Hormozi Mentor Agent
Fetches video transcripts and metadata from the Hormozi YouTube channel using the YouTube Data API v3 for RAG-based querying.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Hormozi Mentor AgentHow do I handle pricing objections in sales calls?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Hormozi Mentor Agent
Alex Hormozi RAG mentor agent. Katie calls hormozi_query() and gets answers grounded in Hormozi's actual YouTube content.
Stack
SQLite + sqlite-vec (local, always-on, no cloud DB needed)
Voyage AI
voyage-3-liteembeddings (1024 dimensions)YouTube Data API v3 +
youtube-transcriptnpmClaude
claude-sonnet-4-6for synthesisMCP server registered with mcporter
Related MCP server: harness-health-engineering
Prerequisites
sqlite-vec — install on Mac mini:
brew install sqlite-vecEnvironment variables — copy
.env.exampleto.envand fill in:YOUTUBE_API_KEY— Google Cloud Console → APIs → YouTube Data API v3 → Create KeyVOYAGE_API_KEY— sign up at voyageai.com (free tier, 5 minutes)ANTHROPIC_API_KEY— already in Mark's environment
Setup
npm install
npm run db:initIngestion
# Full channel load (run once — ~30-60 min for 600+ videos)
npm run ingest
# Subsequent manual refresh (only fetches new videos)
npm run cronQuery (CLI test)
npm run query "what would you do about cold calling pricing objections?"Run the MCP Server
# stdio mode (for mcporter)
node dist/index.js --stdio
# HTTP mode (with health endpoint + built-in weekly cron)
node dist/index.js
# http://localhost:3456/healthmcporter Registration
After building (npm run build), register with mcporter on the Mac mini:
mcporter add hormozi-mentor --command "node /path/to/hormozi-mentor/dist/index.js --stdio"Or if running as HTTP server:
mcporter add hormozi-mentor --url http://localhost:3456/mcpMac mini launchd Cron (Weekly Refresh)
Create /Library/LaunchDaemons/com.marksapp.hormozi-mentor-cron.plist:
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
<key>Label</key>
<string>com.marksapp.hormozi-mentor-cron</string>
<key>ProgramArguments</key>
<array>
<string>/usr/local/bin/node</string>
<string>/Users/mandyassistant/Desktop/MarkProjects/hormozi-mentor/dist/cron-ingest.js</string>
</array>
<key>StartCalendarInterval</key>
<dict>
<key>Weekday</key>
<integer>0</integer>
<key>Hour</key>
<integer>2</integer>
<key>Minute</key>
<integer>0</integer>
</dict>
<key>EnvironmentVariables</key>
<dict>
<key>YOUTUBE_API_KEY</key>
<string>YOUR_KEY_HERE</string>
<key>VOYAGE_API_KEY</key>
<string>YOUR_KEY_HERE</string>
<key>ANTHROPIC_API_KEY</key>
<string>YOUR_KEY_HERE</string>
<key>DB_PATH</key>
<string>/Users/mandyassistant/Desktop/MarkProjects/hormozi-mentor/hormozi.db</string>
</dict>
<key>StandardOutPath</key>
<string>/tmp/hormozi-mentor-cron.log</string>
<key>StandardErrorPath</key>
<string>/tmp/hormozi-mentor-cron.err</string>
</dict>
</plist>Load it:
sudo launchctl load /Library/LaunchDaemons/com.marksapp.hormozi-mentor-cron.plistNotes
The
books/directory is gitignored. Drop Hormozi PDFs there for book ingestion (Phase 2).The
hormozi.dbfile is gitignored. It lives on the Mac mini only.Weekly cron also runs automatically when the HTTP server is up (built into
src/index.tsvia node-cron).
This server cannot be deployed
Maintenance
Related MCP Connectors
Personal YouTube AI knowledge base powered by RAG. Query your subscribed YouTube channels.
Transcribe YouTube via Whisper. Summaries, chapters, semantic-search across your corpus.
Query core AI knowledge, essays, executable Labs, Homeric data and epistemic claims.
Run AI customer support from your terminal: conversations, knowledge base, and chat widget.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables natural language database operations and semantic document search through SQLite and vector database integration. Converts plain English instructions into SQL queries and provides RAG capabilities for uploaded documents.-
- AlicenseNot gradedqualityDmaintenanceEnables querying a local health knowledge base with hybrid RAG (vector + FTS5) and exploring backlinks between notes.MIT
- FlicenseAqualityDmaintenanceEnables indexing local documents (PDF, Markdown, text, code) into a knowledge base and querying them via semantic search using local embeddings, all running privately on your machine.4-
- AlicenseNot gradedqualityCmaintenanceProvides persistent long-term memory for LLMs via local SQLite storage and semantic search, enabling recall across sessions without external APIs.6 npm4MIT