Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
VIDEO_MCP_FFMPEGNoPath to the FFmpeg executable. Overrides the 'tools.ffmpeg' value in video-mcp.yaml.
VIDEO_MCP_ASR_MODELNoPath to the Whisper model file to use for transcription. Overrides the 'asr.model' value in video-mcp.yaml.
VIDEO_MCP_WORKSPACENoWorking directory for output files. Overrides the 'output.workspace' value in video-mcp.yaml.
VIDEO_MCP_ASR_DEVICENoDevice to use for ASR (auto, cpu, cuda). Overrides the 'asr.device' value in video-mcp.yaml.
VIDEO_MCP_WHISPER_CPPNoPath to the whisper.cpp executable. Overrides the 'tools.whisper_cpp' value in video-mcp.yaml.

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": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
video.inspectB

Inspect a video with FFprobe and return normalized media metadata.

video.transcribeC

Transcribe normalized audio with the configured local ASR backend.

video.captionC

Run the complete local caption pipeline for a video.

video.create_previewA

Burn ASS subtitles into a fast, downscaled MP4 preview.

video.renderA

Render a burned-in ASS subtitle preview; alias for video.create_preview.

subtitle.cleanC

Clean a transcript with the optional local LLM and deterministic fallback.

subtitle.export_srtC

Export a normalized transcript JSON file as SRT.

subtitle.export_assB

Export a normalized transcript JSON file as styled ASS.

project.create_kdenliveB

Create an editable Kdenlive project from a video and SRT file.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/petercr/subtitle-machine-kdenlive'

If you have feedback or need assistance with the MCP directory API, please join our Discord server