mcp-youtube-extractor 0.2.0

A Model Context Protocol (MCP) server for YouTube operations

MCP YouTube Extractor

A Model Context Protocol (MCP) server for YouTube operations, demonstrating core MCP concepts including tools and logging.

Features

• MCP Server: A fully functional MCP server with:
  • Tools: Extract information from YouTube videos including metadata and transcripts
  • Comprehensive Logging: Detailed logging throughout the application
  • Error Handling: Robust error handling with fallback logic for transcripts
  • Multiple Transports: Supports both stdio and SSE (Server-Sent Events) protocols
• YouTube Integration: Built-in YouTube API capabilities:
  • Extract video information (title, description, channel, publish date)
  • Get video transcripts with intelligent fallback logic
  • Support for both manually created and auto-generated transcripts

📦 Available on PyPI

This package is now available on PyPI! You can install it directly from PyPI.

Visit the package page: mcp-youtube-extractor on PyPI

Installation

Quick Start (Recommended)

The easiest way to get started is to install from PyPI:

pip install mcp-youtube-extractor

Requirements: Python 3.13+ is required for this package.

Or using pipx (recommended for command-line tools):

pipx install mcp-youtube-extractor

This will install the latest version with all dependencies. You can then run the MCP server directly:

mcp_youtube_extractor

Using uv (Development)

For development or if you prefer uv:

Installing uv

On Linux/macOS:

curl -LsSf https://astral.sh/uv/install.sh | sh

On Windows:

uv is written in Rust, so you'll need the Rust toolchain first.

1. **Install Rust **

   1. Visit this link or copy and paste it into your browser: 👉 https://win.rustup.rs/
   2. The installer (rustup-init.exe) will download automatically
   3. Run the installer and proceed with default options:
      • This installs cargo, rustc, rustup, rustdoc, etc.
      • After installation, C:\Users\[username]\.cargo\bin is automatically added to PATH

2. **Install uv from GitHub **

   After Rust is installed, install uv with this command:

   cargo install --git https://github.com/astral-sh/uv uv
   

   This command fetches and builds the latest version of uv directly from the GitHub repository.

Setting up the project

Once uv is installed:

# Clone and install the project
git clone https://github.com/hwang2006/mcp-youtube-extractor.git
cd mcp-youtube-extractor

# Install dependencies (including dev dependencies)
uv sync --dev

# Set up your API key for development
cp .env.example .env
# Edit .env and add your YouTube API key

From source

1. Clone the repository:

   git clone https://github.com/hwang2006/mcp-youtube-extractor.git
   cd mcp-youtube-extractor
   

2. Install in development mode:

   uv sync --dev
   

Configuration

Environment Variables

For development, create a .env file in the project root with your YouTube API key:

# YouTube API Configuration
YOUTUBE_API_KEY=your_youtube_api_key_here

For production, set the environment variable directly in your system:

export YOUTUBE_API_KEY=your_youtube_api_key_here

Required:

• YOUTUBE_API_KEY: Your YouTube Data API key (required for video metadata)

Getting Your YouTube API Key

To use this MCP server, you'll need a YouTube Data API key. Here's how to get one:

Step 1: Create a Google Cloud Project

1. Go to the Google Cloud Console
2. Click "Select a project" at the top of the page
3. Click "New Project" and give it a name (e.g., "MCP YouTube Extractor")
4. Click "Create"

Step 2: Enable the YouTube Data API

1. In your new project, go to the API Library
2. Search for "YouTube Data API v3"
3. Click on it and then click "Enable"

Step 3: Create API Credentials

1. Go to the Credentials page
2. Click "Create Credentials" and select "API Key"
3. Your new API key will be displayed - copy it immediately
4. Click "Restrict Key" to secure it (recommended)

Step 4: Restrict Your API Key (Recommended)

1. In the API key settings, click "Restrict Key"
2. Under "API restrictions", select "Restrict key"
3. Choose "YouTube Data API v3" from the dropdown
4. Click "Save"

Step 5: Set Up Billing (Required)

