FFmpeg MCP Server
Enables secure video and audio processing using FFmpeg commands in an isolated sandbox environment. Supports file management, Google Cloud Storage integration, and URL-based file transfers for AI-powered multimedia operations.
What is FFmpeg MCP Server?
FFmpeg MCP Server is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables secure video and audio processing using ffmpeg commands in an isolated sandbox environment. supports file management, google cloud storage integration, and url-based file transfers for ai-powe...
Enables secure video and audio processing using FFmpeg commands in an isolated sandbox environment. Supports file management, Google Cloud Storage integration, and URL-based file transfers for AI-powered multimedia operations.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Enables secure video and audio processing using FFmpeg comma
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx ffmpeg-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use FFmpeg MCP Server
FFmpeg MCP Server is a Python-based MCP server that exposes secure, sandboxed FFmpeg video and audio processing operations to AI agents, running on macOS (ARM64 and x86_64). It provides eight tools covering video metadata retrieval, clipping, concatenation, overlay compositing, scaling, frame extraction, and playback — all executable through natural language in Claude or other MCP-compatible clients. Media creators and developers use it to drive complex multimedia processing pipelines through conversation without manually constructing FFmpeg command strings.
Prerequisites
- macOS (ARM64 or x86_64) — Linux/Windows are not currently supported
- FFmpeg installed and available on PATH (brew install ffmpeg on macOS)
- Python 3.10+ and uv package manager (pip install uv or brew install uv)
- An MCP-compatible client such as Claude Desktop or Cline in VS Code
Clone the repository
Clone the ffmpeg-mcp repository to your local machine.
git clone https://github.com/video-creator/ffmpeg-mcp.git
cd ffmpeg-mcpInstall Python dependencies with uv
Use uv to sync the project's dependencies into an isolated virtual environment.
uv syncVerify FFmpeg is installed
Confirm ffmpeg is available on your PATH before configuring the MCP server.
ffmpeg -versionAdd the server to your MCP client configuration
Add the ffmpeg-mcp server entry to your MCP client config. Replace the path with your actual installation directory. The timeout is set to 60 seconds to accommodate long encoding operations.
{
"mcpServers": {
"ffmpeg-mcp": {
"command": "uv",
"args": [
"--directory",
"/path/to/ffmpeg-mcp",
"run",
"ffmpeg-mcp"
],
"timeout": 60000
}
}
}Restart your MCP client and verify
Restart Claude Desktop or your Cline session. Ask Claude to find a video file or get info about a media file to confirm the eight tools are active.
FFmpeg MCP Server Examples
Client configuration
MCP client configuration for the FFmpeg MCP Server using uv as the runner.
{
"mcpServers": {
"ffmpeg-mcp": {
"command": "uv",
"args": [
"--directory",
"/path/to/ffmpeg-mcp",
"run",
"ffmpeg-mcp"
],
"timeout": 60000
}
}
}Prompts to try
Natural language prompts mapping to the eight tools this server exposes.
- "Find the video file named 'interview.mp4' in my Downloads folder"
- "Get the duration, resolution, and codec of /Users/me/Videos/clip.mp4"
- "Clip /Users/me/Videos/long-video.mp4 from 00:01:30 to 00:02:45 and save it as output.mp4"
- "Merge these two videos in order: intro.mp4 and main.mp4"
- "Scale /Users/me/Videos/4k-clip.mp4 to 1920x1080"
- "Extract one frame per second from video.mp4 as PNG images"
- "Overlay watermark.mp4 on top of base.mp4 at position top-right"Troubleshooting FFmpeg MCP Server
ffmpeg command not found when running tools
Install FFmpeg: 'brew install ffmpeg' on macOS. Confirm it is on your PATH by running 'which ffmpeg'. If Claude Desktop launches with a restricted PATH, add the full FFmpeg path to the env block in your MCP config: {"PATH": "/opt/homebrew/bin:/usr/local/bin:/usr/bin"}.
uv: command not found when starting the server
Install uv: 'curl -Ls https://astral.sh/uv/install.sh | sh' or 'brew install uv'. Confirm with 'which uv'. Use the full path to the uv binary in your MCP config args if needed.
Video operations time out for large files
Increase the timeout value in your MCP config from 60000 to 120000 or higher (milliseconds). Large file encoding and concatenation operations can take several minutes depending on file size and codec.
Frequently Asked Questions about FFmpeg MCP Server
What is FFmpeg MCP Server?
FFmpeg MCP Server is a Model Context Protocol (MCP) server that enables secure video and audio processing using ffmpeg commands in an isolated sandbox environment. supports file management, google cloud storage integration, and url-based file transfers for ai-powered multimedia operations. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install FFmpeg MCP Server?
Follow the installation instructions on the FFmpeg MCP Server GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with FFmpeg MCP Server?
FFmpeg MCP Server works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is FFmpeg MCP Server free to use?
Yes, FFmpeg MCP Server is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
FFmpeg MCP Server Alternatives — Similar Cloud Services Servers
Looking for alternatives to FFmpeg MCP Server? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up FFmpeg MCP Server 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 Server?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.