UnificAlly MCP Server (com.unifically/mcp)

The UnificAlly MCP server is an official hosted remote Model Context Protocol (MCP) server that provides “one API for 100+ AI video, image, music, and speech models.” It is accessed by pointing an MCP client to a single endpoint and adding an API key. The server exposes 14 tools.

🛠️ Key Features

Official MCP server for UnificAlly
One API for 100+ AI video, image, music, and speech models
Hosted remote server (no installation or runtime required)
14 tools
Supports generation via models including Veo 3.1, Kling, SeeDance, Grok Imagine, Nano Banana, Suno, ElevenLabs, and more

🚀 Use Cases

Generate AI video (e.g., Veo 3.1, Kling, text-to-video)
Generate AI images (e.g., text-to-image)
Generate AI music (e.g., music-generation via Suno)
Generate speech (text-to-speech via ElevenLabs)

⚡ Developer Benefits

Works with “Claude, Cursor, or any MCP client”
Single endpoint: https://mcp.unifically.com/mcp
API key required; free balance available for every account

⚠️ Limitations

Hosted remote server: no local installation or self-hosting described in the source data

UnificAlly MCP Server

Official MCP (Model Context Protocol) server for UnificAlly: one API for 100+ AI video, image, music, and speech models. Ask Claude, Cursor, or any MCP client to generate with Veo 3.1, Kling, SeeDance, Grok Imagine, Nano Banana, Suno, ElevenLabs, and more.

This is a hosted remote server. Nothing to install or run. Point your client at the endpoint and add your API key.

code

https://mcp.unifically.com/mcp

Get an API key at unifically.com. Every account starts with a free balance.

Config

Add this server to your MCP-compatible client using the configuration below.

json

{
  "mcpServers": {
    "unifically": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.unifically.com/mcp",
        "--header",
        "Authorization: Bearer YOUR_API_KEY"
      ]
    }
  }
}

Remote clients that support Streamable HTTP can skip the bridge:

json

{
  "mcpServers": {
    "unifically": {
      "type": "streamableHttp",
      "url": "https://mcp.unifically.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Tools

`generate_video`

Text or image to video (Veo 3.1, Kling, SeeDance, Grok Imagine, Wan, and more).

`generate_image`

Text or image to image (Nano Banana, Seedream, GPT Image, Qwen, FLUX, and more).

`generate_music`

Music generation with Suno.

`generate_audio`

Speech, dialogue, and sound effects with ElevenLabs.

`edit_video`

Edit an existing video.

`extend_video`

Extend an existing video.

`upscale_media`

Upscale images and video (Topaz, Grok, Veo).

`upload_file`

Upload a local file and get a CDN URL to use as a reference input.

`get_task`

Check the status of a generation task.

`list_tasks`

List recent generation tasks.

`list_models`

Browse the model catalog.

`list_resources`

Browse voices and other resources.

`dry_run_cost`

Price any generation before running it. Never charges.

`check_balance`

Show the current account balance.

Quick start

Claude Code

bash

claude mcp add --transport http unifically https://mcp.unifically.com/mcp --header "Authorization: Bearer sk-..."

Claude (web and desktop connectors)

Add a custom connector. Pasted connector URLs carry no headers, so put the key in the URL:

code

https://mcp.unifically.com/mcp?api_key=sk-...

Cursor / Claude Desktop

json

{
  "mcpServers": {
    "unifically": {
      "url": "https://mcp.unifically.com/mcp",
      "headers": { "Authorization": "Bearer sk-..." }
    }
  }
}

VS Code (Copilot)

json

{
  "servers": {
    "unifically": {
      "type": "http",
      "url": "https://mcp.unifically.com/mcp",
      "headers": { "Authorization": "Bearer sk-..." }
    }
  }
}

Example prompts

Generate a 5 second video of a paper boat floating down a rainy street with Kling
Make a product shot of a ceramic mug on linen with Seedream, then upscale it
How much would 10 seconds of Veo 3.1 Fast cost?
Turn this blog post into a 30 second narrated clip

License

MIT. The hosted server and the UnificAlly API are commercial services. This repository is the public integration surface (docs, registry manifest, and examples).