1. Go to the Billing page
2. Link a billing account to your project
3. Note: YouTube Data API has a free tier of 10,000 units per day, which is typically sufficient for most use cases

API Key Usage Limits

• Free Tier: 10,000 units per day
• Cost: $5 per 1,000 units after free tier
• Typical Usage:
  • Getting video info: ~1 unit per request
  • Getting transcripts: ~1 unit per request
  • Most users stay well within the free tier

Security Best Practices

• Never commit your API key to version control
• Use environment variables as shown in the configuration section
• Restrict your API key to only the YouTube Data API
• Monitor usage in the Google Cloud Console

Usage

Running the MCP Server

Using PyPI Installation (Recommended)

# Install from PyPI
pip install mcp-youtube-extractor

# Quick CLI testing
python yt_extract_cli.py --help
python yt_extract_cli.py dQw4w9WgXcQ

# Run the server
mcp_youtube_extractor

Using Development Setup

# Using uv
cd mcp-youtube-extractor
uv run mcp_youtube_extractor

# Or directly
python -m mcp_youtube_extract.server

Direct Function Call (Quick Testing)

For quick testing or one-off extractions, you can call the YouTube extraction function directly using Python's -c flag:

Basic Usage

# Extract Rick Astley video (Never Gonna Give You Up)
cd mcp-youtube-extractor
uv run python -c "from dotenv import load_dotenv; load_dotenv(); from src.mcp_youtube_extract.server import get_yt_video_info; print(get_yt_video_info('dQw4w9WgXcQ'))"

# Or PyPI Installation
cd mcp-youtube-extractor
python -c "from dotenv import load_dotenv; load_dotenv(); from src.mcp_youtube_extract.server import get_yt_video_info; print(get_yt_video_info('dQw4w9WgXcQ'))"

With Error Handling

uv run python -c "
try:
    from dotenv import load_dotenv
    load_dotenv()
    from src.mcp_youtube_extract.server import get_yt_video_info
    result = get_yt_video_info('dQw4w9WgXcQ')
    print(result)
except Exception as e:
    print(f'Error: {e}')
"

Save Output to File

uv run python -c "
from dotenv import load_dotenv
load_dotenv()
from src.mcp_youtube_extract.server import get_yt_video_info
result = get_yt_video_info('dQw4w9WgXcQ')
with open('video_info.txt', 'w', encoding='utf-8') as f:
    f.write(result)
print('Video information saved to video_info.txt')
"

Extract Multiple Videos

uv run python -c "
from dotenv import load_dotenv
load_dotenv()
from src.mcp_youtube_extract.server import get_yt_video_info

videos = ['dQw4w9WgXcQ', 'jNQXAC9IVRw', '9bZkp7q19f0']
for video_id in videos:
    print(f'\\n=== Processing {video_id} ===')
    try:
        print(get_yt_video_info(video_id))
    except Exception as e:
        print(f'Error: {e}')
    print('\\n' + '='*60)
"

Note: Replace 'dQw4w9WgXcQ' with any YouTube video ID you want to extract. The video ID is the part after v= in a YouTube URL (e.g., https://www.youtube.com/watch?v=dQw4w9WgXcQ).

Command Line Interface (CLI)

For more convenient command-line usage, you can use the included CLI script:

Basic Usage

# Extract full video information and transcript using a video ID
uv run python yt_extract_cli.py dQw4w9WgXcQ

# Or using a full YouTube URL
uv run python yt_extract_cli.py "https://www.youtube.com/watch?v=dQw4w9WgXcQ"

Advanced Options

# Get only video information (skip transcript)
uv run python yt_extract_cli.py dQw4w9WgXcQ --info-only

# Get only transcript (skip video info)
uv run python yt_extract_cli.py dQw4w9WgXcQ --transcript-only

# Save output to a file
uv run python yt_extract_cli.py dQw4w9WgXcQ --output video_info.txt
uv run python yt_extract_cli.py dQw4w9WgXcQ -o video_info.txt

