FFmpeg MCP

v1.0.0โ€ขAPIsโ€ขstable

Enables video and audio processing through FFmpeg, supporting format conversion, compression, trimming, audio extraction, frame extraction, video merging, and subtitle burning through natural language commands.

aiaudioclaudeffmpegmcp
Share:
24
Stars
0
Downloads
0
Weekly
0/5

What is FFmpeg MCP?

FFmpeg MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables video and audio processing through ffmpeg, supporting format conversion, compression, trimming, audio extraction, frame extraction, video merging, and subtitle burning through natural language...

Enables video and audio processing through FFmpeg, supporting format conversion, compression, trimming, audio extraction, frame extraction, video merging, and subtitle burning through natural language commands.

This server falls under the APIs category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Enables video and audio processing through FFmpeg, supportin

Use Cases

Comprehensive video processing
Audio manipulation
Frame and subtitle handling
kevinwatt

Maintainer

LicenseMIT License
Languagepython
Versionv1.0.0
UpdatedMay 8, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx ffmpeg-mcp

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use FFmpeg MCP

FFmpeg MCP (also published as ffmpeg-mcp-lite) is a Python-based MCP server that wraps FFmpeg, enabling AI assistants to perform video and audio processing through natural language commands. It exposes eight tools covering format conversion, compression, trimming, audio extraction, frame extraction, video merging, and subtitle burning. Instead of remembering FFmpeg command-line syntax, users can describe what they want and the server constructs and executes the appropriate FFmpeg command. FFprobe integration provides media metadata inspection before processing.

Prerequisites

  • Python 3.10 or later with pip or uv installed
  • FFmpeg installed on your system (ffmpeg and ffprobe binaries on PATH)
  • An MCP client such as Claude Desktop or Claude Code
  • Sufficient disk space for output files (defaults to ~/Downloads)
1

Install FFmpeg on your system

The MCP server is a wrapper around the FFmpeg binary, so FFmpeg must be installed separately on your operating system before installing the Python package.

# macOS
brew install ffmpeg

# Windows
winget install FFmpeg

# Ubuntu/Debian
sudo apt install ffmpeg
2

Install the ffmpeg-mcp-lite Python package

Install the package using pip or uv. The uv approach is recommended for isolated environments and faster installs.

# Using pip
pip install ffmpeg-mcp-lite

# Using uv
uv pip install ffmpeg-mcp-lite
3

Configure your MCP client

Add the FFmpeg MCP server to your client configuration. Use uvx to run the package in an isolated environment. Optionally set FFMPEG_OUTPUT_DIR to control where output files are saved.

{
  "mcpServers": {
    "ffmpeg": {
      "command": "uvx",
      "args": ["ffmpeg-mcp-lite"],
      "env": {
        "FFMPEG_OUTPUT_DIR": "/Users/you/Downloads"
      }
    }
  }
}
4

Add via Claude Code CLI (alternative)

If you use Claude Code, you can register the server with a single command instead of editing the config file manually.

claude mcp add ffmpeg uvx ffmpeg-mcp-lite
5

Understand the available tools

The server exposes eight ffmpeg_ prefixed tools: ffmpeg_get_info (media metadata via ffprobe), ffmpeg_convert (format/codec conversion), ffmpeg_compress (file size reduction), ffmpeg_trim (extract a time range), ffmpeg_extract_audio (isolate audio track), ffmpeg_extract_frames (capture still images), ffmpeg_merge (concatenate videos), and ffmpeg_add_subtitles (hardcode subtitle overlays).

6

Configure custom FFmpeg binary paths (optional)

If FFmpeg is not on your PATH, specify exact binary locations using environment variables in your MCP client config.

{
  "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/ffmpeg-output"
      }
    }
  }
}

FFmpeg MCP Examples

Client configuration

Standard Claude Desktop configuration for FFmpeg MCP using uvx with a custom output directory.

{
  "mcpServers": {
    "ffmpeg": {
      "command": "uvx",
      "args": ["ffmpeg-mcp-lite"],
      "env": {
        "FFMPEG_OUTPUT_DIR": "/Users/you/Downloads"
      }
    }
  }
}

Prompts to try

Use natural language to describe video and audio processing tasks to Claude once FFmpeg MCP is connected.

- "Convert /tmp/video.mp4 to WebM format"
- "Compress /tmp/large_video.mp4 to reduce its file size using the fast preset"
- "Trim /tmp/recording.mp4 from 00:01:00 to 00:02:30 and save the clip"
- "Extract the audio from /tmp/video.mp4 as an MP3 file"
- "Merge /tmp/part1.mp4 and /tmp/part2.mp4 into a single video"
- "Add subtitles from /tmp/subs.srt to /tmp/movie.mp4"

Troubleshooting FFmpeg MCP

ffmpeg command not found or binary not accessible

Install FFmpeg using your system package manager (brew install ffmpeg on macOS, apt install ffmpeg on Ubuntu). If FFmpeg is installed but not on PATH, set FFMPEG_PATH and FFPROBE_PATH environment variables in your MCP client config to the exact binary paths.

Output files are not where expected

By default, output files are saved to ~/Downloads. Set FFMPEG_OUTPUT_DIR in the env block to a specific directory. Ensure the directory exists and is writable by the process running the MCP server.

Format conversion fails with codec errors

Use ffmpeg_get_info first to inspect the source file's codec and container details. Some conversions require specific codec libraries to be compiled into your FFmpeg installation. Install FFmpeg with full codec support (brew install ffmpeg installs most codecs on macOS by default).

Frequently Asked Questions about FFmpeg MCP

What is FFmpeg MCP?

FFmpeg MCP is a Model Context Protocol (MCP) server that enables video and audio processing through ffmpeg, supporting format conversion, compression, trimming, audio extraction, frame extraction, video merging, and subtitle burning through natural language commands. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install FFmpeg MCP?

Follow the installation instructions on the FFmpeg MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with FFmpeg MCP?

FFmpeg MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is FFmpeg MCP free to use?

Yes, FFmpeg MCP is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

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.

Quick Config Preview

{ "mcpServers": { "ffmpeg-mcp": { "command": "npx", "args": ["-y", "ffmpeg-mcp"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide โ†’

Ready to use FFmpeg MCP?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides