video-deconstructor
by shivam098
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VD_FONT | No | TrueType font (.ttf) used for timestamps on contact sheets. | |
| VD_QUIET | No | Quiet mode flag. | |
| VD_YTDLP | No | Binary path to yt-dlp. | |
| VD_FFMPEG | No | Binary path to ffmpeg. | |
| VD_FFPROBE | No | Binary path to ffprobe. | |
| VD_CACHE_DIR | No | Directory used to cache downloads per video. | |
| VD_JS_RUNTIME | No | Value passed to yt-dlp's --js-runtimes option. | |
| VD_OUTPUT_DIR | No | Output directory for generated artifacts. | |
| GEMINI_API_KEY | No | Your own Gemini API key, needed for the optional gemini_analyze_video tool. Can be set in an "env" block in the MCP config or in your user environment before starting the client. | |
| VD_WHISPER_CLI | No | Path to whisper.cpp's whisper-cli. | |
| VD_GEMINI_MODEL | No | Override the default Gemini model (default is gemini-3.8-flash). | |
| VD_WHISPER_MODEL | No | Path to a GGML Whisper model. |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo recent community issues