home / mcp / video & audio editing mcp server
An FFMPEG powered MCP server for basic Video and Audio editing
Configuration
View docs{
"mcpServers": {
"misbahsy-video-audio-mcp": {
"command": "python",
"args": [
"server.py"
]
}
}
}This MCP Server provides comprehensive video and audio editing capabilities by leveraging FFmpeg. You can automate and orchestrate professional editing tasksโsuch as format conversion, trimming, overlays, transitions, and audio processingโthrough an MCP client, enabling powerful AI-assisted workflows.
You connect to the Video & Audio Editing MCP Server from your MCP client and issue high-level editing requests. Use supported actions to transform video and audio, apply overlays and effects, and assemble multi-clip workflows with transitions. The server exposes a rich set of editing operations that you can trigger from your automation or UI.
Prerequisites you need on your machine before starting: Python 3.8 or newer, FFmpeg, and a suitable runtime for MCP servers.
# Install uv if you haven't already
curl -LsSf https://astral.sh/uv/install.sh | sh
# Start the MCP server directly with uv
uv run server.py# Verify Python 3.8+ is installed
python --version
# Install dependencies (if required by project)
pip install -r requirements.txt
# Run the MCP server directly
python server.py# Start the MCP server with a specified transport (stdio in this example)
python -c "from server import mcp; mcp.run(transport='stdio')"After starting, confirm the server is ready by inspecting the console output for a health check or startup confirmation. You should then be able to send editing requests from your MCP client.
Ensure FFmpeg is accessible from your system path. On macOS or Linux you can typically install it via your package manager; on Windows, download the official FFmpeg binaries and add them to your PATH.
Use the MCP client to request edits by specifying the desired operation (for example, convert_video_format, trim_video, add_text_overlay, concatenate_videos) and providing the necessary input/output paths and parameters. The server will perform the requested actions using FFmpeg under the hood and return the resulting media files or status.
The server includes error handling for missing files, unsupported formats, and invalid parameters. It logs errors clearly and attempts safe fallbacks when possible. Run in a controlled environment and validate outputs during development and testing.
If the MCP server does not connect from your client, verify the command and arguments, ensure the Python environment is active, and try starting the server manually to observe any error messages. Check that FFmpeg is installed and accessible, and confirm network or IPC transport settings in your MCP client configuration.
You can chain multiple editing steps in a workflow, such as converting a video, trimming it, applying a text overlay, and finally concatenating it with another clip, all through your MCP client. The server supports a broad range of operations to enable end-to-end media processing pipelines.
Extract audio tracks from video files to separate audio files for independent processing.
Cut video segments with precise timing to produce shorter clips or highlight reels.
Convert between video formats (MP4, MOV, AVI, etc.) while preserving or altering quality.
Comprehensive video property conversion including resolution, codec, bitrate, and frame rate.
Adjust aspect ratios with padding or cropping to fit target canvases or platforms.
Change video resolution while aiming to preserve visual quality.
Switch video codecs such as H.264, H.265, or VP9.
Set target video bitrate to control quality and file size.
Modify playback frame rate of the output video.
Convert between audio formats like MP3, WAV, AAC, and more.
Adjust audio properties such as sample rate and channels.
Set the audio bitrate to control quality and size.
Change the audio sample rate for compatibility or quality.
Convert between mono and stereo audio configurations.
Change the audio codec inside video files.
Adjust the audio bitrate within video containers.
Change the audio sample rate inside video files.
Modify the number of audio channels in videos.
Burn subtitles with custom styling into the video stream.
Add dynamic text overlays with timing and styling.
Insert image overlays like logos or watermarks.
Insert B-roll footage with transitions for richer editing.
Apply simple transitions such as fades between clips.
Join multiple videos with optional transitions to create a single timeline.
Create slow-motion or time-lapse effects by modifying playback speed.
Auto-detect and remove silent segments from audio.
Verify server status and readiness of capabilities.