video-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VIDEO_MODEL | No | Replicate model in the form owner/name. Any Replicate video model that accepts a prompt input can be used. | minimax/video-01 |
| VIDEO_OUTPUT_DIR | No | Directory where the download_video tool saves files. | ~/Videos/video-mcp |
| REPLICATE_API_TOKEN | Yes | Your Replicate API token, used to authenticate with the Replicate API (paid, billed per generation). |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_videoA | Сгенерировать короткое видео по текстовому описанию. Args: prompt: Подробное описание сцены (лучше на английском), например "a red fox running through snowy forest, cinematic, slow motion". image_url: Необязательно. Ссылка на картинку, которая станет первым кадром. model: Необязательно. Модель Replicate в формате "владелец/название". По умолчанию minimax/video-01. Генерация обычно занимает 1–5 минут. Если видео не успело сгенерироваться, инструмент вернёт ID — затем используйте check_video. |
| check_videoA | Проверить статус генерации видео по ID и получить ссылку, когда оно готово. Args: prediction_id: ID, который вернул generate_video. |
| download_videoA | Скачать готовое видео на компьютер (по умолчанию в папку Videos/video-mcp). Args: video_url: Ссылка на видео из generate_video или check_video. filename: Необязательно. Имя файла, например "fox.mp4". |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool maps to a distinct step in an asynchronous pipeline: creation (generate_video), polling (check_video), and retrieval (download_video). There is no overlap in purpose, and the descriptions explicitly chain them (generate returns an ID for check_video, check_video returns a URL for download_video).
All three names follow a strict verb_noun pattern (generate_video, check_video, download_video) with a shared 'video' resource noun. Fully predictable and consistent.
Three tools are minimal but each earns its place in the async generation workflow, with no bloat. It is at the low end of the scale, so slightly thin for anything beyond single-video generation.
The generate → poll → download lifecycle is fully covered, so an agent can complete the core task end to end. Minor gaps exist: no cancel/delete for a stuck prediction, no way to list past predictions, and no model discovery tool.