prompt	string	required	Text prompt describing the desired video.
model	string	optional	Model, as a short alias or full id. Aliases: 'veo' (default), 'veo-quality', 'veo-lite', 'kling', 'kling-omni', 'hailuo', 'seedance', 'grok-video', 'grok-1.5'. Full ids like 'google/veo-3.1-fast' also work. Call list_models for the catalog, and read a model's docs page for its exact parameters.
duration	integer	optional	Video length in seconds. Omit for the model's default. Allowed values are per-model.
aspect_ratio	string	optional	Output aspect ratio, e.g. '16:9'. Per-model: some accept different sets, some have none.
image_url	string	optional	Optional starting frame for image-to-video. This tool maps it to whatever field the chosen model wants, so pass it here rather than the model's own field name. Must be a public https URL — never a local path, never inline base64. For a local file, upload it first with a direct PUT to files.unifically.com/upload and pass the returned file_url.
end_image_url	string	optional	Optional final frame (start-frame + end-frame interpolation). Only some models support one. Must be a public https URL — never a local path, never inline base64. For a local file, upload it first with a direct PUT to files.unifically.com/upload and pass the returned file_url.
reference_image_urls	array	optional	Optional reference images for style/subject — each must be a public https URL (upload local files first — never a path or base64). Support, the max count, and whether they combine with a start frame are per-model.
seed	integer	optional	Optional seed for reproducible output. Same seed + same input gives the same result on supported models.
wait	boolean	optional	Default true: wait for the job and return the finished result. Set false to get the task_id back immediately and poll with get_task — use for long jobs (high-quality video, full songs) or when the connection might time out.
callback_url	string	optional	Optional webhook URL. When set, the tool returns immediately with the task_id and Unifically POSTs the result to this URL when the task finishes. Webhook body: { task_id, status: 'completed'\|'failed', data: { video_url \| image_url \| audio_url \| ... }, error_message? } — note the media arrives under 'data', not 'output'. Use for long jobs instead of waiting.
confirm_cost	boolean	optional	Only relevant if the operator enabled a spend guard. When a call exceeds the configured confirm threshold it returns a quote; retry with confirm_cost: true to proceed. Safe to ignore otherwise.
provider_options	object	optional	Escape hatch for model-specific fields not exposed as named parameters (e.g. Kling multi_shots, Flux steps). Merged into the API 'input' payload. Rejected: fields the tool already manages (prompt, media URLs, task_id, ...) and reserved routing/billing/auth keys (model, callback_url, dry_run, api_key, authorization) — switch models with the 'model' parameter, not here. See https://docs.unifically.com for per-model fields.

prompt	string	required	Text prompt describing the image (or the edit to apply to image_urls).
model	string	optional	Model, as a short alias or full id. Aliases: 'nano-banana-pro' (default), 'nano-banana', 'nano-banana-2', 'nano-banana-2-lite', 'flux', 'gpt-image', 'qwen', 'kling-image', 'grok-image', 'seedream'. Full ids also work. See list_models. (Upscaling lives in upscale_media, not here.)
resolution	string	optional	Output resolution; omit for the model's default. Per-model: some take sizes like '2k', some megapixels, some have no resolution field.
aspect_ratio	string	optional	Output aspect ratio, e.g. '1:1'. Per-model: some accept different sets, some have none.
image_urls	array	optional	Reference/source images for editing and multi-reference generation — each must be a public https URL. Upload a local file first and pass the returned file_url; never a local path, and never inline base64. The max count is per-model.
image_url	string	optional	Convenience: a single reference/source image (same as image_urls with one entry).
negative_prompt	string	optional	Optional description of what to avoid in the output (supported by Qwen, Wan and some others).
seed	integer	optional	Optional seed for reproducible output. Same seed + same input gives the same result on supported models.
wait	boolean	optional	Default true: wait for the job and return the finished result. Set false to get the task_id back immediately and poll with get_task — use for long jobs (high-quality video, full songs) or when the connection might time out.
callback_url	string	optional	Optional webhook URL. When set, the tool returns immediately with the task_id and Unifically POSTs the result to this URL when the task finishes. Webhook body: { task_id, status: 'completed'\|'failed', data: { video_url \| image_url \| audio_url \| ... }, error_message? } — note the media arrives under 'data', not 'output'. Use for long jobs instead of waiting.
confirm_cost	boolean	optional	Only relevant if the operator enabled a spend guard. When a call exceeds the configured confirm threshold it returns a quote; retry with confirm_cost: true to proceed. Safe to ignore otherwise.
provider_options	object	optional	Escape hatch for model-specific fields not exposed as named parameters (e.g. Kling multi_shots, Flux steps). Merged into the API 'input' payload. Rejected: fields the tool already manages (prompt, media URLs, task_id, ...) and reserved routing/billing/auth keys (model, callback_url, dry_run, api_key, authorization) — switch models with the 'model' parameter, not here. See https://docs.unifically.com for per-model fields.

