTP)★ 1
Write a review

Install

Works with Claude Code, VS Code, Cursor, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install connector/deapi-ai-mcp-server-deapi

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Remote endpoint

  • https://mcp.deapi.ai/mcp Remote (HTTP)

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

35 AI tools for image/video generation, TTS, transcription, OCR & embeddings via deAPI

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
13 read · 14 write · 4 delete · 10 not yet classified
Secrets
None asked for
Install scripts
Nothing to install (hosted)
Runs as
Hosted (remote endpoint)

Tools by what they do 41

Read from the source code; the running server may list different tools.

Read 13 · Look things up without changing anything.

  • audio_to_video_price
  • audio_transcription_price
  • audio_url_transcription_price
  • check_job_status
  • get_available_models
  • get_balance
  • image_to_image_price
  • image_to_video_price
  • image_upscale_price
  • prompt_booster_price
  • video_file_transcription_price
  • video_upscale_price
Show 1 more tools
  • video_url_transcription_price

Write 14 · Create, change, send or run things.

  • image_to_text
  • image_to_text_price
  • text_to_audio
  • text_to_audio_price
  • text_to_embedding
  • text_to_embedding_price
  • text_to_image
  • text_to_image_price
  • text_to_music
  • text_to_music_price
  • text_to_video
  • text_to_video_price
Show 2 more tools
  • video_replace
  • video_replace_price

Delete 4 · Delete, drop, revoke or wipe things.

  • image_remove_background
  • image_remove_background_price
  • video_remove_background
  • video_remove_background_price

Not yet classified 10 · We could not tell from the name and description.

  • audio_to_video
  • audio_transcription
  • audio_url_transcription
  • image_to_image
  • image_to_video
  • image_upscale
  • prompt_booster
  • video_file_transcription
  • video_upscale
  • video_url_transcription

Network hosts it talks to 1

  • mcp.deapi.ai · found in remote endpoint, install command

Tools (41)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • audio_to_video

    Generate video from audio and text prompt. Creates videos conditioned on audio content. The audio drives the video generation, allowing synchronized audio-visual output. Optionally accepts anchor frame images. IMPORTANT: Check model specifications using get_available_models() before calling. Pay attention to features.supports_guidance, features.supports_steps, and model limits. Returns: dict: Contains 'success', 'result_url' with video URL, 'job_id'

  • audio_to_video_price

    Calculate price for audio-to-video generation. Returns: dict: Contains 'success' and 'price' information

  • audio_transcription

    Transcribe audio file to text using Whisper models. Converts audio files to text transcription with optional timestamps. Automatically polls until transcription is complete. Returns: dict: Contains 'success', 'result' with transcription text, 'job_id'

  • audio_transcription_price

    Calculate price for audio transcription. Provide either audio file or duration_seconds for price calculation. Returns: dict: Contains 'success' and 'price' information

  • audio_url_transcription

    Transcribe audio from Twitter Spaces URL to text using Whisper models. Extracts and transcribes audio from Twitter Spaces URLs. NOTE: This endpoint only works with Twitter Spaces URLs. For video content, use video_url_transcription instead. Returns: dict: Contains 'success', 'result' with transcription text, 'job_id'

  • audio_url_transcription_price

    Calculate price for Twitter Spaces audio transcription. Provide either audio_url or duration_seconds for price calculation. Returns: dict: Contains 'success' and 'price' information

  • check_job_status

    Check status of a submitted job. Query current status of any job by ID. Useful for long-running jobs. Args: job_id: Job request ID (UUID) to check status for Returns: dict: Contains 'success', job status, progress, and result if available

  • get_available_models

    Get list of available AI models with detailed specifications. Retrieves all available models for different inference types (txt2img, txt2video, img2img, img2video, audiofile2txt, img2txt, etc.) along with their capabilities, limits, defaults, and features. IMPORTANT - How to use model specifications: Each model's 'info' field contains critical information you MUST check before using: 1. **inference_types**: List of supported operations (e.g., ["txt2img", "img2img"]) 2. **info.limits**: Min/max constraints for ALL parameters. Examples: - max_guidance/min_guidance: Valid range for guidan…

