YouTube MCP server

Extract and analyze video subtitle data for content understanding.
Back to servers
Provider
Anaïs Betts
Release date
Nov 19, 2024
Language
TypeScript
Package
Stats
10.8K downloads
362 stars

This server enhances Claude's capabilities by fetching and processing YouTube video subtitles, allowing Claude to understand and discuss video content. It integrates with Claude.ai using the Model Context Protocol (MCP) to seamlessly handle YouTube video references.

Installation Requirements

Before using the YouTube MCP server, you need to install the required dependencies:

1. Install yt-dlp

This server requires yt-dlp to download YouTube video subtitles.

On macOS (using Homebrew):

brew install yt-dlp

On Windows (using WinGet):

winget install yt-dlp

2. Install the MCP Server

Use the MCP installer to set up the YouTube server:

# Install the MCP installer if you don't have it already
npm install -g @anaisbetts/mcp-installer

# Install the YouTube MCP server
mcp-installer install @anaisbetts/mcp-youtube

Usage

Once installed, the YouTube MCP server works automatically with Claude.ai. Here's how to use it:

Asking Claude About YouTube Videos

Simply ask Claude about a YouTube video by including the video URL in your prompt:

Summarize the YouTube video <<https://www.youtube.com/watch?v=dQw4w9WgXcQ>>

How It Works

  1. When you include a YouTube URL in your message to Claude, the MCP server detects it
  2. The server uses yt-dlp to fetch subtitles from the video
  3. These subtitles are processed and provided to Claude as context
  4. Claude can then respond based on the content of the video

Troubleshooting

If Claude doesn't recognize the YouTube video:

  • Verify that yt-dlp is correctly installed
  • Check that the MCP server is properly running
  • Ensure the YouTube URL is valid and the video has subtitles available
  • Try formatting your request differently (e.g., "What is the main topic of this YouTube video: <<URL>>")

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later