freemcplab / 目录 / 演练场 / Claude Video Vision

● 社区 jordanrendric ⚡ 即开即用

Claude Video Vision

Name: Claude Video Vision (Claude Skill)
Author: jordanrendric

作者 jordanrendric · jordanrendric/claude-video-vision

Make Claude actually understand a video — frames + transcript + scene segmentation, fed in a token-efficient layout.

The skill takes a video file or URL, extracts keyframes (scene-aware), aligns transcript segments, and presents the bundle to Claude for QA, summary, or content extraction. Smart-sampling avoids blowing the context window.

▶ 观看演示 📦 安装 💡 使用场景

为什么要用

核心特性

Scene-aware keyframe extraction
Whisper-quality transcript alignment
Per-scene token budget
Works with local files or YouTube URLs
Output: structured JSON for downstream skills

实时演示

实际使用效果

就绪

安装

选择你的客户端

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "claude-video-vision": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/jordanrendric/claude-video-vision"
      ],
      "_inferred": true
    }
  }
}

打开 Claude Desktop → Settings → Developer → Edit Config。保存后重启应用。

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "claude-video-vision": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/jordanrendric/claude-video-vision"
      ],
      "_inferred": true
    }
  }
}

Cursor 使用与 Claude Desktop 相同的 mcpServers 格式。项目级配置优先于全局。

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "claude-video-vision": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/jordanrendric/claude-video-vision"
      ],
      "_inferred": true
    }
  }
}

点击 Cline 侧栏中的 MCP Servers 图标，然后选 "Edit Configuration"。

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "claude-video-vision": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/jordanrendric/claude-video-vision"
      ],
      "_inferred": true
    }
  }
}

格式与 Claude Desktop 相同。重启 Windsurf 生效。

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "claude-video-vision",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/jordanrendric/claude-video-vision"
      ]
    }
  ]
}

Continue 使用服务器对象数组，而非映射。

~/.config/zed/settings.json

{
  "context_servers": {
    "claude-video-vision": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/jordanrendric/claude-video-vision"
        ]
      }
    }
  }
}

加入 context_servers。Zed 保存后热重载。

claude mcp add claude-video-vision -- git clone https://github.com/jordanrendric/claude-video-vision

一行命令搞定。用 claude mcp list 验证，claude mcp remove 卸载。

使用场景

实战用法： Claude Video Vision

Answer questions about a 30-min talk

👤 Claude Code users ⏱ ~15 min intermediate

何时使用： Conference talk just dropped; you want notes without watching it.

步骤

Ingest

Point skill at the URL.✓ 已复制

→ Frames + transcript ready
Ask

Ask focused questions; skill scopes to relevant scenes.✓ 已复制

→ Precise answers with timestamps

结果： Targeted understanding without re-watching.

组合

与其他 MCP 搭配，撬动十倍杠杆

claude-video-vision + filesystem

Save the structured note output for later reference

Combine claude-video-vision with filesystem: Save the structured note output for later reference✓ 已复制

工具

此 MCP 暴露的能力

工具	输入参数	何时调用	成本
ingest	(see docs)	Pull video + transcript	1 call
query	(see docs)	Scope-aware question answering	1 call

成本与限制

运行它的成本

API 配额: Bound by transcription cost
每次调用 Token 数: Mid (sampled, not full video)
费用: Free skill; transcription/model costs
提示: Use shorter scenes when QA is targeted; use long-window mode for summary

安全

权限、密钥、影响范围

最小权限： fs-read fs-write

凭据存储： API keys for transcription provider in env

数据出站： Transcription provider

切勿授予： process private video without consent

故障排查

常见错误与修复

Transcript misaligned

Lower scene-segmentation threshold; transcript may be off due to music

替代方案