MCP tool reference · #463 of 563 by publishers
create_video
Exposed by 8 servers from 8 publishers, read from the live servers by the Serverdex check; most of them sit in Media & Creative; 37.5% of them take a duration parameter; the most-starred is Xenition (1 stars).
create_video(duration?: integer, prompt: string, language: string, music?: string, title?: string, …)Parameters
share = % of the 8 servers whose schema has it · required = % of those that mark it required| Parameter | Type | Share | Required | Usual description |
|---|---|---|---|---|
| duration | integer | 37.5% | 0% | Clip length in seconds, one of the lengths the model supports (list_models shows durations_seconds). Omit for the model's default. |
| prompt | string | 37.5% | 100% | A description of the video to create. |
| language | string | 25% | 50% | Optional BCP-47 language code (e.g. "en", "vi", "es"). Defaults to "auto". |
| music | string | 25% | 0% | A music bed under a storyboard: glow (warm and calm — a product walkthrough, a story); pulse (upbeat — a launch, a release, a big number); drift (mellow lo-fi — |
| title | string | 25% | 0% | A name for the video in the library; defaults to the headline |
| voice | string | 25% | 0% | Talking-photo models only (list_models marks them talking_photo: true): the voice that says the prompt word for word, by name from the model's voices (for examp |
| accent | string | 12.5% | 0% | Brand colour as #rrggbb |
| artStyle | string | 12.5% | 0% | Optional visual art style. Defaults to AUTOSHORTS (cinematic). Call list_niches for the full list. |
| aspect | string | 12.5% | 0% | 'landscape' (16:9, default), 'portrait' (9:16) or 'square' |
| aspect_ratio | string | 12.5% | 0% | Aspect ratio: 16:9 (landscape), 9:16 (portrait), or 1:1 (square). Defaults to the opening image's shape when 'image' is portrait or landscape, otherwise 16:9. |
| body | string | 12.5% | 0% | A sentence of detail (announcement template) |
| brand_name | string | 12.5% | 0% | — |
Source: the input schema each server returns for create_video, aggregated over the 8 index-tier servers; type and description are the values most servers use. Rebuilt every 6 hours.
Servers with create_video
8 of 8 · 8 publishers · 8 answering live · most-starred first, 3 per publisher| # | Server | Publisher | Category | ★ | Live | How it describes create_video |
|---|---|---|---|---|---|---|
| 1 | Xenitionxenition · Media & Creative | xenition | Media & Creative | 1 | yes | Use this when the user wants a short AI video clip made from a description. Starts the video and returns its id right away; generating takes a few minutes, and video_status reports when it is ready with the file link. The clip is saved to their Xenition library. |
| 2 | Ravenposttarget1m · Communication | target1m | Communication | 1 | yes | Render a short branded video (9:16 vertical by default; also square and landscape) and save it to the media library as an mp4 — returning a media id create_post takes as mediaIds. Either a storyboard (template storyboard: the scenes given in `scenes`, in order, with an optional music bed) or one of the fixed, silent templates in list_video_templates. Pick the canvas by where it goes: vertical for |
| 3 | ABContentsagustinnb · Media & Creative | agustinnb | Media & Creative | — | yes | Make a video (vertical 9:16 by default; also 4:5, 1:1, 16:9) with voice, captions and music from a brief, files (PDF, Word, Excel, PowerPoint, CSV, text, photos) and/or a public website (site_url: we read its text and can use its logo). Spends tokens from the API key in the Authorization header. Returns the order; poll get_video. The script uses only facts from the brief and files. |
| 4 | StoryShortairdropfi · Media & Creative | airdropfi | Media & Creative | — | yes | Create (enqueue) a new AI faceless video from a topic. Returns immediately with a video id and status "PENDING"; the render runs asynchronously — poll get_video every 20-30 seconds until status is "COMPLETED" (playable videoUrl) or "FAILED". Costs 40 credits with the default voice (+25 for a language only ElevenLabs speaks, e.g. Persian); art style does not change the price. A short balance is ref |
| 5 | Epic Videojapage1928 · Media & Creative | japage1928 | Media & Creative | — | yes | Generate a short AI video with synced sound from a text prompt using Epic Video. Videos are 5, 15, 30, 60 or 120 seconds long; anything over 15 seconds is stitched from chained 5-second clips for consistency. Videos cost tokens per second: 1 token/sec at 480p, 2 tokens/sec at 720p (e.g. a 15-second 480p video costs 15 tokens). Free plans get 15 tokens/week and can make videos up to 15 seconds; 60/ |
| 6 | Deepniadeepnia · Media & Creative | deepnia | Media & Creative | — | yes | Use this when the user accepted the price from quote_video: makes the video with Deepnia from that quote_id and credits, paid with the user's Deepnia credits and saved in their Deepnia account. Refunded if it fails; the same quote_id never charges twice. Then follow it with get_creation. |
| 7 | Arcképgmen1057 · Media & Creative | gmen1057 | Media & Creative | — | yes | Start a paid video job. Request follows POST /api/v1/videos/generations (supports mode="t2v", "i2v", "r2v", "edit", "extend", and "a2v" with audio_url + optional image_url/prompt on ltx-2.5-fast / ltx-2.5-pro). Wan models: - wan3.0: unified 2-30 s (480p/720p/1080p; 16:9, 9:16, 1:1, 4:3, 3:4, adaptive; no 21:9, no negative_prompt or shot_type). Multi-shot via `Shot N [start-end]:` in prompt (<= |
| 8 | GenMagicyumaheymans · Media & Creative | yumaheymans | Media & Creative | — | yes | Start generating a video from a text description with GenMagic (or animate an image: pass 'image' as the opening frame), with any text-to-video model, clip length, resolution and sound the model supports (list_models with category "video" shows them and the per-second price). Video is asynchronous, so this returns a job id immediately (nothing is charged yet). Poll it with the get_video tool every |
Stars from GitHub as stored in the Serverdex index (re-read every 7 days per server); live = answered the last daily check of its hosted endpoint.