CapCutAPI-Complete MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@CapCutAPI-Complete MCP Serveradd text overlay to my video at 5 seconds"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
CapCutAPI-Complete
🎬 CapCut API 完整版 - 功能强大的视频编辑API服务,基于剪映(CapCut/JianYing)核心功能实现
🚀 项目简介
CapCutAPI-Complete 是一个基于 Python 的完整视频编辑API服务,提供与剪映(CapCut/JianYing)类似的核心功能。通过HTTP API和MCP协议接口,您可以轻松实现:
🎞️ 视频剪辑和合并
🎵 音频处理和混音
📝 文字和字幕添加
✨ 特效和转场效果
🖼️ 贴纸和装饰元素
📦 批量处理和自动化
Related MCP server: CapCut MCP Server
✨ 核心特性
🎯 视频处理
多轨道编辑:支持无限视频轨道
格式转换:支持MP4、AVI、MOV、MKV等主流格式
分辨率适配:自动适配1080P、4K等分辨率
帧率转换:24fps、30fps、60fps无缝切换
视频压缩:智能压缩保持画质
🎵 音频处理
音频提取:从视频中提取音频轨道
音量调节:精确到毫秒级的音量控制
淡入淡出:平滑的音频过渡效果
音频混合:多轨道音频混音
格式支持:MP3、WAV、AAC、FLAC等
📝 文字和字幕
动态字幕:支持SRT、ASS字幕格式
字体样式:丰富的字体和样式选项
动画效果:文字入场和出场动画
实时预览:即时查看字幕效果
多语言支持:中英文等多语言字幕
✨ 特效和滤镜
转场效果:100+种专业转场
视觉滤镜:电影级调色滤镜
动态特效:粒子、光效、模糊等
自定义特效:支持自定义特效参数
预设模板:一键应用专业模板
🖼️ 贴纸和装饰
静态贴纸:PNG、JPG、SVG格式支持
动态贴纸:GIF和WebP动画贴纸
自定义贴纸:支持用户上传自定义贴纸
位置控制:精确的位置和大小调整
层级管理:灵活的图层顺序控制
🏗️ 架构设计
CapCutAPI-Complete/
├── capcut_server.py # HTTP API服务器
├── mcp_server.py # MCP协议服务器
├── create_draft.py # 草稿管理
├── add_video_track.py # 视频轨道管理
├── add_audio_track.py # 音频轨道管理
├── add_text.py # 文字和字幕管理
├── add_effects.py # 特效和滤镜管理
├── add_stickers.py # 贴纸和装饰管理
├── video_utils.py # 视频处理工具
├── audio_utils.py # 音频处理工具
├── image_utils.py # 图像处理工具
├── utils.py # 通用工具函数
├── Dockerfile # Docker容器配置
├── docker-compose.yml # 多服务编排
└── requirements.txt # 依赖包列表🚀 快速开始
📋 系统要求
Python: 3.8 或更高版本
FFmpeg: 最新版本
操作系统: Windows 10+/macOS 10.14+/Ubuntu 18.04+
内存: 最少4GB RAM(推荐8GB+)
存储: 至少10GB可用空间
🔧 安装步骤
1. 克隆项目
git clone https://github.com/chenzhaohua11/CapCutAPI-Complete.git
cd CapCutAPI-Complete2. 安装依赖
# 创建虚拟环境
python -m venv venv
source venv/bin/activate # Linux/macOS
# 或
venv\Scripts\activate # Windows
# 安装依赖
pip install -r requirements.txt3. 安装FFmpeg
Ubuntu/Debian:
sudo apt update
sudo apt install ffmpegmacOS:
brew install ffmpegWindows:
解压并添加到系统PATH
4. 启动服务
# 启动HTTP API服务器
python capcut_server.py
# 启动MCP服务器
python mcp_server.py🐳 Docker部署
1. 使用Docker Compose
# 启动所有服务
docker-compose up -d
# 查看服务状态
docker-compose ps
# 查看日志
docker-compose logs -f capcut-api2. 单独构建镜像
# 构建镜像
docker build -t capcut-api .
