yt-repurpose
Enables AI assistants to extract YouTube transcripts and repurpose them into social media posts via LLM.
README
yt-repurpose
Extract YouTube transcripts and repurpose them into social media posts.
Available as a CLI tool, a Node.js library, and an MCP server for AI assistants.
Quick Start
# Install globally
npm install -g yt-repurpose
# Set your Google API key (YouTube Data API v3)
yt-repurpose config set google-api-key YOUR_KEY
# Extract a transcript
yt-repurpose https://www.youtube.com/watch?v=VIDEO_ID
# Repurpose into social posts (requires Anthropic or OpenAI key)
yt-repurpose config set anthropic-key YOUR_KEY
yt-repurpose https://www.youtube.com/watch?v=VIDEO_ID --repurpose
# Choose platforms and provider
yt-repurpose https://www.youtube.com/watch?v=VIDEO_ID --repurpose --platforms twitter,tiktok,linkedin --provider openai
Getting a Google API Key
- Go to Google Cloud Console
- Create a project (or select an existing one)
- Enable the YouTube Data API v3
- Create an API key under Credentials
- Set it:
yt-repurpose config set google-api-key YOUR_KEY
CLI Usage
# Transcript only (default)
yt-repurpose <youtube-url>
# Repurpose with LLM
yt-repurpose <youtube-url> --repurpose
# Options
--repurpose Generate social media posts from transcript
--platforms <list> Comma-separated: twitter,tiktok,linkedin,instagram,blog (default: twitter,linkedin)
--provider <name> LLM provider: anthropic or openai (default: anthropic)
--model <model> Override default model
--google-api-key <key> Google API key (overrides config)
--anthropic-key <key> Anthropic API key (overrides config)
--openai-key <key> OpenAI API key (overrides config)
# Config management
yt-repurpose config set <key> <value>
yt-repurpose config get <key>
# Keys: google-api-key, anthropic-key, openai-key
MCP Server
Add to your Claude Desktop config (claude_desktop_config.json):
{
"mcpServers": {
"yt-repurpose": {
"command": "npx",
"args": ["-y", "yt-repurpose-mcp"],
"env": {
"GOOGLE_API_KEY": "your-google-api-key"
}
}
}
}
MCP Tools
get_youtube_transcript- Extract transcript from a YouTube URL. Returns the title and full text for the LLM to naturally repurpose.repurpose_transcript- Extract and repurpose in one step using an LLM (requires Anthropic or OpenAI key in env).
Library Usage
import { getTranscript, repurpose } from 'yt-repurpose-core';
// Extract transcript
const result = await getTranscript({
url: 'https://www.youtube.com/watch?v=VIDEO_ID',
googleApiKey: 'YOUR_KEY',
});
console.log(result.title, result.fullText);
// Repurpose with LLM
const posts = await repurpose({
transcript: result.fullText,
title: result.title,
platforms: ['twitter', 'linkedin'],
provider: 'anthropic',
apiKey: 'YOUR_ANTHROPIC_KEY',
});
Packages
| Package | npm | Description |
|---|---|---|
yt-repurpose |
CLI | Command-line tool |
yt-repurpose-mcp |
MCP Server | For AI assistants (Claude Desktop, etc.) |
yt-repurpose-core |
Library | Core transcript + repurpose logic |
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.