# Combine options: save only video info to file
uv run python yt_extract_cli.py dQw4w9WgXcQ --info-only -o video_metadata.txt

CLI Help

# See all available options
uv run python yt_extract_cli.py --help

CLI Features:

• Flexible output: Choose video info only, transcript only, or both
• File output: Save results directly to a file
• Progress indicators: See what's happening during extraction
• Error handling: Clear error messages for troubleshooting
• Help system: Built-in help with --help flag

Transport Protocols

This MCP server supports two transport protocols:

stdio Transport (Default - Production Use)

• Best for: Claude Desktop integration and production deployments
• Configuration: Default transport when running mcp_youtube_extractor
• Usage: Communicates via standard input/output streams
• Integration: Works seamlessly with MCP clients like Claude Desktop

SSE Transport (Testing & Debugging)

• Best for: Development, testing, and debugging MCP servers
• Configuration: HTTP-based Server-Sent Events protocol
• Benefits:
  • Easy testing with curl commands
  • Real-time monitoring of server responses
  • Web browser compatibility for quick checks
  • Detailed debugging capabilities

For comprehensive SSE testing and debugging, see the detailed guide in mcp-sse-guide.md. This guide covers:

• Setting up SSE transport for testing
• Step-by-step MCP protocol handshake sequence
• Testing with curl commands and browser
• Troubleshooting common issues
• Transport protocol comparison and use cases

Quick SSE Testing Setup:

# Start server with SSE transport (modify server.py)
mcp.run(transport="sse")  # Instead of mcp.run()

# Test with curl
curl -N -H "Accept: text/event-stream" http://127.0.0.1:8000/sse

Running Tests

# Run all pytest tests
uv run pytest

# Run specific pytest test
uv run pytest tests/test_with_api_key.py

# Run tests with coverage
uv run pytest --cov=src/mcp_youtube_extract --cov-report=term-missing

Note: The tests/ directory contains 4 files:

• test_context_fix.py - Pytest test for context API fallback functionality
• test_with_api_key.py - Pytest test for full functionality with API key
• test_youtube_unit.py - Unit tests for core YouTube functionality
• test_inspector.py - Standalone inspection script (not a pytest test)

Test Coverage: The project maintains excellent test coverage with comprehensive testing across all components:

• Core YouTube functionality thoroughly tested
• MCP protocol handling verified
• Error handling and fallback logic validated
• Professional development and testing workflow

Running the Inspection Script

The test_inspector.py file is a standalone script that connects to the MCP server and validates its functionality:

# Run the inspection script to test server connectivity and functionality
uv run python tests/test_inspector.py

This script will:

• Connect to the MCP server
• List available tools, resources, and prompts
• Test the get_yt_video_info tool with a sample video
• Validate that the server is working correctly

Using the YouTube Tool

The server provides one main tool: get_yt_video_info

This tool takes a YouTube video ID or a full URL and returns:

• Video metadata (title, description, channel, publish date)
• Video transcript (with fallback logic for different transcript types)

Example Usage:

# Using a video ID
video_id = "dQw4w9WgXcQ"
result = get_yt_video_info(video_id)

# Or using a full URL
video_url = "https://www.youtube.com/watch?v=dQw4w9WgXcQ"
result = get_yt_video_info(video_url)

Client Configuration

To use this MCP server with a client (e.g., Claude Desktop), add the following configuration to your client's settings:

Using PyPI Installation (Recommended)

{
  "mcpServers": {
    "mcp_youtube_extractor": {
      "command": "mcp_youtube_extractor",
      "env": {
        "YOUTUBE_API_KEY": "your_youtube_api_key"
      }
    }
  }
}

Using Development Setup

{
  "mcpServers": {
    "mcp_youtube_extractor": {
      "command": "uv",
      "args": [
        "--directory",
        "<your-project-directory>",
        "run",
        "mcp_youtube_extractor"
      ],
      "env": {
        "YOUTUBE_API_KEY": "your_youtube_api_key"
      }
    }
  }
}

