Claude Code 的 CapCut MCP 服务器, 带有用于自动视频编辑的扩展工具、预设和参数化工作流程
概览
一个扩展的MCP(Model Context Protocol)服务器,用于通过克洛德代码将CapCut视频编辑自动化. 支持虚化打字,动画预设,并全称头部制作工作流程. 这个项目是麻省理工学院许可的@atx-guy的Capcut-mcp-server的叉和延伸. 所有原始工具都保存并扩展了: - 参数化打字系统(font,大小,位置,颜色) - 动画预设库 - 说话头制作预设 - Reels/Shorts工作流程预设 - 字幕样式系统 - Node.js 18+ - Claude代码 - CapCut (Windows 或 Mac) - C. 一个专业的模型背景协议(MCP)服务器,用于视频编辑自动化. 这个服务器使AI助手和应用程序能够通过CapCut强大的编辑能力程序化地创建和编辑视频.
概述（AI 翻译）
用于自动化的扩展的 MCP( 模式上下文协议) 服务器 CapCut视频编辑通过克洛德代码. 辅助 排版,动画预设,并有完整的谈话头制作工作流程.
□ 依据
这个项目是叉子和延伸 capcut- mcp 服务器 由麻省理工学院颁发执照的@atx-guy编写。
所有原始工具都得到保存和扩展,包括:
- 辅助打字系统(字体、大小、位置、颜色)
- 动画预设库
- 讨论头部生产预设
- 工作流程预设
- 字幕风格系统
□ 工具
- 工具 * * 描述 * *
|-|-|-.
QQ[ [T0]] 创建自定义尺寸和 fps QQ的新项目
capcut_add_video添加带有时间、过渡和速度的视频剪辑QQ [[T2] 添加带有音量和淡出效果的音频 QQ [[T3] 添加有字体、颜色和动画的有样式文字QQ QQ [ [T4]] 导入带有自定义样式的 SRT 字幕 QQcapcut_add_effect应用视觉效果 .capcut_save_draft将工程保存到 CapCut 草稿文件夹 {}capcut_talking_head完全说话的头部预设(一个命令) .
□ 要求
- 节点.js 18+
- 克劳德代码
本页由 AI 翻译，技术细节请以原文为准。
README
以下为原文 README 节选，完整内容请查看原文。
CapCut MCP Server — Extended
An extended MCP (Model Context Protocol) server for automating CapCut video editing through Claude Code. Supports parametrized typography, animation presets, and full talking-head production workflows.
Based on
This project is a fork and extension of capcut-mcp-server by @atx-guy, licensed under MIT.
All original tools have been preserved and extended with:
- Parametrized typography system (font, size, position, color)
- Animation presets library
- Talking head production preset
- Reels/Shorts workflow preset
- Subtitle style system
Tools
| Tool | Description |
|---|---|
capcut_create_draft |
Create a new project with custom dimensions and fps |
capcut_add_video |
Add video clip with timing, transitions and speed |
capcut_add_audio |
Add audio with volume and fade effects |
capcut_add_text |
Add styled text with fonts, colors and animations |
capcut_add_subtitle |
Import SRT subtitles with custom styling |
capcut_add_effect |
Apply visual effects |
capcut_save_draft |
Save project to CapCut drafts folder |
capcut_talking_head |
Full talking head preset (one command) |
Requirements
- Node.js 18+
- Claude Code
- CapCut (Windows or Mac)
Installation
git clone https://github.com/TU_USUARIO/capcut-mcp-server-pro
cd capcut-mcp-server-pro
npm install
npm run build
claude mcp add capcut -- node /ruta/dist/index.js
Usage
claude
> Crea un proyecto talking head con el video en C:/grabacion.mp4,
subtítulos en blanco, fuente Montserrat 72px, y guárdalo en CapCut
License
MIT — see LICENSE
CapCut MCP Server
A professional Model Context Protocol (MCP) server for CapCut Pro video editing automation. This server enables AI assistants and applications to create and edit videos programmatically through CapCut’s powerful editing capabilities.
🎬 Features
- Complete Video Editing Suite: Create drafts, add videos, audio, text, images, effects, and more
- Professional Tools: 11 specialized tools for video production workflows
- Type-Safe: Built with TypeScript for reliability and excellent IDE support
- Flexible Transport: Supports both stdio (local) and HTTP (remote) connections
- Input Validation: Comprehensive Zod schemas with helpful error messages
- Dual Output Formats: JSON for machines, Markdown for humans
📋 Prerequisites
Before using this MCP server, you need to have the VectCutAPI (CapCut API server) running:
-
Install VectCutAPI:
git clone https://github.com/sun-guannan/VectCutAPI.git cd VectCutAPI pip install -r requirements.txt -
Start the API Server:
python capcut_server.pyThe server will start on
http://localhost:9001by default.
🚀 Installation
Option 1: Install from npm (once published)
安装
This server does not publish a one-line install command.
Open the repository installation guide 新手？先看 mcpskill.org 教程 →配置
{
"mcpServers": {
"capcut": {
"command": "node",
"args": ["/absolute/path/to/capcut-mcp-server/dist/index.js"],
"env": {
"CAPCUT_API_URL": "http://localhost:9001"
}
}
}
}