YouTube MCP Server

This MCP server enables AI assistants to access and analyze YouTube video content by retrieving subtitles and transcripts. It uses yt-dlp to download subtitles from YouTube videos and makes them available through the Model Context Protocol. With this integration, you can ask your AI assistant to summarize, analyze, or extract information from YouTube videos by simply providing the video URL. The server handles the technical aspects of retrieving the video's text content, allowing the AI to work with the video's information directly.

Overview

The YouTube MCP server allows AI assistants to access and analyze the content of YouTube videos by retrieving their subtitles or transcripts. This enables you to ask your AI assistant questions about YouTube videos or request summaries without having to manually transcribe the content.

Prerequisites

Before installing the YouTube MCP server, you need to have:

yt-dlp installed on your system (this is the tool that extracts subtitles from YouTube)
- On macOS: Install via Homebrew with brew install yt-dlp
- On Windows: Install via WinGet with winget install yt-dlp
- On Linux: Use your distribution's package manager or follow the instructions on the yt-dlp GitHub page
Node.js or Bun runtime environment

Installation

The easiest way to install the YouTube MCP server is using the mcp-installer:

Install the mcp-installer if you haven't already:
```
npm install -g @anaisbetts/mcp-installer
```

Install the YouTube MCP server:

mcp-installer install @anaisbetts/mcp-youtube

Alternatively, you can clone the repository and install it manually:

Clone the repository:

git clone https://github.com/anaisbetts/mcp-youtube.git

Navigate to the directory and install dependencies:
```
cd mcp-youtube
npm install
```
Start the server:
```
npm start
```

Usage

Once the server is installed and running, you can use it with your AI assistant by asking questions about YouTube videos. Simply include the YouTube video URL in your query.

Example queries:

"Summarize this YouTube video: https://www.youtube.com/watch?v=dQw4w9WgXcQ"
"What are the main points discussed in this video: https://www.youtube.com/watch?v=example"
"Extract the key information from this YouTube tutorial: https://www.youtube.com/watch?v=example"

The MCP server will automatically:

Extract the video ID from the URL
Use yt-dlp to download the subtitles
Process the subtitles to remove formatting
Provide the transcript to the AI assistant

Troubleshooting

If you encounter issues:

Ensure yt-dlp is correctly installed and accessible from your command line
Check that the YouTube video has subtitles available (some videos don't have subtitles)
Verify that your AI assistant is properly configured to use the MCP server
Check the server logs for any error messages

Limitations

The server can only retrieve subtitles if they are available for the video
Very long videos may have their transcripts truncated due to token limitations
The quality of the analysis depends on the quality of the subtitles