omni-video-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ELEVENLABS_API_KEY | Yes | Required for high-fidelity word-level transcription mapping during ingestion. |
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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| omni_video_ingestA | Ingests a directory of video files, generates word-level audio transcripts, and constructs a semantic Visual Scene Graph for B-Roll searching. Returns the path to the generated project metadata. |
| omni_video_previewA | Generates a filmstrip PNG of the specified video segment. Useful for visually verifying cut boundaries or B-roll placement. Returns the absolute path to the generated PNG file. |
| omni_video_generate_vfxC | Renders motion graphics (e.g., lower thirds, titles) using Hyperframes. Returns the path to the rendered transparent .mov or .webm file. |
| omni_video_renderA | Orchestrates the final render pipeline: applies EDL cuts, overlay graphics, LUT color grading, audio restoration, and subtitle burning. Returns the path to the final rendered video. |
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 targets a distinct stage of the video pipeline: ingest, VFX generation, preview verification, and final render. There is no overlap in functionality.
All tools follow the consistent pattern 'omni_video_<verb>', using clear action verbs (ingest, generate_vfx, preview, render) that accurately describe their purpose.
With 4 tools, the server is well-scoped for a video processing pipeline. Each tool serves a critical, non-redundant role, making the set neither too sparse nor too heavy.
The pipeline covers ingest, VFX, preview, and render, but lacks independent tools for editing (e.g., trimming) or managing overlays directly. However, the render tool bundles many operations, minimizing gaps.