Youtube Transcript Downloader

🚀 YouTube MCP Server

A server that acts as a bridge between the YouTube API and AI assistants, based on the Model Context Protocol.

🚀 Quick Start

The YouTube MCP Server serves as a crucial link between the YouTube API and AI assistants, leveraging the Model Context Protocol. It enables seamless interaction between AI applications and external data sources.

✨ Features

• Download closed captions for a given video.
• Create video summaries.

📦 Installation

First, make sure you have the uv tool installed. Then, use the following command to install the server:

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

⚠️ Important Note

If you have already installed the server, you can use the uv tool upgrade --reinstall command to update it.

⚠️ Important Note

If you want to uninstall the server, use the uv tool uninstall mcp-youtube command.

💻 Usage Examples

Basic Usage

Once installed, the server can be used to perform tasks such as downloading closed captions and creating video summaries.

Advanced Usage

For more advanced usage scenarios, you can configure the server according to your specific needs.

📚 Documentation

What is MCP?

The Model Context Protocol (MCP) is a system that allows AI applications (such as Claude Desktop) to connect to external tools and data sources. It provides a clear and secure way for AI assistants to interact with local services and APIs while keeping users in control.

What does this server do?

• [x] Download closed captions for a given video.

Practical Use Cases

• [x] Create video summaries.

Prerequisites

• uv tool

Configuration

Claude Desktop Configuration

Configure Claude Desktop to recognize the YouTube MCP Server:

1. Open the configuration file of Claude Desktop:

   • On MacOS, the configuration file is located at ~/Library/Application Support/Claude/claude_desktop_config.json.
   • On Windows, the configuration file is located at %APPDATA%\Claude\claude_desktop_config.json.

   ⚠️ Important Note

   You can also find the claude_desktop_config.json file in the settings of the Claude Desktop application.

2. Add the server configuration:

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

Development

Getting Started

1. Clone the repository.
2. Install the dependencies:

uv sync

3. Run the server:

uv run mcp-youtube --help

To add new tools:

1. Create a new class that inherits from ToolArgs:

class NewTool(ToolArgs):
    """Description of the new tool."""
    pass

The attributes of the class will be used as the parameters of the tool, and the docstring of the class will be used as the tool description.

2. Implement the tool_runner function for the new tool:

@tool_runner.register
async def new_tool(args: NewTool) -> t.Sequence[TextContent | ImageContent | EmbeddedResource]:
    pass

This function should return a sequence containing TextContent, ImageContent, or EmbeddedResource. It should be asynchronous and accept an argument of the new class.

3. Done! Restart the client, and the new tool should be available. You can verify it through Claude Desktop or by running the tool directly.

Debugging the Server in the Inspector

The MCP Inspector is a tool for debugging the server with a beautiful UI. To run it, use the following command:

npx @modelcontextprotocol/inspector uv run mcp-youtube

🔧 Technical Details

The server is developed based on the Model Context Protocol, which enables AI assistants to interact with the YouTube API. It uses the uv tool for installation, management, and running. The server's code structure allows for easy addition of new tools by following specific development steps.

📄 License

No license information provided in the original document.

🛠️ Troubleshooting

Message “Could not connect to MCP server mcp-youtube”

Add the full path of the mcp-youtube executable file to the command-line parameters in the configuration file.