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.
Before using the YouTube MCP server, you need to install the required dependencies:
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
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
Once installed, the YouTube MCP server works automatically with Claude.ai. Here's how to use it:
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>>
If Claude doesn't recognize the YouTube video:
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.
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"
]
}
}
}
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.
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.