  • get_balance

    Get current account balance. Check your deAPI account balance and remaining credits. Returns: dict: Contains 'success' and balance information with amount and currency

  • image_remove_background

    Remove background from an image. Takes an image and removes its background, returning a transparent PNG. Accepts images as: - URLs (recommended for chaining with text_to_image - avoids base64 bloat) - Data URIs (from Claude Desktop attachments) - Base64 strings Returns: dict: Contains 'success', 'result_url' with processed image URL, 'job_id'

  • image_remove_background_price

    Calculate price for image background removal. Provide width and height for price calculation. Returns: dict: Contains 'success' and 'price' information

  • image_to_image

    Transform an existing image using a text prompt. Modifies images based on text descriptions. Useful for style transfer and editing. Accepts images as URLs (preferred), data URIs (data:image/...;base64,...), or base64 strings. When a URL is available (e.g., from a previous text_to_image result), always prefer passing the URL directly. Returns: dict: Contains 'success', 'result_url', 'job_id', and metadata

  • image_to_image_price

    Calculate price for image-to-image transformation. Returns: dict: Contains 'success' and 'price' information

  • image_to_text

    Extract text from image using OCR (Optical Character Recognition). Reads text from images like documents, screenshots, signs, etc. Returns: dict: Contains 'success', 'result' with extracted text, 'job_id'

  • image_to_text_price

    Calculate price for OCR text extraction. Provide width and height for price calculation. Returns: dict: Contains 'success' and 'price' information

Show 26 more tools
  • image_to_video

    Generate video from static image(s). Animates images into videos using AI models. Accepts images as: - URLs (recommended for chaining with text_to_image - avoids base64 bloat) - Data URIs (from Claude Desktop attachments) - Base64 strings IMPORTANT: Check model specifications using get_available_models() before calling. Pay attention to features.supports_guidance and limits for width/height/frames/fps. Returns: dict: Contains 'success', 'result_url' with video URL, 'job_id'

  • image_to_video_price

    Calculate price for image-to-video generation. Returns: dict: Contains 'success' and 'price' information

  • image_upscale

    Upscale an image to higher resolution. Takes an image and upscales it using AI models for enhanced quality. Accepts images as: - URLs (recommended for chaining with text_to_image - avoids base64 bloat) - Data URIs (from Claude Desktop attachments) - Base64 strings Returns: dict: Contains 'success', 'result_url' with upscaled image URL, 'job_id'

  • image_upscale_price

    Calculate price for image upscaling. Provide width and height for price calculation. Returns: dict: Contains 'success' and 'price' information

  • prompt_booster

    Enhance a prompt using AI guides tailored to a specific deAPI model + inference type. Synchronous — returns the enhanced prompt(s) directly. Charged per call; use `prompt_booster_price` first if you want a quote. Returns: dict: Contains 'success', 'prompt' (enhanced), and 'negative_prompt' (enhanced, if applicable).

  • prompt_booster_price

    Calculate the price for a prompt-booster call. Returns: dict: Contains 'success' and 'price'.

  • text_to_audio

    Convert text to speech audio using TTS models. Generates natural-sounding speech from text with customizable voice and parameters. Returns: dict: Contains 'success', 'result_url' with audio URL, 'job_id'

  • text_to_audio_price

    Calculate price for text-to-audio generation. Returns: dict: Contains 'success' and 'price' information

  • text_to_embedding

    Generate text embeddings using AI models. Converts text into vector embeddings for semantic search, similarity comparison, and other NLP tasks. Accepts a single string or a list of strings. Returns: dict: Contains 'success', 'result' with embedding vectors, 'job_id'

  • text_to_embedding_price

    Calculate price for text embedding generation. Returns: dict: Contains 'success' and 'price' information

  • text_to_image

    Generate image from text prompt using AI diffusion models. Creates images from text descriptions. Returns the generated image URL. Returns: dict: Contains 'success', 'result_url', 'job_id', and metadata

  • text_to_image_price

    Calculate price for text-to-image generation. Returns: dict: Contains 'success' and 'price' information

