What are the prerequisites for running mcp-ffmpeg?
You need Node.js version 14 or higher and FFmpeg installed on your system.
@bitscorp-mcp
基本信息
mcp-ffmpeg: resize videos, extract audio.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"ffmpeg": {
"command": "npx",
"args": [
"--yes",
"mcp-ffmpeg"
]
}
}
}Get the version of FFmpeg installed on the system
Resize a video to one or more standard resolutions
Extract audio from a video file
Get detailed information about a video file
mcp-ffmpeg is a Node.js server that uses FFmpeg to manipulate video files. It provides APIs to resize videos to different resolutions (360p, 480p, 720p, 1080p) and extract audio in MP3, AAC, WAV, and OGG formats. This server is designed for users who want to process videos through an MCP-compatible client, such as Claude Desktop.
Install Node.js (v14+) and FFmpeg on your system. Clone the repository, run npm install, then start the server with npm start. Alternatively, run directly with npx /path/to/mcp-ffmpeg. For integration with Claude Desktop, add the server to your Claude Desktop config file under mcpServers using the npx command. Once configured, use natural language prompts like "resize the video at /path/to/video.mp4 to 720p resolution".
uploads and output directoriesYou need Node.js version 14 or higher and FFmpeg installed on your system.
On macOS, run `brew install ffmpeg`. On Ubuntu/Debian, run `sudo apt update && sudo apt install ffmpeg`. On Windows, download FFmpeg from the official website, extract it to a folder (e.g., `C:\ffmpeg`), and add the `bin` folder to your PATH.
Locate your Claude Desktop config file (macOS: `~/.config/claude-desktop/config.json`, Windows: `%APPDATA%\Claude Desktop\config.json`, Linux: `~/.config/claude-desktop/config.json`). Add the server under `mcpServers` with `"command": "npx"` and `"args": ["--yes", "/absolute/path/to/mcp-ffmpeg"]`. Restart Claude Desktop.
The server has a file size limit of 500 MB for uploads.
Uploaded files are temporarily stored in the `uploads` directory, and processed files are saved in the `output` directory.
Hindsight: Agent Memory That Learns
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
Painless E2E Automation for Mobile and Web

Health by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one
评论