
Rippr Mcp
io.github.mrslbt由 GitHub 账号 mrslbt 发布v1.3.0更新于 Oct 25, 2026
Rip YouTube transcripts to disk for AI agents, RAG pipelines, and LLM workflows.
概览
本地 MCP 服务器,抓取 YouTube 视频字幕并保存到磁盘,再把文件路径返回给助手。
- 可以做什么
- 根据 YouTube 视频链接抓取字幕,保存到本地 rippr 字幕文件夹,并把文件路径返回给模型。可按 RAG 纯文本、带时间戳分段的 JSON 或可读 Markdown 三种格式输出。在一种方式失败时依次尝试播放器接口、页面源码、字幕面板等多种提取策略并重试。
- 适用场景
- 适合需要让助手把 YouTube 字幕抓取成本地文件、用于 RAG 流程、LLM 工作流或笔记整理,并且使用 Claude Desktop、Claude Code CLI 或 Cursor 等桌面 MCP 客户端的场景。
- 运行要求
- 以本地 stdio 进程运行,通过 npx 启动 npm 包 rippr-mcp,需要 Node.js 以及访问 YouTube 的网络。仅支持桌面 MCP 客户端,云端或手机客户端无法启动它。无需账号或 API 密钥。
安装
在 SourceWeft 中
- 打开 控制台中的 Rippr Mcp,将其添加到工作区。
- 为需要使用其工具的对话启用该服务。
Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。
其他 MCP 客户端
参照 仓库 中的启动说明。
README
rippr
YouTube transcript ripper for humans and AI agents.
[npm] [npm downloads] [Manifest V3] [MIT License] [LobeHub MCP] [Glama MCP]
Website · Chrome Web Store · MCP Server (npm)
Three ways to use rippr
🌐 Website — rippr.me
Paste a YouTube URL, get the transcript. Clean text, no signup.
🧩 Chrome Extension — Chrome Web Store
One-click transcript extraction directly on any YouTube page. Multiple output formats (RAG, JSON, Markdown).
🤖 MCP Server — npm
Connect rippr to Claude, Cursor, or any MCP-compatible client. Saves each transcript to ~/rippr/transcripts/ and returns the file path to the model.
Desktop clients only. rippr runs as a local stdio process, so it works with Claude Desktop, Claude Code CLI, and Cursor. It does not work with cloud-hosted clients (claude.ai on the web, the Claude mobile app, or Claude Code on phone / web), which can't spawn local processes.
Add to Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):
Then ask: "Rip this YouTube video: [url]". See mcp/README.md for the full tool surface.
Output formats
- RAG (.txt) — single continuous text block, optimized for chunking and embedding
- Structured (.json) — timestamped segments with metadata
- Readable (.md) — markdown with headers and formatting
How it works
Multi-strategy extraction for maximum reliability:
- Innertube API — YouTube's internal player API (Android client)
- HTML scraping — parses
ytInitialPlayerResponsefrom page source - Transcript panel — opens YouTube's built-in transcript panel as last resort
Caption XML parsed in multiple formats (srv3, timedtext, JSON3). Retry with exponential backoff on transient failures.
Privacy
Runs entirely on your machine. No data sent to external servers. No accounts, no tracking. Only communicates with YouTube's own APIs.
More MCPs
Disclaimer
Rippr is an unofficial, community-built tool. It is not affiliated with, endorsed by, or sponsored by YouTube or Google LLC. YouTube is a trademark of Google LLC.
Rippr accesses publicly available YouTube transcript data through endpoints that YouTube's own apps use. Use is subject to YouTube's Terms of Service, and use is at your own risk. The author accepts no liability for takedowns, rate limits, account actions, or any other consequences of use.
If YouTube changes their internal APIs in ways that break extraction, the tool may stop working without notice. For long-term production use, consider the official YouTube Data API v3 with an API key (not currently supported by this package).
License
来源:README.md,提交 c82845e
工具
0版本历史
1- v1.3.0最新Sep 16, 2026
评分
已满足适用检查项的 50%
该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。
- 近 30 天内可连通25 分
请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。
- 已声明认证方式10 分
请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。
- 已列出工具15 分
请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。
- 描述必需15 分
- 图标10 分
- 文档15 分
- 许可证10 分