Gobbler MCP - Quick Start Guide¶
Get up and running with Gobbler in 5 minutes! This guide covers the essentials to get your first transcription.
Prerequisites Checklist¶
Before you begin, ensure you have:
- [ ] Python 3.11+ - Check with
python3 --version - [ ] uv package manager - Install with
curl -LsSf https://astral.sh/uv/install.sh | sh - [ ] Docker (optional, for web/document conversion) - Download Docker
- [ ] ffmpeg (optional, for audio extraction) - Install with
brew install ffmpeg(macOS)
3 Simple Steps to Your First Transcription¶
Step 1: Install Gobbler¶
# Clone the repository
git clone https://github.com/Enablement-Engineering/gobbler.git
cd gobbler
# Install dependencies
make install
Step 2: Install to Claude Code¶
# Show the installation command
make claude-install
# Run the displayed command (example):
claude mcp add gobbler-mcp -- uv --directory /path/to/gobbler run gobbler-mcp
Restart Claude Code after installation.
Step 3: Try Your First Transcription¶
Open Claude Code and try:
That's it! Gobbler will extract the transcript and return it as clean markdown.
Verify It Works¶
Run these verification commands to ensure everything is set up correctly:
You should see: - ✅ Python 3.11+ detected - ✅ uv installed - ✅ Gobbler MCP installed
Need Web Scraping or Document Conversion?¶
If you want to use Gobbler's full feature set (web scraping, document conversion):
This starts Docker services AND the background worker: - Crawl4AI - Web scraping with JavaScript rendering - Docling - Document conversion (PDF, DOCX, PPTX, XLSX) - Redis - Background job queue - RQ Worker - Processes long-running tasks
Common First-Run Issues¶
Issue: "Python 3.11+ required"¶
Solution: Install Python 3.11 or higher from python.org
Issue: "uv not found"¶
Solution: Install uv package manager:
Issue: "Gobbler MCP not installed"¶
Solution: Run the installation:
Issue: "Docker daemon not running"¶
Solution: Start Docker Desktop or run:
Issue: "Services unavailable"¶
Solution: Start the services:
Issue: YouTube transcription works, but web scraping doesn't¶
Solution: This is normal! YouTube transcription doesn't need Docker. For web scraping:
What You Can Do Without Docker¶
Gobbler works great even without Docker! These features are available out of the box:
- ✅ YouTube transcripts - Extract official video transcripts
- ✅ YouTube playlist batch - Process entire playlists
- ✅ YouTube downloads - Download videos in various qualities
- ✅ Audio/video transcription - Whisper-based transcription with Metal acceleration
- ✅ Batch audio processing - Transcribe entire directories
Available Commands¶
Here are the most useful commands for getting started:
make help # Show all available commands
make verify # Check installation and system health
make diagnose # Run diagnostics and suggest fixes
make start # Start all services (Docker + worker)
make stop # Stop all services
make status # Check service health
make logs # View service logs
Next Steps¶
Now that you're up and running:
-
Explore capabilities - Try different types of content:
-
Read the CLI guide - Learn about all available commands in the CLI Usage guide
-
Explore skills - See all available skills in the Skills Reference
-
Configure Gobbler - Customize settings in
~/.config/gobbler/config.yml(optional)
Getting Help¶
If you run into issues:
- Run diagnostics:
make diagnose - Check service logs:
make logs - Review common issues above
- Open an issue on GitHub
Pro Tips¶
- Background processing - Long tasks automatically queue with
auto_queue=true - Batch operations - Process multiple items efficiently with batch tools
- Health checks - Use
make statusto verify all services are healthy - Configuration - Customize behavior in
~/.config/gobbler/config.yml
Happy Gobbling! 🦃