  • text_to_music

    Generate music from text description and lyrics. Creates music tracks from text prompts with customizable parameters including tempo, key, time signature, and optional style reference audio. IMPORTANT: Check model specifications using get_available_models() before calling. Pay attention to model limits for duration, inference_steps, guidance_scale, and bpm. Returns: dict: Contains 'success', 'result_url' with audio URL, 'job_id'

  • text_to_music_price

    Calculate price for text-to-music generation. Returns: dict: Contains 'success' and 'price' information

  • text_to_video

    Generate video from text prompt. Creates videos from text descriptions. Returns the generated video URL. IMPORTANT: Before calling this tool, use get_available_models() to check the model's specifications. Pay special attention to: - features.supports_guidance: If "0", set guidance_scale to 0 - limits.max_steps/min_steps: Valid range for steps parameter - limits.max_fps/min_fps: Valid range for fps parameter - defaults: Recommended values for the model Returns: dict: Contains 'success', 'result_url' with video URL, 'job_id'

  • text_to_video_price

    Calculate price for text-to-video generation. Returns: dict: Contains 'success' and 'price' information

  • video_file_transcription

    Transcribe video file to text using Whisper models. Extracts audio from video and converts it to text transcription with optional timestamps. Accepts video files as URLs (preferred), data URIs, or base64 strings. Automatically polls until transcription is complete. Returns: dict: Contains 'success', 'result' with transcription text, 'job_id'

  • video_file_transcription_price

    Calculate price for video file transcription. Provide either video file or duration_seconds for price calculation. Returns: dict: Contains 'success' and 'price' information

  • video_remove_background

    Remove background from a video. Takes a video and removes its background. Accepts videos as: - URLs (recommended to avoid base64 bloat) - Data URIs (from attachments) - Base64 strings Returns: dict: Contains 'success', 'result_url' with processed video URL, 'job_id'

  • video_remove_background_price

    Calculate price for video background removal. Returns: dict: Contains 'success' and 'price' information

  • video_replace

    Replace a person in a video with the character from a reference image. Performs AI-powered character replacement — takes an input video and a reference image, and replaces the person in the video with the character from the image. IMPORTANT: Check model specifications using get_available_models() before calling. Pay attention to limits for width/height, max_video_duration_seconds, and steps. Returns: dict: Contains 'success', 'result_url' with processed video URL, 'job_id'

  • video_replace_price

    Calculate price for video character replacement. Estimates the cost based on model, video duration, and dimensions. Returns: dict: Contains 'success' and 'price' information

  • video_upscale

    Upscale a video to higher resolution. Takes a video and upscales it using AI models for enhanced quality. Accepts videos as: - URLs (recommended to avoid base64 bloat) - Data URIs (from attachments) - Base64 strings Returns: dict: Contains 'success', 'result_url' with upscaled video URL, 'job_id'

  • video_upscale_price

    Calculate price for video upscaling. Pass width+height (and optionally scale/duration) to estimate price without uploading a video file. Returns: dict: Contains 'success' and 'price' information

  • video_url_transcription

    Transcribe video from URL to text using Whisper models. Extracts audio from video URL and converts it to text transcription with optional timestamps. Supports YouTube, Twitter/X, Twitch, and Kick videos. Automatically polls until transcription is complete. Returns: dict: Contains 'success', 'result' with transcription text, 'job_id'

  • video_url_transcription_price

    Calculate price for video URL transcription. Returns: dict: Contains 'success' and 'price' information

Signals

Stars
1
Forks
1
Open issues
0
Last commit
May 4, 2026 (5 months ago)
Last release
Mar 31, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.deapi-ai/mcp-server-deapi
Version
0.3.0
Auth
Auth not stated
License
MIT
Repository
github.com/deapi-ai/mcp-server-deapi
First seen
Oct 24, 2026
Last checked
Oct 25, 2026
Source
Official MCP Registrygithub-graphql

More from deapi-ai

Cite this page

deAPI MCP Server. Agent Mart. https://agentmart.dev/connectors/deapi-ai-mcp-server-deapi (last updated 2026-10-25)