Skip to main content
Glama
kevinwatt

FFmpeg MCP

by kevinwatt
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
FFMPEG_PATHNoPath to ffmpeg binaryffmpeg
FFPROBE_PATHNoPath to ffprobe binaryffprobe
FFMPEG_OUTPUT_DIRNoDefault output directory~/Downloads

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
ffmpeg_get_infoA

Get video/audio file metadata using ffprobe.

Args:
    file_path: Path to the media file

Returns:
    JSON string with media metadata including duration, resolution,
    codecs, bitrate, and stream information
ffmpeg_convertB

Convert video/audio to a different format.

Args:
    file_path: Path to the input media file
    output_format: Target format (e.g., mp4, mkv, webm, mp3, wav)
    scale: Optional resolution scale (e.g., "1280:720", "1920:-1" for auto height)
    video_codec: Optional video codec (e.g., libx264, libx265, libvpx-vp9)
    audio_codec: Optional audio codec (e.g., aac, mp3, opus)

Returns:
    Path to the converted file
ffmpeg_compressA

Compress a video file to reduce file size.

Args:
    file_path: Path to the input video file
    quality: Compression quality level - "low" (smallest file), "medium", or "high" (best quality)
    scale: Optional resolution scale (e.g., "1280:720", "1920:-1" for auto height)
    preset: Encoding speed preset - faster presets = larger files, slower = smaller files

Returns:
    Path to the compressed file
ffmpeg_trimA

Trim a video to extract a specific segment.

Args:
    file_path: Path to the input video file
    start_time: Start time (e.g., "00:01:30" or "90" for 90 seconds)
    end_time: End time (e.g., "00:02:00"). Mutually exclusive with duration.
    duration: Duration of the clip (e.g., "30" for 30 seconds). Mutually exclusive with end_time.

Returns:
    Path to the trimmed file
ffmpeg_extract_audioA

Extract audio track from a video file.

Args:
    file_path: Path to the input video file
    audio_format: Output audio format (mp3, aac, wav, flac, ogg, opus)
    bitrate: Audio bitrate (e.g., "128k", "192k", "320k"). If not specified, uses format default.

Returns:
    Path to the extracted audio file
ffmpeg_mergeA

Concatenate multiple video files into one.

Args:
    file_paths: List of paths to video files to merge (in order)
    output_path: Optional output file path. If not specified, saves to default output directory.

Returns:
    Path to the merged file
ffmpeg_extract_framesA

Extract frames from a video as images.

Args:
    file_path: Path to the input video file
    interval: Extract one frame every N seconds (e.g., 1.0 for one frame per second)
    count: Total number of frames to extract (evenly distributed). Mutually exclusive with interval.
    format: Output image format (jpg, png, bmp)

Returns:
    Path to the directory containing extracted frames
ffmpeg_add_subtitlesA

Add subtitles to a video file (burn-in/hardcode).

Args:
    file_path: Path to the input video file
    subtitle_path: Path to the subtitle file (SRT, ASS, VTT)
    style: Subtitle style - "outline" (default), "shadow", "background", or "glow"
    font_size: Font size for subtitles (default: 24)
    output_path: Optional output file path. If not specified, saves to default output directory.

Returns:
    Path to the output video with subtitles

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4/5.0

Scored across 8 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: adding subtitles, compressing, converting, extracting audio, extracting frames, getting info, merging, and trimming. No overlap in functionality.

Naming Consistency5/5

All tools follow a consistent 'ffmpeg_verb_noun' pattern in snake_case (e.g., ffmpeg_extract_audio, ffmpeg_get_info). No deviations.

Tool Count5/5

With 8 tools, the server covers a broad range of common FFmpeg operations without being excessive. Each tool serves a distinct, useful purpose.

Completeness4/5

The tool set covers core video/audio operations (info, conversion, compression, trimming, merging, subtitle addition) but lacks advanced features like video effects or audio filters. It is sufficient for typical use cases.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources