Skip to main content

🎬 ffmpeg-mcp

A powerful MCP server for video and audio processing through FFmpeg

PyPI version License: MIT Python Version

Integrate FFmpeg with Claude, Dive, and other MCP-compatible AI systems. Convert, compress, trim videos, extract audio, and more — all through natural language.

Features • Installation • Tools • Usage • Configuration


✨ Features

📊 Media Information

  • Get comprehensive metadata
  • Duration, resolution, codecs
  • Bitrate and stream details
  • JSON formatted output

🔄 Format Conversion

  • Convert between any formats
  • MP4, MKV, WebM, MOV, etc.
  • Custom video/audio codecs
  • Resolution scaling

🗜️ Video Compression

  • Quality presets (low/medium/high)
  • Encoding speed control
  • H.264 optimization
  • Size reduction stats

✂️ Video Trimming

  • Precise start/end times
  • Duration-based cuts
  • Stream copy (fast)
  • No re-encoding needed

🎵 Audio Extraction

  • Multiple formats supported
  • MP3, AAC, WAV, FLAC, OGG, Opus
  • Bitrate control
  • High quality output

🎞️ Advanced Features

  • Merge multiple videos
  • Extract frames as images
  • Interval or count-based extraction
  • JPG, PNG, BMP, WebP output

📝 Subtitles

  • Burn-in SRT/ASS/VTT subtitles
  • Multiple styles available
  • Customizable font size
  • Works great with Whisper MCP

🚀 Installation

Prerequisites

Install FFmpeg on your system:

Platform Command
🪟 Windows winget install FFmpeg
🍎 macOS brew install ffmpeg
🐧 Linux sudo apt install ffmpeg

Getting Started

Add the following config to your MCP client:

{
  "mcpServers": {
    "ffmpeg": {
      "command": "uvx",
      "args": ["ffmpeg-mcp-lite"]
    }
  }
}

MCP Client Configuration

Dive
  1. Open Dive Desktop
  2. Click "+ Add MCP Server"
  3. Paste the config provided above
  4. Click "Save" and you're ready!
Claude Code

Use the Claude Code CLI to add the ffmpeg MCP server:

claude mcp add ffmpeg uvx ffmpeg-mcp-lite
Claude Desktop

Add to your claude_desktop_config.json:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "ffmpeg": {
      "command": "uvx",
      "args": ["ffmpeg-mcp-lite"]
    }
  }
}
Cursor

Go to Cursor Settings -> MCP -> New MCP Server. Use the config provided above.

VS Code / Copilot

Install via the VS Code CLI:

code --add-mcp '{"name":"ffmpeg","command":"uvx","args":["ffmpeg-mcp-lite"]}'
Windsurf

Follow the configure MCP guide using the standard config from above.

Manual Installation

pip install ffmpeg-mcp-lite

Or with uv:

uv pip install ffmpeg-mcp-lite

🛠️ Available Tools

All tools are prefixed with ffmpeg_ to avoid naming conflicts with other MCP servers.

📊 Media Information

Tool Description
ffmpeg_get_info

Get comprehensive video/audio metadata

  • Parameters: file_path
  • Returns: JSON with duration, resolution, codecs, bitrate, streams

🔄 Conversion & Compression

Tool Description
ffmpeg_convert

Convert video/audio to different formats

  • Parameters: file_path, output_format, scale, video_codec, audio_codec
  • Formats: mp4, mkv, webm, mov, mp3, wav, etc.
ffmpeg_compress

Compress video to reduce file size

  • Parameters: file_path, quality, scale, preset
  • Quality: low, medium, high
  • Preset: ultrafast to veryslow

✂️ Editing

Tool Description
ffmpeg_trim

Trim video to extract a segment

  • Parameters: file_path, start_time, end_time or duration
  • Time format: "00:01:30" or seconds
ffmpeg_merge

Concatenate multiple videos into one

  • Parameters: file_paths (list), output_path
  • Supports: Same codec videos

🎵 Audio & Frames

Tool Description
ffmpeg_extract_audio

Extract audio track from video

  • Parameters: file_path, audio_format, bitrate
  • Formats: mp3, aac, wav, flac, ogg, opus
ffmpeg_extract_frames

Extract frames as images

  • Parameters: file_path, interval or count, format
  • Formats: jpg, png, bmp, webp

📝 Subtitles

Tool Description
ffmpeg_add_subtitles

Burn-in subtitles to video (hardcode)