prompt	string	optional	The content to synthesize: spoken text for text-to-speech/dialogue, or the sound description for sound effects. Not used for transcription (pass audio_url instead).
model	string	optional	Model, as a short alias or full id. Aliases: 'tts' (default, text-to-speech), 'sfx' (sound effect), 'dialogue', 'stt' (transcribe), 'voice-changer' (transform a voice, needs audio_url), 'voice-isolation' (clean/isolate audio, needs audio_url). Full ids also work. For music use generate_music.
voice_id	string	optional	Voice id for text-to-speech. Discover available voices with the list_resources tool. Falls back to a default voice if omitted.
dialogue	array	optional	Model 'dialogue' only: the conversation as an array of turns, each { text, voice_id } (voice ids from list_resources). Replaces prompt for dialogue.
duration	number	optional	Duration in seconds (max 36000 = 10h, a billing ceiling this server imposes — not a model limit). Sound effects: omit for automatic. Transcription: the job is PRICED by this declared length (defaults to 300s = 5 min) — pass the audio's real length or short clips are overcharged.
audio_url	string	optional	Source audio (public https URL) for audio-input models: transcription ('stt'), voice change ('voice-changer'), and cleanup ('voice-isolation'). For local files, upload_file first.
language_code	string	optional	Transcription: optional ISO 639 language code (e.g. 'eng', 'spa'). Auto-detected when omitted.
diarize	boolean	optional	Transcription: label who is speaking (speaker diarization). Default false.
wait	boolean	optional	Default true: wait for the job and return the finished result. Set false to get the task_id back immediately and poll with get_task — use for long jobs (high-quality video, full songs) or when the connection might time out.
callback_url	string	optional	Optional webhook URL. When set, the tool returns immediately with the task_id and Unifically POSTs the result to this URL when the task finishes. Webhook body: { task_id, status: 'completed'\|'failed', data: { video_url \| image_url \| audio_url \| ... }, error_message? } — note the media arrives under 'data', not 'output'. Use for long jobs instead of waiting.
confirm_cost	boolean	optional	Only relevant if the operator enabled a spend guard. When a call exceeds the configured confirm threshold it returns a quote; retry with confirm_cost: true to proceed. Safe to ignore otherwise.
provider_options	object	optional	Escape hatch for model-specific fields not exposed as named parameters (e.g. Kling multi_shots, Flux steps). Merged into the API 'input' payload. Rejected: fields the tool already manages (prompt, media URLs, task_id, ...) and reserved routing/billing/auth keys (model, callback_url, dry_run, api_key, authorization) — switch models with the 'model' parameter, not here. See https://docs.unifically.com for per-model fields.

