Package Exports

rippr-mcp
rippr-mcp/build/index.js

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (rippr-mcp) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

rippr-mcp

YouTube transcript extraction for AI agents. MCP server for Claude, Cursor, and any MCP-compatible client.

Website · Chrome Extension

What it does

Extracts transcripts from any YouTube video and returns clean text optimized for LLM consumption. Uses YouTube's InnerTube API with HTML scraping fallback for maximum reliability.

Install

npx rippr-mcp

Configure in Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "rippr": {
      "command": "npx",
      "args": ["rippr-mcp"]
    }
  }
}

Restart Claude Desktop. Then ask:

"Get me the transcript of this YouTube video: https://www.youtube.com/watch?v=..."

Tools

`rip_transcript`

Extract the full transcript from a YouTube video.

Input:

Parameter	Type	Required	Description
`url`	string	yes	Any YouTube URL format
`format`	string	no	`"text"` (default, single block) or `"segments"` (timestamped JSON)

Output (text format):

Title: Video Title
Channel: Channel Name
Language: en (auto-generated)
URL: https://www.youtube.com/watch?v=...

Full transcript text as a single continuous block...

Output (segments format):

{
  "title": "Video Title",
  "channel": "Channel Name",
  "language": "en",
  "isAutoGenerated": true,
  "videoUrl": "https://www.youtube.com/watch?v=...",
  "segmentCount": 142,
  "segments": [
    { "start": 0.5, "duration": 2.1, "text": "Hello world" },
    { "start": 2.6, "duration": 1.8, "text": "Next segment" }
  ]
}

How it works

Tries YouTube's InnerTube API (Android client) first
Falls back to HTML scraping if InnerTube fails
Parses caption XML in multiple formats (srv3, timedtext, JSON3)
Retries with exponential backoff on transient failures

No API keys required. No data sent to external servers. Runs entirely on your machine.

Privacy

rippr-mcp runs locally. It only communicates with YouTube's own APIs to fetch caption data. No telemetry, no analytics, no tracking.

License

MIT