PodLearn MCP Server
Enables transcription, search, and lesson generation from podcast and YouTube URLs directly inside Claude Code.
README
<div align="center">
🎧 PodLearn for Claude Code
Stop listening. Start learning.
The podcast & video knowledge engine, right inside Claude Code. Drop a link. Get a verbatim transcript, a searchable archive, and an AI lesson in seconds.
</div>
Some of the best thinking on the planet is locked inside hours of audio you'll never have time for. PodLearn unlocks it. Hand Claude any podcast or YouTube URL and it transcribes the whole thing (yes, even long talks with no captions), makes every word searchable, and distills the ideas into a structured lesson. No tab-switching, no copy-paste, no "I'll get to it later."
One install adds the PodLearn skill and MCP server to Claude Code. The skill handles the routing; the MCP does the work. You just talk.
✨ Why people use it
- ⏱️ Hours → minutes. A 2-hour interview becomes a transcript + lesson you skim in five.
- 🔎 Find the exact moment. Full-text search across every transcript, with citations. "Where did they talk about pricing?" jumps you straight there.
- ▶️ YouTube that actually works. Paste any video, captions or not. Conference talks, lectures, channel deep-dives, all transcribed natively.
- 📚 Bulk a whole season.
transcribe_feedingests an entire podcast feed in one shot, not episode-by-episode. - 🧠 Lessons, not just text. Auto-generated key takeaways and structured notes you can act on.
- 🤖 Agent-native. It's a real MCP server, so every call composes with the rest of your Claude workflow (turn a lesson into a LinkedIn post, feed quotes into a doc, whatever).
💬 What you can ask
"What podcasts do you have about AI agents?" "Transcribe this and make me a lesson: ‹youtube or podcast URL›" "Find the best quotes about pricing from ‹episode›" "Transcribe the last 10 episodes of ‹podcast› and summarize the themes." "Turn that lesson into a LinkedIn post."
⚡ Install (60 seconds)
1. Grab your token (free, 2 credits to try) at podlearn.ai/settings — a
pl_mcp_…token. Keep it handy.
2. Add the marketplace — in Claude Code (run this on its own, wait for confirmation):
/plugin marketplace add blutrich/podlearn-plugin
3. Install the plugin — then run:
/plugin install podlearn@podlearn
⚠️ Run them one at a time — they're two separate slash commands. Pasting both lines at once makes Claude treat the second as part of the first.
4. Paste your token when prompted. Claude Code asks for your PodLearn MCP
token on install. It's stored in your system keychain (never a settings file,
never an env var), and the bundled MCP authenticates automatically — no
separate claude mcp add, the plugin registers the server for you.
5. Restart Claude Code (or claude reload) and start asking.
That's it. The plugin ships the skill and the MCP, so there's no separate
claude mcp add step and nothing to wire up by hand.
📦 What's inside
Skill (podlearn) |
Routes your intent through the MCP tools so you never think about which one to call. |
| MCP server | search_podcasts · search_youtube · search_episodes · list_feed_episodes · transcribe_url · transcribe_feed (bulk/season) · get_transcription · search_transcription · generate_lesson · generate_linkedin_post · and more. |
🔌 Just the MCP server (without the plugin)
The plugin already bundles the server, so most people don't need this. But if you want the MCP on its own — in Claude Desktop, Cursor, ChatGPT, or any other MCP client, or in Claude Code without the skill — add it directly.
Claude Code (one command, with your token from podlearn.ai/settings):
claude mcp add --transport http podlearn \
https://httiyebjgxxwtgggkpgw.supabase.co/functions/v1/mcp-server-streamable \
--header "Authorization: Bearer pl_mcp_YOUR_TOKEN"
Any MCP client (Desktop, Cursor, etc.) — point it at the Streamable HTTP endpoint:
| Field | Value |
|---|---|
| Transport | Streamable HTTP (http) |
| URL | https://httiyebjgxxwtgggkpgw.supabase.co/functions/v1/mcp-server-streamable |
| Header | Authorization: Bearer pl_mcp_YOUR_TOKEN |
Generate the pl_mcp_… token at podlearn.ai/settings.
Full tool reference: podlearn.ai/mcp-docs.
🔄 Manage
/plugin marketplace update podlearn # pull the latest
/plugin uninstall podlearn@podlearn # remove the plugin
/plugin marketplace remove podlearn # remove the marketplace
🔐 Notes
- Your data, your token. The MCP authenticates with the token you entered on
the install prompt (stored in your keychain). Auth error? Re-check it in
/pluginconfig or generate a fresh one at podlearn.ai/settings. - Transparent pricing. Reading and searching transcripts already in your
library is free. Paid actions (
transcribe_url,transcribe_feed,generate_lesson) spend PodLearn credits, and the skill confirms the cost before charging. Start with 2 free credits; top up or subscribe at podlearn.ai.
🌐 Also available
PodLearn runs as a web app at podlearn.ai and as an MCP server for Claude Desktop, ChatGPT, Cursor, and any MCP-compatible client. This plugin is the fastest way to use it from Claude Code.
📄 License
AGPL-3.0 — © 2026 Ofer Blutrich. Built on the PodLearn platform.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。