FFmpeg MCP Lite
MCP server for video/audio processing via FFmpeg - convert, compress, trim, extract audio, add subtitles
What is FFmpeg MCP Lite?
FFmpeg MCP Lite is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for video/audio processing via ffmpeg - convert, compress, trim, extract audio, add subtitles
MCP server for video/audio processing via FFmpeg - convert, compress, trim, extract audio, add subtitles
This server falls under the APIs category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCP server for video/audio processing via FFmpeg - convert,
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx ffmpeg-mcp-liteConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use FFmpeg MCP Lite
FFmpeg MCP Lite is a lightweight Python MCP server that wraps the FFmpeg command-line tool, letting AI assistants convert, compress, trim, extract, and merge video and audio files through natural language instructions. It exposes eight tools with an ffmpeg_ prefix that map directly to common FFmpeg operations, and uses ffprobe for media metadata inspection. The server is designed to be minimal and easy to deploy with uvx, making FFmpeg's full processing power accessible without needing to remember complex command-line flags.
Prerequisites
- Python 3.10 or later with pip or uv installed
- FFmpeg installed on your system (ffmpeg and ffprobe binaries accessible on PATH)
- An MCP client such as Claude Desktop or Claude Code
- Adequate disk space for output video and audio files
Install FFmpeg on your system
FFmpeg MCP Lite requires the FFmpeg binary to be installed independently. Install it using your system's package manager.
# macOS
brew install ffmpeg
# Windows
winget install FFmpeg
# Ubuntu/Debian
sudo apt install ffmpegInstall the Python package
Install ffmpeg-mcp-lite from PyPI using pip or uv. Using uv provides isolated environments and faster installs.
pip install ffmpeg-mcp-lite
# or
uv pip install ffmpeg-mcp-liteAdd to your MCP client configuration
Register the server in your MCP client config using uvx to run the package in an isolated environment. Set FFMPEG_OUTPUT_DIR to control where processed files are saved.
{
"mcpServers": {
"ffmpeg": {
"command": "uvx",
"args": ["ffmpeg-mcp-lite"],
"env": {
"FFMPEG_OUTPUT_DIR": "/Users/you/Downloads"
}
}
}
}Set custom binary paths if needed
If your FFmpeg installation is in a non-standard location, configure the FFMPEG_PATH and FFPROBE_PATH environment variables to point to the exact binaries.
{
"mcpServers": {
"ffmpeg": {
"command": "uvx",
"args": ["ffmpeg-mcp-lite"],
"env": {
"FFMPEG_PATH": "/usr/local/bin/ffmpeg",
"FFPROBE_PATH": "/usr/local/bin/ffprobe",
"FFMPEG_OUTPUT_DIR": "/tmp/output"
}
}
}
}Explore the eight available tools
The server provides: ffmpeg_get_info (inspect media properties via ffprobe), ffmpeg_convert (change format or codec), ffmpeg_compress (reduce file size), ffmpeg_trim (cut a time segment), ffmpeg_extract_audio (pull audio track), ffmpeg_extract_frames (grab still images), ffmpeg_merge (join multiple videos), and ffmpeg_add_subtitles (burn in subtitles from an SRT file).
FFmpeg MCP Lite Examples
Client configuration
Claude Desktop configuration for FFmpeg MCP Lite using uvx with a default output directory.
{
"mcpServers": {
"ffmpeg": {
"command": "uvx",
"args": ["ffmpeg-mcp-lite"],
"env": {
"FFMPEG_OUTPUT_DIR": "/Users/you/Downloads"
}
}
}
}Prompts to try
Natural language prompts to use with Claude for video and audio processing via FFmpeg MCP Lite.
- "Get information about /tmp/video.mp4 — what codec and resolution is it?"
- "Convert /tmp/clip.mov to MP4 format"
- "Compress /tmp/large.mp4 to reduce its file size, use a fast preset"
- "Trim /tmp/recording.mp4 to just the section from 2 minutes to 5 minutes"
- "Extract the audio from /tmp/podcast.mp4 as an MP3"
- "Burn the subtitles from /tmp/movie.srt into /tmp/movie.mp4"Troubleshooting FFmpeg MCP Lite
FFmpeg binary not found when running tools
Run ffmpeg -version in your terminal to confirm FFmpeg is on PATH. If it is not, install it with brew install ffmpeg (macOS) or your OS package manager. Set FFMPEG_PATH and FFPROBE_PATH in the MCP server's env block if FFmpeg is in a non-standard location.
Output files are missing after a successful tool call
Check the FFMPEG_OUTPUT_DIR setting — output defaults to ~/Downloads if not set. Ensure the directory exists and the MCP server process has write permission to it.
Subtitle burning fails or produces an error
Ensure your FFmpeg build includes the libass library, which is required for subtitle rendering. The brew formula on macOS includes libass by default. On Linux, install ffmpeg with the --enable-libass compile flag or use a distribution package that includes it.
Frequently Asked Questions about FFmpeg MCP Lite
What is FFmpeg MCP Lite?
FFmpeg MCP Lite is a Model Context Protocol (MCP) server that mcp server for video/audio processing via ffmpeg - convert, compress, trim, extract audio, add subtitles It connects AI assistants to external tools and data sources through a standardized interface.
How do I install FFmpeg MCP Lite?
Follow the installation instructions on the FFmpeg MCP Lite GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with FFmpeg MCP Lite?
FFmpeg MCP Lite works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is FFmpeg MCP Lite free to use?
Yes, FFmpeg MCP Lite is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
FFmpeg MCP Lite Alternatives — Similar APIs Servers
Looking for alternatives to FFmpeg MCP Lite? Here are other popular apis servers you can use with Claude, Cursor, and VS Code.
Kong
★ 43.4k🦍 The API and AI Gateway
API Mega List
★ 5.4kThis GitHub repo is a powerhouse collection of APIs you can start using immediately to build everything from simple automations to full-scale applications. One of the most valuable API lists on GitHub—period. 💪
Fetch
★ 5.4kFetch web content and convert to markdown for AI consumption
Fusio
★ 2.1kSelf-Hosted API Management for Builders
Korean Law
★ 1.8k국가법령정보MCP v4.0 | 법제처 41개 API → 17개 MCP 도구. 법령·판례·조례 검색 + LLM 환각 방지 인용검증 + 조문 영향 그래프(impact_map) + 시점 비교 자동 diff(time_travel) + 시민 5단계 실행 가이드(action_plan) | 41 Korean legal APIs → 17 MCP tools
RuleGo
★ 1.5k⛓️RuleGo is a lightweight, high-performance, embedded, next-generation component orchestration rule engine framework for Go.
Browse More APIs MCP Servers
Explore all apis servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up FFmpeg MCP Lite in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use FFmpeg MCP Lite?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.