remotion-mcp-server

remotion-mcp-server

Enables Claude to analyze reference videos (download, transcripts, frames) and generate new branded Instagram Reels/YouTube Shorts as React/TSX compositions, rendered to MP4 via Remotion.

Category
访问服务器

README

remotion-mcp-server

An MCP (Model Context Protocol) server that gives Claude the ability to analyze reference videos and generate branded Instagram Reels / YouTube Shorts using Remotion (React-based programmatic video) — entirely from a chat conversation.

Point Claude at a reference reel, and it can:

  1. Download it (yt-dlp), pull out frames + audio, and get a full transcript (YouTube captions first, faster-whisper fallback for everything else — Instagram, TikTok, local files).
  2. Generate a new composition in the same style — dialogue-bubble reels or fact/listicle reels — as real React/TSX code.
  3. Render it to MP4 with Remotion.
  4. Tell you how to open it in Remotion Studio to scrub and review before you call it final.

No CapCut, no manual editing — Claude writes the video.

Tools

Tool What it does
analyze_video(url) Downloads a reference video from YouTube/Instagram/Facebook/direct URL. Extracts frames at 0.5fps, audio, duration, and a full transcript (captions or Whisper).
create_dialogue_reel(...) Generates an animated speaker-bubble dialogue reel (Remotion TSX) and renders it to MP4.
create_facts_reel(...) Generates a facts/listicle-style reel with animated bullet points and renders it to MP4.
render_composition(id) Re-renders any existing composition in the project.
list_outputs() Lists rendered MP4s in the output folder.

Both create_* tools return a preview hint telling Claude/you how to open the composition in Remotion Studio (npm run dev → localhost:3000) before treating the render as final.

Setup

1. Clone and install Python deps

git clone https://github.com/<your-username>/remotion-mcp-server.git
cd remotion-mcp-server
pip install -r requirements.txt

You'll also need ffmpeg on your PATH (or install imageio-ffmpeg, which the server falls back to automatically).

2. Set up the Remotion project

This server needs a Remotion project to write generated compositions into and render from. A ready-to-use starter is included:

cd remotion-template
npm install
cd ..

Or point REMOTION_MCP_PROJECT at your own existing Remotion project — it just needs the two marker comments from remotion-template/src/Root.tsx present in its Root.tsx.

3. Configure (optional)

Copy .env.example to .env and adjust if you're not using the defaults (custom yt-dlp/ffmpeg paths, a different project folder, a default watermark).

4. Register with Claude

Add to your Claude Desktop / Claude Code MCP config:

{
  "mcpServers": {
    "remotion-video": {
      "command": "python",
      "args": ["/absolute/path/to/remotion-mcp-server/server.py"]
    }
  }
}

Restart Claude, and ask it to analyze a reference reel and build you one in the same style.

How it works

  • analyze_video downloads with yt-dlp, extracts frames + audio with ffmpeg, then transcribes: YouTube captions via youtube-transcript-api first, falling back to local faster-whisper transcription for everything else.
  • create_dialogue_reel / create_facts_reel template out a .tsx composition file, register it in the Remotion project's Root.tsx between marker comments, and call npx remotion render.
  • Generated compositions show up live in Remotion Studio (npm run dev) via hot-reload — no restart needed — so you can scrub through and review before treating a render as final.

License

MIT — see LICENSE.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选