YouTube Video Summarizer MCP
Fetch and summarize YouTube videos by extracting titles, descriptions, and transcripts.
YouTube Video Summarizer MCP Server
An MCP (Model Context Protocol) server that enables AI assistants to analyze and summarize YouTube videos by extracting captions, descriptions, and metadata.
Features
- Extract video captions/subtitles in multiple languages
- Retrieve comprehensive video metadata (title, description, duration)
- Provide structured data to AI assistants for comprehensive video summarization
- Works with any MCP-compatible client through MCP integration
- Support for multiple YouTube URL formats
- Language-specific caption extraction
Integrating with MCP Clients
To add the MCP server to your MCP client, you can use either method:
Option 1: Using npx (No Installation Required)
Add the following to your MCP client configuration file:
{
"mcpServers": {
"youtube-video-summarizer": {
"command": "npx",
"args": ["-y", "youtube-video-summarizer-mcp"]
}
}
}
The server automatically filters out any npm/npx output to ensure MCP protocol compliance.
Option 2: Global Installation (Recommended for Production)
-
Install the package globally:
npm install -g youtube-video-summarizer-mcp -
Add the following to your MCP client configuration file:
{
"mcpServers": {
"youtube-video-summarizer": {
"command": "youtube-video-summarizer",
"args": []
}
}
}
Available Tools
When integrated with an MCP client, the following commands become available:
- get-video-info-for-summary-from-url: Extract video information and captions from a YouTube URL
- get-video-captions: Get captions/subtitles for a specific video
- get-video-metadata: Retrieve comprehensive video metadata
Usage Examples
Once integrated with your MCP client, you can use natural language to request video summaries:
"Can you summarize this YouTube video: https://youtube.com/watch?v=VIDEO_ID"
"What are the main points from this video's captions?"
"Extract the key information from this YouTube link"
Installation
npm install -g youtube-video-summarizer-mcp
Development
git clone https://github.com/nabid-pf/youtube-video-summarizer-mcp.git
cd youtube-video-summarizer-mcp
npm install
npm run build
How It Works
- URL Parsing: Extracts video IDs from various YouTube URL formats
- Caption Extraction: Uses youtube-caption-extractor to get subtitles
- Metadata Retrieval: Fetches video title, description, and other details
- MCP Integration: The Model Context Protocol (MCP) to communicate with AI assistants
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
This project is licensed under the MIT License - see the LICENSE file for details.
관련 서버
Bright Data
스폰서Discover, extract, and interact with the web - one interface powering automated access across the public internet.
SERP Scraper MCP
Extract structured Google & Bing results — organic, ads, featured snippets, PAA, related searches. Keyword research and rank checking. Free alternative to SerpApi. No API keys required.
YouTube Data
Access YouTube video data and transcripts using the YouTube Data API.
Patchright Lite MCP Server
A server that wraps the Patchright SDK to provide stealth browser automation for AI models.
Tech Collector MCP
Collects and summarizes technical articles from sources like Qiita, Dev.to, NewsAPI, and Hacker News using the Gemini API.
E-Commerce Intelligence MCP Server
Shopify store analysis, product catalog extraction, pricing strategy, and inventory monitoring
SideButton
Open-source MCP server with knowledge packs, 40+ browser tools, and YAML workflow engine for AI agents.
1001Proxy - Proxy MCP Server for AI Agents
Use Claude, OpenAI Cursor, and any MCP-compatible AI agent to buy and manage proxies using natural language. No custom integrations needed - simply connect your client to the server and start chatting.
Plain Markdown
Convert any URL to clean, LLM-ready Markdown
Lightpanda Go MCP server
A Go-based MCP server for interacting with the Lightpanda Browser using the Chrome DevTools Protocol (CDP).
Haunt API
Extract clean, structured data from any URL — directly from Claude, Cursor, or any MCP-compatible AI.
