Grok Imagine Video MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEBUG | No | true でデバッグログを有効化 | false |
| OUTPUT_DIR | No | 動画のデフォルト出力ディレクトリ | |
| XAI_API_KEY | Yes | xAI API キー | |
| VIDEO_POLL_INTERVAL | No | ポーリング間隔（ミリ秒） | 5000 |
| VIDEO_MAX_POLL_ATTEMPTS | No | 最大ポーリング回数 | 120 |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_videoA | Generate a new video using xAI Grok Imagine Video API (grok-imagine-video). Supports text-to-video (T2V), image-to-video (I2V), and reference-to-video (R2V). Supports aspect ratios: 16:9, 4:3, 1:1, 9:16, 3:4, 3:2, 2:3. Video duration: 1-15 seconds (default 8). Resolution: 480p, 720p, or 1080p (1080p only with model grok-imagine-video-1.5). The output MP4 always contains an auto-generated audio track (sound effects, ambience, score) driven by the prompt; there is no audio parameter. For image-to-video, provide image_url, image_path, or image_file_id. For reference-to-video, provide reference_images. |
| edit_videoA | Edit an existing video using xAI Grok Imagine Video API. Provide a source video URL along with a prompt describing the desired changes. The maximum supported video length is 8.7 seconds. The edited video will have the same duration as the original. |
| extend_videoA | Extend an existing video by generating continuation content using xAI Grok Imagine Video API. Provide a source video URL and a prompt describing what should happen next. The extension segment duration is 1-10 seconds (default 6). |
| upload_fileA | Upload a local image or video file to the xAI Files API and get a file_id. The file stays private; the returned file_id can be used as input for generate_video (image_file_id, reference_images[].file_id), edit_video, and extend_video (video_file_id). Useful for reusing the same asset across multiple calls without re-uploading. Supported: images (jpg/jpeg/png/gif/webp/bmp/tiff) and videos (mp4), max 48 MB. |
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 4 tools
Each tool has a clearly distinct purpose: generate creates new videos, edit modifies existing ones, extend continues them, and upload_file handles file ingestion. No overlap or ambiguity.
All tool names follow a consistent verb_noun pattern in snake_case (generate_video, edit_video, extend_video, upload_file). The pattern is uniform and predictable.
With 4 tools, the server is well-scoped for video generation. Each tool serves a necessary core function without redundancy or bloat.
The tool set covers the full video lifecycle: generate, edit, extend, and upload. There are no obvious missing operations for the stated domain.