prompt	string	optional	For mode 'music' (default): the song description (simple) or full lyrics (custom:true). For 'cover'/'extend'/'add-vocals'/'add-instrumental': optional style/lyrics guidance. For 'sound': describe the sound effect (required). For 'lyrics': the lyric idea. Not used by stems/stems-all/wav.
mode	string	optional	Suno operation. 'music' (default) makes a new song. 'cover' re-sings a track; 'extend' lengthens it (needs continue_at); 'add-vocals'/'add-instrumental' layer onto it; 'stems'/'stems-all' split a track (need clip_id); 'lyrics' writes lyrics; 'sound' makes a sound effect from a prompt; 'wav' exports a clip as WAV (needs clip_id). cover/extend/add-vocals/add-instrumental need audio_url.
audio_url	string	optional	Source track (public https URL) for cover/extend/add-vocals/add-instrumental. For local files, upload_file first.
clip_id	string	optional	Clip id of a completed Suno music task — required by 'stems'/'stems-all' (split into stems) and 'wav' (export as WAV).
continue_at	number	optional	For extend: the time in seconds of the source track to continue from (required for 'extend').
custom	boolean	optional	music/cover/extend only. false (default): prompt is a description. true: prompt is the full lyrics; style goes in tags.
tags	string	optional	Music style tags, e.g. 'pop, electronic, upbeat'.
title	string	optional	Song title.
negative_tags	string	optional	Styles to avoid, e.g. 'metal, jazz'.
instrumental	boolean	optional	true for instrumental-only (no vocals).
mv	string	optional	Suno model version for songs — default 'chirp-bluejay'; others 'chirp-v3-5', 'chirp-v4', 'chirp-auk', 'chirp-crow', 'chirp-fenix'. ('sound' defaults to 'chirp-fenix' and 'lyrics' to 'default' — both still honor an explicit mv if you pass one.)
wait	boolean	optional	Default true: wait for the job and return the finished result. Set false to get the task_id back immediately and poll with get_task — use for long jobs (high-quality video, full songs) or when the connection might time out.
callback_url	string	optional	Optional webhook URL. When set, the tool returns immediately with the task_id and Unifically POSTs the result to this URL when the task finishes. Webhook body: { task_id, status: 'completed'\|'failed', data: { video_url \| image_url \| audio_url \| ... }, error_message? } — note the media arrives under 'data', not 'output'. Use for long jobs instead of waiting.
confirm_cost	boolean	optional	Only relevant if the operator enabled a spend guard. When a call exceeds the configured confirm threshold it returns a quote; retry with confirm_cost: true to proceed. Safe to ignore otherwise.
provider_options	object	optional	Escape hatch for model-specific fields not exposed as named parameters (e.g. Kling multi_shots, Flux steps). Merged into the API 'input' payload. Rejected: fields the tool already manages (prompt, media URLs, task_id, ...) and reserved routing/billing/auth keys (model, callback_url, dry_run, api_key, authorization) — switch models with the 'model' parameter, not here. See https://docs.unifically.com for per-model fields.

video_url	string	required	The source video to edit (or the reference/control video for motion transfer). Must be a public https URL — never a local path, never inline base64. For a local file, upload it first with a direct PUT to files.unifically.com/upload and pass the returned file_url.
prompt	string	required	What to change — the edit instruction (e.g. 'make it snow', 'turn day into night', 'apply this motion to the subject').
model	string	optional	Edit model, alias or full id. Aliases: 'video-edit' (default, Gemini Omni), 'kling-edit', 'wan-edit', 'motion-control' (Kling motion transfer). See list_models (category video, the *-edit / motion-control ids).
image_urls	array	optional	Optional reference/subject images (each a public https URL) — used by motion-control (the subject to animate) and omni edit models. The max count is per-model.
aspect_ratio	string	optional	Optional output aspect ratio, if the model supports it.
seed	integer	optional	Optional seed for reproducible output. Same seed + same input gives the same result on supported models.
wait	boolean	optional	Default true: wait for the job and return the finished result. Set false to get the task_id back immediately and poll with get_task — use for long jobs (high-quality video, full songs) or when the connection might time out.
callback_url	string	optional	Optional webhook URL. When set, the tool returns immediately with the task_id and Unifically POSTs the result to this URL when the task finishes. Webhook body: { task_id, status: 'completed'\|'failed', data: { video_url \| image_url \| audio_url \| ... }, error_message? } — note the media arrives under 'data', not 'output'. Use for long jobs instead of waiting.
confirm_cost	boolean	optional	Only relevant if the operator enabled a spend guard. When a call exceeds the configured confirm threshold it returns a quote; retry with confirm_cost: true to proceed. Safe to ignore otherwise.
provider_options	object	optional	Escape hatch for model-specific fields not exposed as named parameters (e.g. Kling multi_shots, Flux steps). Merged into the API 'input' payload. Rejected: fields the tool already manages (prompt, media URLs, task_id, ...) and reserved routing/billing/auth keys (model, callback_url, dry_run, api_key, authorization) — switch models with the 'model' parameter, not here. See https://docs.unifically.com for per-model fields.