# 运行容器
docker run -p 5000:5000 -v $(pwd)/data:/app/data capcut-api📖 API使用指南
🌐 HTTP API接口
创建项目草稿
curl -X POST http://localhost:5000/create_draft \
-H "Content-Type: application/json" \
-d '{
"name": "我的第一个项目",
"resolution": "1920x1080",
"fps": 30,
"duration": 60
}'添加视频
curl -X POST http://localhost:5000/add_video \
-H "Content-Type: application/json" \
-d '{
"draft_id": "draft_123456",
"video_url": "https://example.com/video.mp4",
"start_time": 0,
"duration": 10,
"position": {"x": 0, "y": 0},
"size": {"width": 1920, "height": 1080}
}'添加音频
curl -X POST http://localhost:5000/add_audio \
-H "Content-Type: application/json" \
-d '{
"draft_id": "draft_123456",
"audio_url": "https://example.com/audio.mp3",
"start_time": 0,
"duration": 10,
"volume": 0.8
}'添加文字
curl -X POST http://localhost:5000/add_text \
-H "Content-Type: application/json" \
-d '{
"draft_id": "draft_123456",
"content": "Hello, CapCut API!",
"start_time": 2,
"duration": 5,
"position": {"x": 100, "y": 100},
"font_size": 48,
"color": "#FFFFFF"
}'添加特效
curl -X POST http://localhost:5000/add_effect \
-H "Content-Type: application/json" \
-d '{
"draft_id": "draft_123456",
"effect_type": "fade_in",
"start_time": 0,
"duration": 2,
"intensity": 0.8
}'导出视频
curl -X POST http://localhost:5000/export_video \
-H "Content-Type: application/json" \
-d '{
"draft_id": "draft_123456",
"format": "mp4",
"quality": "high",
"fps": 30
}'🔌 MCP协议接口
MCP (Media Control Protocol) 提供更高性能的接口:
from mcp_client import MCPClient
client = MCPClient("localhost", 5001)
# 创建项目
draft = client.create_draft(
name="MCP项目",
resolution="1920x1080",
fps=30
)
# 添加媒体
video_id = client.add_video(draft.id, "video.mp4")
audio_id = client.add_audio(draft.id, "audio.mp3")
text_id = client.add_text(draft.id, "Hello World")
# 应用特效
client.add_transition(video_id, "fade_in")
client.add_filter(video_id, "vintage")
# 导出结果
output_path = client.export(draft.id, "final_video.mp4")📁 项目结构
CapCutAPI-Complete/
├── 📁 项目根目录
├── 📁 data/ # 数据存储目录
│ ├── 📁 uploads/ # 上传文件
│ ├── 📁 drafts/ # 项目草稿
│ ├── 📁 exports/ # 导出文件
│ └── 📁 cache/ # 缓存文件
├── 📁 templates/ # 模板文件
├── 📁 config/ # 配置文件
├── 📁 logs/ # 日志文件
├── 📁 tests/ # 测试文件
└── 📁 docs/ # 文档文件📞 联系方式
项目维护者: chenzhaohua11
邮箱: 863654981@qq.com
GitHub: chenzhaohua11
项目地址: CapCutAPI-Complete
This server cannot be deployed
Maintenance
Related MCP Connectors
AI video editor for agents and humans: timeline, captions, color, audio and generation as MCP tools.
Trim, watermark, extract audio, and convert video to 9:16 vertical via API or MCP server.
- CueFrameOAuthai.cueframe
Compose, edit and render video with your AI agent. Turn footage into finished edits with content-aware reframing, word-timed captions and motion graphics. Hosted MCP with OAuth sign-in; cloud processing uses credits.
Build, run, schedule, and publish AI video pipelines to YouTube and TikTok from any MCP client.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI models to fully automate and control the OpenCut Video Editor through a comprehensive set of MCP tools for timeline manipulation, scene management, media handling, and rendering.37 npm8MIT
- AlicenseAqualityDmaintenanceEnables AI assistants to fully control CapCut video editing projects, including creating projects, importing media, adding text/subtitles, managing audio, and editing timelines.251MIT
- FlicenseNot gradedqualityFmaintenanceAutomates CapCut video editing through an HTTP/MCP API, enabling draft creation, material addition (video, audio, text, images), effects, and AI-powered enhancements via natural language.95-
- AlicenseNot gradedqualityAmaintenanceEnables AI agents and MCP clients to programmatically edit video projects on a local desktop editor, with 119 tools for multitrack editing, effects, captions, audio, and batch auto-editing, producing reviewable and reversible real timeline edits.AGPL 3.0