# PodLearn [Health: Active]

**Category:** 🎙️ Podcasts  
**Repository:** https://github.com/blutrich/podlearn-plugin  
**GitHub Stars:** 2  
**Views:** 3  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/podlearn

## Description
Search 4M+ podcasts & YouTube, transcribe any episode, search transcripts, generate AI lessons.

## Claude Desktop Quick Installation
No confirmed install details yet, so no config is published. Follow the setup steps in the repository above.

## Documentation

## What PodLearn MCP server does

PodLearn MCP server brings podcast and YouTube research into MCP-compatible clients. It searches more than four million podcasts and YouTube content, finds episodes and feed entries, and processes media into transcripts. Once content is in the PodLearn library, an agent can search the transcript text and retrieve the full transcription.

It can generate key takeaways and notes from a transcript, and it includes a tool for converting a lesson into a LinkedIn post. These capabilities make it relevant to the 🎙️ Podcasts category, as well as workflows involving lectures, interviews, conference talks, and other long-form videos.

## How it works

PodLearn MCP server is available as a hosted Streamable HTTP service at `https://podlearn.ai/mcp`. An MCP client connects to that endpoint and authenticates with OAuth through a PodLearn account. Headless clients can use a personal API token in an `Authorization: Bearer ...` header instead. Tokens should not be placed in the URL.

The tool set covers discovery, ingestion, retrieval, and transformation. Search tools locate podcasts, YouTube videos, or episodes. `list_feed_episodes` enumerates episodes from a feed. `transcribe_url` handles one podcast or YouTube URL, while `transcribe_feed` can process a complete feed in bulk. `get_transcription` retrieves stored text, and `search_transcription` finds terms or passages within saved transcripts.

## Setup and configuration

Claude Code users can install the repository’s plugin through the Claude Code marketplace. The plugin includes both a routing skill and the MCP server, so a separate manual MCP registration is not required for that installation path. After restarting Claude Code, authenticate the `podlearn` server from `/mcp` and approve read-only or read-and-write access in the browser.

For direct connections, configure an MCP client with the hosted URL and OAuth. The README gives direct commands for Claude Code and Codex, and also documents custom-connector setup for Claude. Cursor and other MCP clients can use the same Streamable HTTP endpoint when they support the required connection and authentication flow.

## Limitations and notes

A PodLearn account is required. Reading and searching transcripts already stored in the library is free, while `transcribe_url`, `transcribe_feed`, and `generate_lesson` consume PodLearn credits. The service starts with two free credits, and the skill confirms paid actions before charging.

Permissions affect available operations. A read-only OAuth approval will not provide write access; re-authentication is required when the client reports an insufficient scope. For browserless use, create a personal token in PodLearn settings and send it as a bearer header. The repository is licensed under AGPL-3.0.

_Full upstream README: https://allmcps.com/mcp/podlearn/readme_