Skip to main content
Glama
kwacky1

video-understanding-mcp

by kwacky1

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
VU_CACHE_DIRNoContent-addressed cache root. Defaults to the system cache directory.
VU_FFMPEG_PATHNoPath to the ffmpeg executable.ffmpeg
VU_FFPROBE_PATHNoPath to the ffprobe executable.ffprobe
VU_WHISPER_PATHNoPath to the whisper-cli executable.whisper-cli
VU_MAX_INPUT_BYTESNoMaximum accepted input size in bytes.10737418240
VU_ALLOWED_READ_ROOTSNoReadable filesystem roots. Defaults to the current working directory.current directory
VU_WHISPER_MODEL_PATHNoAbsolute path to a GGML model for transcription.
VU_ALLOWED_WRITE_ROOTSNoWritable output roots. Defaults to the readable roots.readable roots

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

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
video_probeA

Inspect a local media file with ffprobe and return normalised metadata. The path must be absolute and inside an allowed read root.

video_transcribeA

Transcribe the first audio stream of a local media file with whisper.cpp. Processing is offline and writes timestamped JSON and Markdown into an allowed output directory.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources