About bluzername/lennys-quotes
bluzername/lennys-quotes is an MCP server published by bluzername in the Automation category: mCP server that puts 269 episodes of Lenny's Podcast product wisdom inside Claude Code, Cursor, or any MCP client. Local, free, no API keys.
The repository has 13 stars and 3 forks, with the last commit 5 days ago. Recent commit activity is the strongest signal that reported issues will get attention.
Install
git clone https://github.com/bluzername/lennys-quotesThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (5)
get_episodeGet episode details, description, YouTube link
Parameters not published.
list_guestsBrowse all 269 guests, filter by name or views
Parameters not published.
random_wisdomGet serendipitous inspiration by topic
Parameters not published.
search_quotesSearch 51,000+ transcript segments by keyword
Parameters not published.
search_quotes_smart3-phase LLM-assisted search for nuanced topics
Parameters not published.
Ask AI
Ask AI about bluzername/lennys-quotes
Powered by Claude · Grounded in docs
Security checks
Static checks derived from the repository 11 hours ago. Heuristics on the source, not an audit.
- ✓README presentThe repository ships documentation.
- !License declaredNo license file. Legally you have no right to use it in a product.
- ✓Tests presentA test suite exists in the repository.
- ✓Dependencies pinnedA lockfile pins dependency versions.
- ✓No dynamic code executionSource scan found no eval, dynamic Function, or shell execution.
- !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.
Releases
README
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
| Tool | What it does |
|---|---|
search_quotes |
BM25 full-text search over every transcript segment. Supports "exact phrases" and a guest filter. Returns speaker, episode, date and a YouTube link to the exact second. |
search_quotes_smart |
Three-step search for nuanced topics: the model expands the query, reviews candidates, and gets the final picks. |
list_guests |
Browse episodes by name, views, or date (newest first). |
get_episode |
Episode details by guest, title, slug or video id, optionally with the full transcript. |
random_wisdom |
A random substantive guest quote, optionally on a topic. |
data_status |
Episode count, newest episode, and when the data was built. |
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 ...@latestis never blocked on transcripts.
Environment variables:
| Variable | Effect |
|---|---|
LENNYS_DB |
Use this database file and never download. |
LENNYS_OFFLINE=1 |
Never touch the network; fails if nothing is cached. |
LENNYS_REFRESH_HOURS |
How often to check for new data (default 24). |
LENNYS_DATA_URL |
Alternative download URL for the gzipped database. |
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.
README fetched from the repository 11 hours ago. The original is authoritative.