npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@idk500/video-vision-mcp

v1.2.0

Published

Video MCP server with AI vision analysis using OpenAI-compatible endpoints (default: Zhipu Bigmodel glm-4.6v-flash)

Downloads

48

Readme

🎬 Video Vision MCP

License: MIT Node.js Version TypeScript

🚀 基于 Model Context Protocol (MCP) 的视频分析与拍摄脚本生成工具,使用 OpenAI 兼容的多模态视觉模型(默认:智谱 Bigmodel glm-4.6v-flash,免费可用)

✨ 简介

Video Vision MCP 是一个专业的视频分析和脚本生成工具,通过 MCP 协议为 AI 助手提供强大的视频处理能力。它可以从视频中提取关键帧,使用多模态视觉模型进行智能内容分析,并生成专业的拍摄脚本。

Fork 自 pickstar-2002/video-capture-script-mcp,主要改动:将视觉后端从腾讯混元替换为 OpenAI 兼容接口(默认智谱 Bigmodel glm-4.6v-flash,免费可用),无需腾讯云密钥。感谢原作者的开源贡献。

🎯 主要功能

  • 🖼️ 智能帧提取: 支持多种策略提取视频关键帧
    • 均匀间隔提取 (uniform)
    • 关键帧提取 (keyframe)
    • 场景变化检测 (scene_change)
  • 🤖 AI 内容分析: 使用多模态视觉模型分析视频/图片内容
  • 🎬 拍摄脚本生成: 基于视频分析结果,生成专业拍摄脚本
    • 支持多种类型:商业广告、纪录片、教学视频、叙事视频
    • 可自定义目标受众、拍摄风格、时长要求
  • 📊 批量图片分析: 批量分析多张图片内容
  • 📹 视频信息获取: 获取视频时长、分辨率、帧率等元数据

📦 安装

在 MCP 兼容工具中配置

{
  "mcpServers": {
    "video-vision-mcp": {
      "command": "npx",
      "args": ["-y", "@idk500/video-vision-mcp@latest"],
      "env": {
        "VISION_API_KEY": "your_api_key_here"
      }
    }
  }
}

本地开发

git clone https://github.com/idk500/video-capture-script-mcp.git
cd video-capture-script-mcp
npm install
npm run build

🔑 配置(视觉模型 API Key)

视觉分析功能需要一个支持图片输入的多模态模型 API Key。默认使用智谱 Bigmodel glm-4.6v-flash(免费)

获取 Key

  1. 访问 https://open.bigmodel.cn/usercenter/apikeys
  2. 注册/登录智谱开放平台
  3. 创建 API Key(格式:xxxxxxxxxxxxxxxx.xxxxxxxxxxxxxxxx

配置方式(任选其一)

环境变量(推荐):

export VISION_API_KEY=your_api_key_here
# 可选:自定义端点和模型
export VISION_ENDPOINT=https://open.bigmodel.cn/api/paas/v4
export VISION_MODEL=glm-4.6v-flash
export TEXT_MODEL=glm-4.6

启动参数:

node dist/index.js --secret-id your_api_key_here

切换其他 OpenAI 兼容后端

只要接口兼容 OpenAI Chat Completions(支持 image_url 内容),都可以用:

export VISION_ENDPOINT=https://your-openai-compatible-endpoint/v1
export VISION_MODEL=your-vision-model
export TEXT_MODEL=your-text-model
export VISION_API_KEY=your-key

🛠️ 可用工具

| 工具 | 说明 | 需要视觉模型 | |------|------|:---:| | extract_video_frames | 从视频提取关键帧(本地,依赖 FFmpeg) | 否 | | get_video_info | 获取视频时长/分辨率/帧率等元信息 | 否 | | analyze_video_content | 抽帧后送入视觉模型,总结视频内容 | 是 | | analyze_image_batch | 批量分析图片内容 | 是 | | generate_video_script | 抽帧→视觉理解→生成专业拍摄脚本 | 是 | | generate_image_script | 基于多张图片生成拍摄脚本 | 是 |

脚本类型commercial(商业广告)/ documentary(纪录片)/ tutorial(教学)/ narrative(叙事)/ custom(自定义)

📋 系统要求与依赖

  • Node.js >= 18.0.0
  • FFmpeg(帧提取与视频信息)
    • Windows: choco install ffmpeg
    • macOS: brew install ffmpeg
    • Linux: sudo apt install ffmpeg

📝 开发

npm run dev      # 开发模式(tsx)
npm run build    # 编译到 dist/
npm run lint     # 代码检查

📄 许可证

MIT License

Copyright (c) 2025 pickstar-2002(原作者) Copyright (c) 2025 idk500(Bigmodel 后端改造)

🙏 致谢

本项目 Fork 自 pickstar-2002/video-capture-script-mcp,感谢原作者的完整实现。Fork 改动点:将腾讯混元视觉后端替换为 OpenAI 兼容接口(默认智谱 Bigmodel glm-4.6v-flash)。

🐛 问题反馈

请在 GitHub Issues 中反馈问题或建议。