Lenny's Wisdom MCP Server
Provides structured access to actionable insights, frameworks, and leadership advice curated from episodes of Lenny's Podcast. It enables users to search for specific product management situations, compare guest perspectives, and browse a catalog of industry frameworks.
README
Lenny's Wisdom MCP Server
An MCP (Model Context Protocol) server providing structured access to wisdom from 20 curated Lenny's Podcast episodes featuring world-class product leaders.
<p align="center"> <a href="https://www.lennyspodcast.com/"> <img src="https://raw.githubusercontent.com/edisoncruz/lennys-wisdom-mcp/main/assets/lennys-podcast-logo_fixed.jpg" alt="Lenny's Podcast" width="300"/> </a> </p>
<h3 align="center">ποΈ Built with transcripts from <a href="https://www.lennyspodcast.com/">Lenny's Podcast</a></h3>
<p align="center"> <strong>Inspired by Lenny Rachitsky's generous decision to make all 320+ podcast transcripts freely available.</strong><br/> <a href="https://www.linkedin.com/posts/lennyrachitsky_here-are-the-full-transcripts-from-all-320-activity-7417011928159629313-am-q/">See his LinkedIn announcement β</a> </p>
<p align="center"> <em>This project transforms those transcripts into actionable wisdom accessible directly in your workflow via Claude Desktop.</em> </p>
Date: February 9, 2026
Status: MCP with highly adaptable foundation established. The remaining 280 transcripts will be extracted by the end of February 2026.
Why This Matters
We want to meet users where they are by making the collective wisdom of Lenny's tech titan guests available in your Claude, ChatGPT, or LLM of choice.
Instead of generic responses to prompts like "Look through these transcripts and give me frameworks about product-market fit" or "What does Brian Chesky have to say about prioritization?", this MCP server super-powers your LLM by augmenting its reasoning capabilities with the minds of the most successful leaders in tech.
Ask natural questions. Get specific, actionable advice from world-class PMsβwith context, timestamps, and quotes.
Features
π Core Tools (4)
- search_wisdom(query) - Keyword search across all episodes
- list_guests() - Browse all 20 available guests
- get_episode(episode_id) - Get full episode details
- search_by_topic(topic) - Filter by topic tags
π― Advanced Tools (5)
- get_advice_for_situation(situation) - Get curated advice for specific PM challenges
- get_actionable_insights(topic) - Filter for only immediately actionable tactics
- compare_perspectives(topic, guests) - Compare how different leaders approach the same topic
- get_quotes_by_guest(guest_name, topic) - Deep-dive into a specific leader's philosophy
- list_frameworks() - Browse all frameworks (DHM, LNO, JTBD, Pre-mortems, etc.)
π Episode Library (20 Episodes)
- Brian Chesky (Airbnb) - Founder mode, product obsession
- Claire Hughes Johnson (Stripe COO) - Scaling operations
- Matt Mochary (CEO Coach) - High output management
- Kim Scott - Radical Candor framework
- Gibson Biddle (Netflix VP Product) - DHM framework
- Shishir Mehrotra (Coda CEO) - Growth loops, Eigenquestions
- Shreyas Doshi (Stripe/Twitter) - Pre-mortems, LNO framework
- Casey Winters (Pinterest) - Kindle vs Fire strategies
- Dan Shipper (Every) - AI-first operations
- Ben Horowitz (a16z) - Running towards fear, managerial leverage
- Camille Fournier - Engineering management
- Ami Vora (Meta/WhatsApp) - Product leadership at scale
- Deb Liu (Ancestry CEO) - 30/60/90 onboarding
- April Dunford - Positioning frameworks
- Bob Moesta - Jobs to Be Done
- Annie Duke - Decision-making under uncertainty
- Bangaly Kaba (Instagram) - Growth loops
- Bret Taylor (ex-Salesforce Co-CEO) - Product-led growth
- Drew Houston (Dropbox) - Founder mode, scaling
- Dharmesh Shah (HubSpot) - Culture as product
Installation
Option 1: Claude Desktop or ChatGPT Desktop
1. Install the package:
pip install -e /path/to/lennys-wisdom-mcp
2. Configure Claude Desktop:
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%/Claude/claude_desktop_config.json (Windows):
{
"mcpServers": {
"lennys-wisdom": {
"command": "python",
"args": ["/path/to/lennys-wisdom-mcp/lennys_wisdom/server.py"]
}
}
}
3. Restart Claude Desktop
Option 2: Claude Code or Cowork
Claude Code and Cowork automatically detect MCP servers installed via pip:
pip install -e /path/to/lennys-wisdom-mcp
# MCP server is now available in Claude Code/Cowork
Usage Examples
"I'm joining a new company as VP Product, what should I do?"
β get_advice_for_situation() returns curated advice from multiple leaders
"Show me actionable insights about hiring"
β get_actionable_insights() filters for immediately implementable advice
"How do Brian Chesky and Ben Horowitz approach leadership differently?"
β compare_perspectives() shows side-by-side comparison
"What frameworks are available?"
β list_frameworks() catalogs DHM, LNO, JTBD, Pre-mortems, etc.
Technical Overview
Architecture: FastMCP server with 9 tools accessing 280+ insights from 20 manually extracted episodes (~320,000 words processed)
Data Format: JSON files with 15 key insights per episode, including verbatim quotes, timestamps, themes with relevance scores, topic tags, frameworks, and actionable flags
Search: Keyword matching with relevance scoring
Output: Markdown-formatted responses
Extracted: February 2026 using Claude Sonnet 4.5
Contributing
Contributions welcome! Please submit a Pull Request.
Additional Resources
- Official Podcast Transcripts - Full verbatim transcripts of all episodes (maintained by Lenny's co-host)
- Lenny's Podcast - Subscribe to the podcast
- Lenny's Newsletter - Product management insights and advice
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.