YouTube Transcript Downloader MCP server

Bridges YouTube API to download closed captions, enabling video transcript analysis and content processing.
Back to servers
Provider
Sergey Parfenyuk
Release date
Dec 26, 2024
Language
Python
Stats
10 stars

This YouTube MCP server allows AI assistants like Claude Desktop to interact with YouTube content through the Model Context Protocol (MCP), providing functionalities such as downloading closed captions for analysis and summarization.

Installation

Prerequisites

Before installing the YouTube MCP server, you need to have the uv tool installed on your system. Visit the uv getting started guide for installation instructions.

Installing the Server

Install the YouTube MCP server using the following command:

uv tool install git+https://github.com/sparfenyuk/mcp-youtube

Updating the Server

If you've already installed the server and need to update it:

uv tool upgrade --reinstall

Uninstalling the Server

To remove the server from your system:

uv tool uninstall mcp-youtube

Configuration

The server needs to be configured to work with Claude Desktop.

Claude Desktop Configuration

  1. Locate your Claude Desktop configuration file:

    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Windows: %APPDATA%\Claude\claude_desktop_config.json

    You can also access this file through the Settings menu in the Claude Desktop app

  2. Add the YouTube MCP server configuration to the file:

    {
      "mcpServers": {
        "mcp-youtube": {
            "command": "mcp-youtube",
          }
        }
      }
    }
    

Usage

The YouTube MCP server currently supports downloading closed captions for YouTube videos. This functionality can be especially useful for:

  • Creating summaries of video content
  • Analyzing video transcripts
  • Extracting key information from YouTube videos

Troubleshooting

"Could not connect to MCP server mcp-youtube" Error

If you encounter this error in Claude Desktop, your server configuration may be incorrect. Try using the full path to the mcp-youtube binary in your configuration file instead of just the command name.

For example:

{
  "mcpServers": {
    "mcp-youtube": {
        "command": "/full/path/to/mcp-youtube",
      }
    }
  }
}

Replace /full/path/to/mcp-youtube with the actual path on your system.

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