  • Parameters: file_path, subtitle_path, style, font_size, output_path
  • Formats: SRT, ASS, VTT
  • Styles: outline, shadow, background, glow

💡 Usage Examples

Get Media Information

"Get info about /path/to/video.mp4"
"What's the resolution and duration of this video?"
"Show me the codec information for my video"

Convert Videos

"Convert video.mp4 to WebM format"
"Convert this video to MKV with h265 codec"
"Convert and scale to 1280x720"

Compress Videos

"Compress video.mp4 with medium quality"
"Compress this video to reduce file size, use fast preset"
"Compress with high quality and scale to 1920:-1"

Trim Videos

"Trim video.mp4 from 00:01:00 to 00:02:30"
"Cut the first 30 seconds from this video"
"Extract a 1-minute clip starting at 5:00"

Extract Audio

"Extract audio from video.mp4 as MP3"
"Get the audio track in AAC format with 192k bitrate"
"Extract audio as FLAC for best quality"

Extract Frames

"Extract one frame every 5 seconds from video.mp4"
"Get 10 frames evenly distributed from this video"
"Extract frames as PNG images"

Merge Videos

"Merge video1.mp4 and video2.mp4 together"
"Concatenate these three videos into one"

Add Subtitles

"Add subtitles.srt to video.mp4"
"Burn in Chinese subtitles with shadow style"
"Add subtitles with font size 32 and glow effect"

🔧 Configuration

Environment Variables

Variable Description Default
FFMPEG_PATH Path to ffmpeg binary ffmpeg
FFPROBE_PATH Path to ffprobe binary ffprobe
FFMPEG_OUTPUT_DIR Default output directory ~/Downloads

Custom Configuration

{
  "mcpServers": {
    "ffmpeg": {
      "command": "uvx",
      "args": ["ffmpeg-mcp-lite"],
      "env": {
        "FFMPEG_OUTPUT_DIR": "/path/to/output"
      }
    }
  }
}

🏗️ Architecture

Built With

  • FFmpeg - Video/audio processing engine
  • FastMCP - MCP Python framework
  • asyncio - Async subprocess execution
  • Python 3.10+ - Type hints and modern features

Key Features

  • ✅ Async Processing: Non-blocking FFmpeg execution
  • ✅ Type Safe: Full type hints with mypy validation
  • ✅ Well Tested: 31 test cases with pytest
  • ✅ Cross Platform: Works on Windows, macOS, Linux
  • ✅ Modular Design: One file per tool

🤝 Contributing

Contributions are welcome!

  1. Fork the repository
  2. Create a feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

Development

# Clone and install
git clone https://github.com/kevinwatt/ffmpeg-mcp-lite.git
cd ffmpeg-mcp-lite
uv sync

# Run tests
uv run pytest

# Type checking
uv run mypy src/

# Linting
uv run ruff check src/

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.


🙏 Acknowledgments

  • FFmpeg - The powerful multimedia framework
  • Anthropic - For the Model Context Protocol
  • Dive - MCP-compatible AI platform

Metadata

Release files for ffmpeg-mcp-lite 0.2.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for ffmpeg-mcp-lite 0.2.2
File Size Uploaded
ffmpeg_mcp_lite-0.2.2.tar.gz 18.7 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for ffmpeg-mcp-lite 0.2.2
File Interpreter ABI Platform
ffmpeg_mcp_lite-0.2.2-py3-none-any.whl Python 3 none any Details

Total release size: 35.4 kB

Release files / ffmpeg_mcp_lite-0.2.2.tar.gz

Download URL ffmpeg_mcp_lite-0.2.2.tar.gz
Size 18.7 kB
Tags Source
SHA-256 checksum
How to use checksums
c39a2b1e74c4736053b113268dc5f5979d13dbd7c397ef8459a11c3a65790f29
BLAKE2b-256 checksum
How to use checksums
5a954f3818bef0ceb923d8f45430ee526ee607f24abbf540983493d0f1fb80fd
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.9

Release files / ffmpeg_mcp_lite-0.2.2-py3-none-any.whl

Download URL ffmpeg_mcp_lite-0.2.2-py3-none-any.whl
Size 16.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
7a62ca395ce62365a09c88b014e9b81de508563bbc5d1e1dc128a13f9d8c1632
BLAKE2b-256 checksum
How to use checksums
4883caee60032f7aa93b2cdc6353263f7830ad3d15f41f74f88af1febfb89001
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.9

Release history Release notifications | RSS feed

This release

0.2.2 This release

2 release files

0.2.1

2 release files

0.2.0

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page