Development

Project Structure

mcp-youtube-extractor/
├── src/
│   └── mcp_youtube_extract/
│       ├── __init__.py
│       ├── server.py          # MCP server implementation
│       ├── youtube.py         # YouTube API utilities
│       └── logger.py          # Logging configuration
├── tests/
│   ├── __init__.py
│   ├── test_context_fix.py    # Context API fallback tests
│   ├── test_inspector.py      # Server inspection tests
│   ├── test_with_api_key.py   # Full functionality tests
│   └── test_youtube_unit.py   # Unit tests for core functionality
├── logs/                      # Application logs
├── dist/                      # Built packages
├── yt_extract_cli.py          # Command-line interface script
├── mcp-sse-guide.md           # SSE transport testing guide
├── CHANGELOG.md               # A log of all notable changes to the project
├── .env.example               # Environment variables template
├── .gitignore                 # Git ignore rules
├── .python-version            # Python version specification
├── pyproject.toml             # Project configuration
├── LICENSE                    # MIT License
├── uv.lock                    # UV package lock file
└── README.md

Testing Strategy

The project uses a comprehensive testing approach:

1. Unit Tests (test_youtube_unit.py): Test core YouTube functionality with mocked APIs
2. Integration Tests (test_context_fix.py, test_with_api_key.py): Test full server functionality
3. Manual Validation (test_inspector.py): Interactive server inspection tool
4. Transport Testing: SSE transport protocol testing guide (mcp-sse-guide.md)

Error Handling

The project includes robust error handling:

• Graceful API failures: Returns appropriate error messages instead of crashing
• Fallback logic: Multiple strategies for transcript retrieval
• Consistent error responses: Standardized error message format
• Comprehensive logging: Detailed logs for debugging and monitoring

Building

# Install build dependencies
uv add --dev hatch

# Build the package
uv run hatch build

# Check package integrity
uv run twine check dist/*

# Check what was created
ls dist
mcp_youtube_extractor-0.1.0-py3-none-any.whl
mcp_youtube_extractor-0.1.0.tar.gz

Release Process

# 1. Update version in pyproject.toml
# 2. Update CHANGELOG.md
# 3. Run tests
uv run pytest tests/ -v

# 4. Build package
uv run hatch build

# 5. Upload to TestPyPI
uv run twine upload --repository testpypi dist/*

# 6. Test installation from TestPyPI
pip install --index-url https://test.pypi.org/simple/ --extra-index-url https://pypi.org/simple/ mcp-youtube-extractor

# 7. Upload to PyPI
uv run twine upload dist/*

# 8. Test installation
pip install mcp-youtube-extractor

Documentation

• README.md - Main project documentation (this file)
• CHANGELOG.md - A log of all notable changes to the project.
• mcp-sse-guide.md - Comprehensive guide for SSE transport protocol testing
• API Documentation - Inline documentation in source code
• Test Documentation - Testing strategy and coverage reports

Acknowledgments

This project is based on the original mcp_youtube_extract repository by sinjab. This enhanced version includes:

• Professional PyPI distribution as mcp-youtube-extractor
• Windows installation guide for uv and Rust toolchain
• SSE transport testing guide (mcp-sse-guide.md)
• Enhanced CLI interface with additional options
• Comprehensive transport protocol documentation
• Extended testing and debugging capabilities
• Modern dependency management with latest security updates

Special thanks to the original author for creating the foundational MCP YouTube extraction framework.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Getting Started

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

Development Workflow

1. Setup: uv sync --dev
2. Make changes: Edit code and tests
3. Test: uv run pytest tests/ -v
4. Build: uv run hatch build
5. Verify: uv run twine check dist/*

Support

If you encounter any issues or have questions, please:

1. Review the existing issues
2. Create a new issue with detailed information about your problem
3. Include logs and error messages when applicable
4. For SSE transport issues, refer to the mcp-sse-guide.md troubleshooting section

Links

• GitHub Repository: https://github.com/hwang2006/mcp-youtube-extractor
• PyPI Package: https://pypi.org/project/mcp-youtube-extractor/