YouTube Watch Later MCP Server: Access Custom YouTube Playlists

Overview: What is YouTube Watch Later MCP Server?

The YouTube Watch Later MCP Server is a specialized server that integrates with Model Context Protocol (MCP) to provide access to a custom YouTube playlist in real-time. It retrieves URLs of videos added within a configurable timeframe, offering AI applications like Claude Desktop, Continue, and Cursor the ability to programmatically retrieve content from your Google Playlists. This server enhances these AI applications by providing a seamless way to integrate and interact with external data sources using MCP.

🔧 Core Features & MCP Capabilities

The YouTube Watch Later MCP Server offers several core features that make it indispensable for integrating with various AI workflows:

• Video URL Retrieval: The server can retrieve URLs of videos added to the specified playlist within a configurable number of days.
• OAuth2 Authentication: Secure access to your YouTube data by leveraging OAuth2, ensuring privacy and compliance.
• Simple Interface: A straightforward tool that returns just the video URLs for easy integration into AI applications.

These features are implemented using MCP, which provides a standardized protocol for AI applications like Claude Desktop. This ensures seamless integration without requiring complex configurations or API setups from the application side.

MCP Protocol Implementation

The YouTube Watch Later server adheres to the MCP protocol to ensure compatibility with various AI clients, including:

• Claude Desktop: Full support for all features.
• Continue: Supports video URL retrieval and authentication.
• Cursor: Tools only integration.

This server utilizes TypeScript and the @modelcontextprotocol/sdk library along with the googleapis package (YouTube Data API v3) to build a robust and interoperable solution. The protocol flow diagram below illustrates how data is transferred between the AI application, MCP client, and the YouTube Watch Later server.

⚙️ MCP Architecture & Protocol Implementation

The architecture of the YouTube Watch Later server involves several key components:

• MCP Client: Connects to the server through a standardized protocol.
• Server Proxy: Handles incoming requests from the MCP client.
• YouTube Data API: Retrieves video URLs based on configured parameters.

MCP Protocol Flow Diagram

graph TD
    A[AI Application] -->|MCP Client| B[MCP Protocol]
    B --> C[MCP Server]
    C --> D[Data Source/Tool: YouTube API]
    style A fill:#e1f5fe
    style B fill:#a6e2dd
    style C fill:#f3e5f5
    style D fill:#e8f5e8

Data Architecture Diagram

graph TD
    A[Data Source] --> B[Django App]
    B -->|API| C[MCP Server]
    C -->|Streaming| D[AI Application]
    style A fill:#b0bce4
    style B fill:#e2f9ff
    style C fill:#f3e5f5
    style D fill:#e8f5e8

🚀 Getting Started with Installation

To set up and run the YouTube Watch Later MCP Server, either use Smithery or manually install it.

Installing via Smithery

For automated installation using Smithery:

npx -y @smithery/cli install youtube-watchlater --client claude

Manual Installation

1. Clone this repository:

   git clone https://github.com/rados10/youtube-watchlater-mcp.git
   cd youtube-watchlater
   

2. Install dependencies:

   npm install
   

3. Build the project:

   npm run build
   

💡 Key Use Cases in AI Workflows

Real-Time Content Integration

AI applications can integrate with the YouTube Watch Later MCP Server to fetch real-time content from playlists, ensuring that users always have access to up-to-date videos.

Scheduled Notifications

Automatically notify users of new additions to their favorite playlist by scheduling tasks using AI workflows.

🔌 Integration with MCP Clients

The server is compatible with Claude Desktop, Continue, Cursor, and other applications:

• Claude Desktop: Full support for video URL retrieval.
• Continue: Supports URL retrieval and authentication.
• Cursor: Tools only integration.

Configuration Code Sample

Here’s an example of how to configure the server in your MCP settings file:

{
  "mcpServers": {
    "youtube-watchlater": {
      "command": "node",
      "args": ["/path/to/youtube-watchlater/build/index.js"],
      "env": {
        "OAUTH_CLIENT_ID": "your_client_id",
        "OAUTH_CLIENT_SECRET": "your_client_secret",
        "OAUTH_REFRESH_TOKEN": "your_refresh_token"
      }
    }
  }
}

📊 Performance & Compatibility Matrix

The server has the following compatibility and performance characteristics:

• AI Application Support:

  • Claude Desktop: Full support
  • Continue: Partial support (video URL, authentication)
  • Cursor: Tools only

• Performance: Configurable based on the timeframe for video retrieval.

🛠️ Advanced Configuration & Security

Token Refresh

While refresh tokens typically do not expire, they can be generated again if necessary:

1. Revoke application access from your Google account settings.
2. Reset security settings and re-run the get-refresh-token.js script.

OAUTH_CLIENT_ID="your_client_id" OAUTH_CLIENT_SECRET="your_client_secret" node get-refresh-token.js

Security Best Practices

• OAuth2 Authentication: Use OAuth2 for secure API integrations.
• Environment Variables: Store sensitive information like OAUTH_CLIENT_ID and OAUTH_CLIENT_SECRET as environment variables.

❓ Frequently Asked Questions (FAQ)

1. How do I get the OAUTH_CLIENT_ID and OAUTH_CLIENT_SECRET?

   • You can obtain these values by creating a new OAuth 2.0 Client ID in Google Cloud Console.

2. What should I do if my refresh token becomes invalid or expires?

   • Simply re-run the get-refresh-token.js script to generate a new one.

3. Can this server be used with other YouTube playlists besides Watch Later?

   • Yes, it can fetch from any playlist using the appropriate parameters.

4. Does the server support multiple timeframes for video retrieval?

   • Absolutely, you can configure it to fetch videos added in the last 1 day to 30 days.

5. Is there a limit to the number of URLs that can be retrieved at once?

   • There is no specific limit; however, consider performance implications and optimize as needed.

👨‍💻 Development & Contribution Guidelines

To modify the server:

1. Make Your Changes: Edit src/index.ts.
2. Rebuild: Run npm run build to compile.
3. Restart MCP Server: Apply changes by restarting the MCP server.

Contributions are welcome! Follow our contribution guidelines for submitting pull requests.

🌐 MCP Ecosystem & Resources

For more information, visit:

• Smithery AI
• YouTube Data API v3 Documentation

Explore the power of integrating YouTube playlists with your AI applications using the YouTube Watch Later MCP Server.