@herrwelle
基本信息
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"youtube-transcript-mcp-server-herrwelle": {
"command": "npx",
"args": [
"@modelcontextprotocol/inspector"
]
}
}
}Extract transcripts from YouTube videos
A high-performance, serverless implementation of a YouTube transcript extraction service using the Model Context Protocol (MCP), deployed on Cloudflare Workers. It enables AI assistants to retrieve transcripts from YouTube videos through a simple API.
Install by configuring Claude Desktop with a remote MCP server URL. Use the get_transcript tool with a YouTube URL or video ID and an optional language code (defaults to English). Run locally with wrangler dev after cloning the repository and installing dependencies. Deploy with wrangler deploy.
The README lists Node.js 18 or higher, Wrangler CLI (`npm install -g wrangler`), and dependencies installed via `npm install`. It uses `@modelcontextprotocol/sdk` and `youtube-captions-scraper`.
Use `wrangler dev` to run locally, then test with the MCP Inspector by setting Transport Type to `SSE` and entering `http://localhost:8787/sse` as the URL. Connect and try the `get_transcript` tool.
It uses Server-Sent Events (SSE) for streaming connections, as indicated in the README under “SSE Transport” and in the configuration example for Claude Desktop.
The README does not explicitly state any limits, but the implementation relies on `youtube-captions-scraper` for transcript extraction and runs on Cloudflare Workers, which have standard Workers limits (not detailed in the README).
The README does not describe authentication. The remote server is accessed via a public URL (e.g., `https://your-deployed-worker.workers.dev/sse`). No auth mechanisms are mentioned.
Transcribe YouTube videos, podcasts, meetings and media links into speaker-labelled, timestamped transcripts, then search who said what, ask questions answered with timestamped citations, pull chapters and paste-ready ti
Make AI-drawn video from chat. Claude, Cursor or Claude Code plans the film, the model draws every frame in code at 30 fps, and you edit it on a timeline with narration, music and sound effects.
Create greetings and personalized PNG cards for 30 occasions in 15 languages, including Hindi, Greek and Hebrew. Free remote MCP with curated phrases, occasion-matched backgrounds and four styles, including motivational.
Official JSON2Video MCP server. Video API for automated video production at scale: render videos from templates with AI voiceovers, subtitles and AI images. Remote server with OAuth (https://mcp.json2video.com/mcp) or lo
Drive Veltake Studio from any AI agent: create film and ad projects, have the Studio agent build scenes on the canvas, price and start renders, export edited cuts, and make single images, video, speech and music in one c
评论