VectCutAPI Video Editing

What it does

When your agent uses it

• Building a short video draft programmatically for CapCut or JianYing
• Adding subtitles from an SRT file to a draft
• Batch-producing videos from a spreadsheet of inputs
• Giving an agent MCP tools for video editing

Example prompts

• “Create a vertical CapCut draft with this video clip and add the subtitles from ./captions/intro.srt.”
• “Add a dissolve transition between the two clips in my draft and give me the preview URL.”
• “Produce a video for each row in ./batch/products.xlsx.”
• “Set up the VectCutAPI MCP server so my agent can edit drafts.”

Requirements

• Python 3.10 or later
• CapCut (international) or JianYing installed
• FFmpeg for some video processing (optional)

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1双协议支持 - HTTP REST API 和 MCP 协议
2. 2实时预览 - 网页预览无需下载
3. 3可二次编辑 - 导入剪映/CapCut 精修
4. 4云端处理 - 全云端操作生成视频

What it can do on your machine

Read from SKILL.md and the folder at commit cfa4779. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • pip
  • python

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • capcutapi.top

  Also links to:

  • vectcut.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

VectCutAPI Video Editing loads about 2.1k tokens when it runs, and up to ~9.2k if it reads all its reference files. Until then it costs about 177 tokens; SKILL.md has 392 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~177

When it runs · the whole SKILL.md, loaded when a task matches

~2.1k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~9.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from sun-guannan/VectCutAPI at commit cfa4779, republished under its Apache-2.0 licence (© sun-guannan). 392 words, ~2,105 tokens.

name

vectcut-api

description

VectCutAPI is a powerful cloud-based video editing API tool that provides programmatic control over CapCut/JianYing (剪映) for professional video editing. Use this skill when users need to: (1) Create video draft projects programmatically, (2) Add video/audio/image materials with precise control, (3) Add text, subtitles, and captions, (4) Apply effects, transitions, and animations, (5) Add keyframe animations, (6) Process videos in batch, (7) Generate AI-powered videos, (8) Integrate with n8n workflows, (9) Build MCP video editing agents. The API supports HTTP REST and MCP protocols, works with both CapCut (international) and JianYing (China), and provides web preview without downloading.

# 安装依赖
pip install -r requirements.txt      # HTTP API 基础依赖
pip install -r requirements-mcp.txt  # MCP 协议支持 (可选)

# 配置文件
cp config.json.example config.json

# 启动服务
python capcut_server.py  # HTTP API 服务器 (端口: 9001)
python mcp_server.py     # MCP 协议服务器

1. 创建草稿 (create_draft)
   - 设置分辨率: 1080x1920 (竖屏) / 1920x1080 (横屏) / 1080x1080 (方形)
   - 获取 draft_id

2. 添加素材轨道
   - add_video: 添加视频轨道
   - add_audio: 添加音频轨道
   - add_image: 添加图片素材

3. 添加文字元素
   - add_text: 添加标题、说明文字
   - add_subtitle: 导入 SRT 字幕文件

4. 应用特效
   - add_effect: 添加视频特效
   - add_sticker: 添加贴纸素材
   - add_video_keyframe: 添加关键帧动画

5. 保存草稿
   - save_draft: 生成可导入剪映的草稿文件

AI 文案生成
    ↓
TTS 文字转语音 → audio_url
    ↓
图生视频 → video_url
    ↓
VectCutAPI 组合草稿
    ↓
导出或二次编辑

import requests

# 1. 创建草稿
response = requests.post("http://localhost:9001/create_draft", json={
    "width": 1080,
    "height": 1920
})
draft_id = response.json()["output"]["draft_id"]

# 2. 添加背景视频
requests.post("http://localhost:9001/add_video", json={
    "draft_id": draft_id,
    "video_url": "https://example.com/background.mp4",
    "start": 0,
    "end": 10,
    "volume": 0.6
})

# 3. 添加标题文字
requests.post("http://localhost:9001/add_text", json={
    "draft_id": draft_id,
    "text": "欢迎使用 VectCutAPI",
    "start": 1,
    "end": 5,
    "font_size": 56,
    "font_color": "#FFD700",
    "shadow_enabled": True,
    "background_color": "#000000"
})

# 4. 保存草稿
response = requests.post("http://localhost:9001/save_draft", json={
    "draft_id": draft_id
})
draft_url = response.json()["output"]["draft_url"]
print(f"草稿已保存: {draft_url}")

requests.post("http://localhost:9001/add_video", json={
    "draft_id": draft_id,
    "video_url": "https://example.com/video2.mp4",
    "transition": "fade_in",           # 转场类型
    "transition_duration": 0.5,        # 转场时长(秒)
    "target_start": 10                 # 在时间轴 10 秒处开始
})

requests.post("http://localhost:9001/add_video_keyframe", json={
    "draft_id": draft_id,
    "track_name": "video_main",
    "property_types": ["scale_x", "scale_y", "alpha"],
    "times": [0, 2, 4],          # 关键帧时间点
    "values": ["1.0", "1.2", "0.8"]  # 对应属性值
})

requests.post("http://localhost:9001/add_subtitle", json={
    "draft_id": draft_id,
    "srt_url": "https://example.com/subtitles.srt",
    "font_size": 32,
    "font_color": "#FFFFFF",
    "background_alpha": 0.7
})

{
  "mcpServers": {
    "vectcut-api": {
      "command": "python",
      "args": ["mcp_server.py"],
      "cwd": "H:/ComfyUI/web/VectCutAPI",
      "env": {
        "PYTHONPATH": "H:/ComfyUI/web/VectCutAPI",
        "DEBUG": "0"
      }
    }
  }
}

"text_styles": [
    {"start": 0, "end": 2, "font_color": "#FF6B6B"},
    {"start": 2, "end": 4, "font_color": "#4ECDC4"},
    {"start": 4, "end": 6, "font_color": "#45B7D1"}
]

{
  "is_capcut_env": true,
  "draft_domain": "https://www.capcutapi.top",
  "port": 9001,
  "preview_router": "/draft/downloader",
  "is_upload_draft": false,
  "oss_config": {
    "bucket_name": "your-bucket",
    "access_key_id": "your-key-id",
    "access_key_secret": "your-secret",
    "endpoint": "https://your-endpoint.aliyuncs.com"
  }
}

python auto_video_editor.py input.xlsx

© sun-guannan, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts, references) in vectcut-skill/skill of sun-guannan/VectCutAPI.

• SKILL.md
• references/api_reference.md
• references/workflows.md
• scripts/vectcut_client.py

Open the folder on GitHubat commit cfa4779