MCP FFmpeg Video Processor
MCP FFmpeg 视频处理器
一个使用 FFmpeg 处理视频文件的 Node.js 服务器。此服务器提供以下 API:
将视频调整为不同的分辨率(360p、480p、720p、1080p)
从各种格式的视频中提取音频(MP3、AAC、WAV、OGG)
先决条件
在运行此应用程序之前,您需要安装以下内容:
Node.js (v14 或更高版本)
**FFmpeg——**视频处理需要它
安装 FFmpeg
在 macOS 上:
brew install ffmpeg在 Ubuntu/Debian 上:
sudo apt update
sudo apt install ffmpeg在 Windows 上:
从官方网站下载FFmpeg
将文件解压到文件夹(例如,
C:\ffmpeg)将
bin文件夹添加到 PATH 环境变量中
Related MCP server: mcp-ffmpeg
安装
克隆此存储库:
git clone https://github.com/bitscorp-mcp/mcp-ffmpeg.git
cd mcp-ffmpeg安装依赖项:
npm install通过 Smithery 安装
要通过Smithery自动为 Claude Desktop 安装 mcp-ffmpeg:
npx -y @smithery/cli install @bitscorp-mcp/mcp-ffmpeg --client claude运行服务器
使用以下命令启动服务器:
npm start对于文件更改时自动重启的开发:
npm run dev通过 Smithery 安装
要通过Smithery自动为 Claude Desktop 安装 mcp-ffmpeg:
npx -y @smithery/cli install @bitscorp-mcp/mcp-ffmpeg --client claude要为 Cursor 安装 mcp-ffmpeg,请转至“设置”->“Cursor 设置”->“功能”->“MCP 服务器”->“+ 添加”
选择类型:命令并粘贴以下内容,使用来自 Adjust 的 API 密钥
npx -y @smithery/cli@latest run @bitscorp/mcp-ffmpeg与 Claude Desktop 一起使用
该 MCP FFmpeg 服务器可以与 Claude Desktop 集成,通过自然语言请求处理视频。
使用 npx 运行
您可以直接使用 npx 运行服务器:
npx /path/to/mcp-ffmpeg或者如果你已经将包发布到 npm:
npx mcp-ffmpeg配置 Claude 桌面
要将此服务器添加到 Claude Desktop,请更新您的 Claude Desktop 配置文件:
找到您的 Claude Desktop 配置文件:
macOS:
~/.config/claude-desktop/config.json或~/Library/Application Support/Claude Desktop/config.jsonWindows:
%APPDATA%\Claude Desktop\config.jsonLinux:
~/.config/claude-desktop/config.json
将 FFmpeg MCP 服务器添加到
mcpServers部分:
{
"mcpServers": {
"ffmpeg": {
"command": "npx",
"args": [
"--yes",
"/absolute/path/to/mcp-ffmpeg"
]
}
}
}如果您已将软件包发布到 npm:
{
"mcpServers": {
"ffmpeg": {
"command": "npx",
"args": [
"--yes",
"mcp-ffmpeg"
]
}
}
}重新启动 Claude Desktop 以使更改生效。
克劳德的示例提示
配置完成后,您可以使用如下提示:
Using the ffmpeg MCP server, please resize the video at /path/to/video.mp4 to 720p resolution.笔记
上传的视频暂时存储在
uploads目录中处理后的视频和音频文件存储在
output目录中服务器上传文件大小限制为 500MB
执照
麻省理工学院
Available Tools
4 toolsextract-audioC
Extract audio from a video file
Inputs: videoPath (required), format, outputDir.
get-ffmpeg-versionA
Get the version of FFmpeg installed on the system
Inputs: no named parameters.
get-video-infoC
Get detailed information about a video file
Inputs: videoPath (required).
resize-videoB
Resize a video to one or more standard resolutions
Inputs: videoPath (required), resolutions (required), outputDir.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: extract-audio handles audio extraction, get-ffmpeg-version checks system version, get-video-info provides metadata, and resize-video adjusts video dimensions. There is no overlap in functionality, making tool selection unambiguous.
The tools follow a consistent verb-noun pattern with hyphens (e.g., extract-audio, resize-video), except for get-ffmpeg-version which includes an extra noun. This minor deviation does not significantly impact readability or predictability.
With only 4 tools, the set feels thin for a video processing domain. While the tools cover basic operations, there are likely gaps for common tasks like format conversion, trimming, or adding effects, which might limit agent effectiveness.
The tool set is severely incomplete for video processing. It lacks essential operations such as format conversion, trimming/cutting, merging videos, adding subtitles, or applying filters. This will cause frequent agent failures when handling typical video editing workflows.
Maintenance
Related MCP Connectors
Transform video, audio and images, and generate media from prompts. FFmpeg, captions, models.
Video, audio, and image processing for AI agents: convert, transcribe, upscale - 150+ operations.
FFmpeg as a service for AI agents: typed video editing tools, async jobs, downloadable outputs.
FFmpeg Micro - The FFmpeg Api - www.ffmpeg-micro.com Transcode videos from n8n or Make using FFmpeg in the cloud. MCP Server: https://github.com/ffmpeg-micro/ffmpeg-micro-mcp/
Related MCP Servers
- AlicenseBqualityDmaintenanceA Node.js server that provides advanced video and image processing capabilities through the Model Context Protocol, enabling operations like conversion, compression, editing, and effects application.1019 npm29ISC
- AlicenseAqualityDmaintenanceA job queue-based FFmpeg wrapper enabling AI assistants to perform video processing tasks such as trimming, format conversion, resolution change, and subtitle conversion through natural language.8MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server for programmatic video editing using ffmpeg, enabling draft creation and refinement via natural language.6 npmISC
- FlicenseNot gradedqualityDmaintenanceAn MCP server that enables natural language video editing using FFmpeg, supporting operations like trimming, merging, format conversion, and more with real-time progress tracking.-