task_id	string	required	task_id of the completed generation to extend. Extenders are model-internal: Veo extend works on Veo generations, Grok extend on Grok Imagine generations.
model	string	optional	Which extender, as an alias or full id: 'veo' / 'google/veo-3.1-extend' (default, adds 8s) or 'grok' / 'xai/grok-imagine-video-extend'. Each only continues its OWN model's generations: Grok extend needs a task_id from xai/grok-imagine-video — NOT from xai/grok-imagine-1.5-video, which cannot be extended. See list_models.
prompt	string	optional	What should happen in the extended segment. Required for Veo, and for Grok custom mode (i.e. when video_preset is not set).
base_model	string	optional	Veo only: base model variant. Default 'fast'.
video_preset	string	optional	Grok only: preset mode. When set, prompt/extend_at/extend_duration are ignored.
extend_at	number	optional	Grok custom mode: seconds into the source video where the extension begins. Required with prompt.
extend_duration	number	optional	Grok custom mode: extension length in seconds. Required with prompt.
seed	integer	optional	Reproducibility seed (Veo).
wait	boolean	optional	Default true: wait for the job and return the finished result. Set false to get the task_id back immediately and poll with get_task — use for long jobs (high-quality video, full songs) or when the connection might time out.
callback_url	string	optional	Optional webhook URL. When set, the tool returns immediately with the task_id and Unifically POSTs the result to this URL when the task finishes. Webhook body: { task_id, status: 'completed'\|'failed', data: { video_url \| image_url \| audio_url \| ... }, error_message? } — note the media arrives under 'data', not 'output'. Use for long jobs instead of waiting.
confirm_cost	boolean	optional	Only relevant if the operator enabled a spend guard. When a call exceeds the configured confirm threshold it returns a quote; retry with confirm_cost: true to proceed. Safe to ignore otherwise.
provider_options	object	optional	Escape hatch for model-specific fields not exposed as named parameters (e.g. Kling multi_shots, Flux steps). Merged into the API 'input' payload. Rejected: fields the tool already manages (prompt, media URLs, task_id, ...) and reserved routing/billing/auth keys (model, callback_url, dry_run, api_key, authorization) — switch models with the 'model' parameter, not here. See https://docs.unifically.com for per-model fields.

url	string	optional	Public https URL of a file to import into Unifically storage.
content_type	string	optional	MIME type of the LOCAL file you want to upload, e.g. 'image/png', 'image/jpeg', 'video/mp4', 'audio/mpeg'. Pass this (instead of url) to get back a one-time upload_url you can PUT the file to with plain curl and NO api key. Only image/, video/ and audio/* are accepted.

page	integer	optional	1-indexed page number. Default 1.
page_size	number	optional	Items per page: 10, 25, 50, or 100. Default 25.
status	string	optional	Filter by task status. Omit for all. (Tasks the generation tools report as 'pending' appear here as 'processing'.)
model	string	optional	Filter by exact model id, e.g. 'google/veo-3.1-fast'.
category	string	optional	Filter by output type, comma-separated from: llm, video, image, audio. E.g. 'video,image'. Note: there is no 'upscale' category — upscales are recorded under video/image.
provider	string	optional	Filter by provider slug(s), comma-separated — the part of the model id before the '/', e.g. 'google,elevenlabs'.
created_after	integer	optional	Unix timestamp in seconds, inclusive lower bound on creation time.
created_before	integer	optional	Unix timestamp in seconds, inclusive upper bound. Must be >= created_after when both are given.

resource	string	optional	Which provider's voice list to return. Default 'elevenlabs-voices'. Options: 'elevenlabs-voices' (ElevenLabs TTS/dialogue/voice-changer voices — use the voice_id in generate_audio), 'kling-voices' (Kling video voices — use the id as voice_id), 'veo-voices' (Google Veo voices — use the id as 'voice'; requires an image/character reference). Aliases 'tts'/'kling'/'veo' work. NOTE: this is Unifically's provider-resource catalog, distinct from the MCP protocol's resources/list.
query	string	optional	Filter the voice list by name/labels — space-separated words, all must match (e.g. 'british female'). Applies to all voice lists.
category	string	optional	ElevenLabs voices only: which set to return. Default 'premade' (~21 stable official voices); 'all' includes the large shared library.
limit	integer	optional	Max items to return. Default 50.

category	string	optional	Filter by category. Omit to return everything.
provider	string	optional	Filter by provider. Takes the stable key ('google', 'black-forest-labs', 'moonshotai') or the human name the user is likely to say ('Black Forest Labs', 'Moonshot AI'). Case-insensitive. Combinable with category.
refresh	boolean	optional	Set true to bypass the hourly cache and re-fetch the live catalog now.