Lennys Quotes

Lenny's Podcast Wisdom

MCP server for AI-powered product management insights

Query every episode of Lenny's Podcast from Claude Code, Cursor, or any MCP client.

Credit: built on the content of Lenny Rachitsky's Podcast, the #1 podcast for product people. Transcripts are the official ones Lenny publishes. Subscribe to support his work.

Why

Lenny's Podcast is a goldmine of product wisdom from leaders at Airbnb, Stripe, Netflix, OpenAI, Anthropic and more. This server makes all of it searchable by your AI assistant while you write PRDs, plan roadmaps, or make product calls.

No API keys. No LLM costs. Runs locally. Updates itself every week.

Installation

Requires Node 22.13 or newer.

claude mcp add lennys-wisdom -- npx -y lennys-podcast-wisdom@latest

Or install globally:

npm install -g lennys-podcast-wisdom
claude mcp add lennys-wisdom -- lennys-wisdom

For Cursor or other clients, add a stdio server with command npx and args -y lennys-podcast-wisdom@latest.

The first start downloads the transcript database (about 22 MB) into ~/.cache/lennys-wisdom/. Later starts are instant.

Usage

Ask naturally:

"Search Lenny's podcast for advice on product-market fit"
"What does Brian Chesky say about design?"
"What are the newest episodes?"
"Give me random wisdom about leadership"

Tools

How it stays current

Lenny's Dropbox (official transcripts)  +  YouTube RSS / yt-dlp (metadata)
                    |
        weekly GitHub Action: npm run sync
                    |
        episodes/{slug}/transcript.md  (committed, diffable)
                    |
        npm run build:db  ->  SQLite + FTS5  ->  GitHub release "data"
                    |
        your server checks for a newer database once a day and swaps it in

• New episodes land in the repo every Monday without a code release.
• Installed servers refresh their local database in the background; no reinstall needed.
• Code releases (npm) and data releases are independent, so npx ...@latest is never blocked on transcripts.

Environment variables:

Development

npm install
npm test                 # unit tests (node:test)
npm run build:db         # episodes/ -> data/lennys.db
npm run smoke            # spawn the server over stdio and exercise every tool
npm run sync -- --dry-run

To run the server from source against a local database: LENNYS_DB=data/lennys.db npm run dev.

Data source

Transcript text is Lenny's own public Dropbox folder of episode transcripts. Metadata comes from the YouTube channel. The initial archive was seeded from ChatPRD/lennys-podcast-transcripts and the matching logic was adapted from sdmurff's sync script. Thanks to both.

License

MIT for the code. Transcript content belongs to Lenny Rachitsky and is redistributed for personal and research use; please credit the podcast.