# PodLearn

- Registry name: `io.github.blutrich/podlearn` · version 1.1.0
- Categories (automatic, keyword rules): Audio & speech, AI, media & content
- Authentication at last check: No auth
- Declared risk: Has destructive tools (destructiveHint)
- Capabilities (declared by the server): resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.blutrich%2Fpodlearn
- Server page: https://mcpstation.net/s/io.github.blutrich--podlearn.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://podlearn.ai/mcp`

## Tools (as reported by the server, not verified)

- `search\_podcasts`: Search PodLearn library AND PodcastIndex.org \(4M+ podcasts\) by keyword. Also resolves Spotify/Apple Podcasts URLs. Returns rows tagged with \`source: local\|podcastindex\|spotify\`. First move when the user names a podcast/host but you don't have its id.
- `list\_podcasts`: List podcasts already in the PodLearn library, optionally filtered by category. Returns most-recently-added first. For discovery beyond the library use search\_podcasts.
- `get\_podcast\_details`: Fetch full metadata for one podcast in the PodLearn library, including its episode count. The podcast must already be in the local DB \(source=local in search\_podcasts results\).
- `search\_episodes`: Cross-podcast episode search by title/description AND parent podcast name/author. Returns local episodes only — for podcasts discoverable on PodcastIndex that aren't yet ingested, use list\_feed\_episodes instead. \`status: "transcribed"\` filters to ready-to-read; \`status: "untranscribed"\` to available
- `list\_feed\_episodes`: Fetch the canonical episode list for a podcast directly from PodcastIndex \(the upstream RSS index\). NO COST — pure discovery. Each episode is enriched with \`in\_library\`, \`episode\_id\` \(if already ingested\), and \`transcription\_status\`. For episodes you want to ingest: call transcribe\_url\(audio\_url, ti
- `list\_episodes`: List episodes already in the local DB for a specific podcast. Requires podcast\_id \(use search\_podcasts first if you only have a name\). For cross-podcast search use search\_episodes; for canonical PodcastIndex listings use list\_feed\_episodes.
- `get\_episode\_details`: Fetch full metadata for one episode including transcription\_status and lesson\_generation\_status. Tells you whether get\_transcription is ready or you need to transcribe first: start\_transcription\(episode\_id\) for an in-library episode \(inherits its existing show/artwork/feed linkage automatically\) or
- `transcribe\_url`: Ingest and transcribe an EXTERNAL / arbitrary audio URL — a URL the user pasted, or audio not reachable through the index. Creates a STANDALONE episode row. If the episode is already in the library \(it has an episode\_id\), prefer start\_transcription\(episode\_id\) instead — it inherits the episode's exi
- `transcribe\_feed`: Bulk/season transcription — kick off transcription for up to \`max\` \(cap 25\) not-yet-transcribed episodes of a podcast feed in ONE call. Pass the \`feed\_id\` from search\_podcasts / list\_feed\_episodes. Already-transcribed episodes are skipped free. COSTS 1 credit per newly enqueued episode \(or subscript
- `start\_transcription`: Kick off transcription on an episode ALREADY in the library. Use only when the episode row exists and transcription\_status is not "completed". Inherits the episode's existing show, artwork, and feed linkage automatically — no need to pass podcast context. For audio not yet in the library, use transc
- `get\_transcription`: Fetch transcript text for a completed episode. PAGINATED — returns up to 120,000 characters per call \(Claude.ai/Desktop caps a tool result at \~150k chars\). Most transcripts fit in one call; only very long episodes page. If the response has \`has\_more: true\`, call again with \`offset: \<next\_offset\>\`. F
- `search\_transcription`: Keyword search WITHIN a single episode's transcript. Returns matching chunks with surrounding context. Use instead of get\_transcription when the user asked about a specific topic — server does this faster + cheaper on context.
- `get\_transcription\_segments`: Fetch timestamped transcript segments. Use when the user wants timestamps — "jump to where they discuss X", chapter boundaries, durations of specific parts.
- `list\_lessons`: List the calling user's saved AI-generated lessons.
- `get\_lesson\_content`: Fetch the full body of one AI-generated lesson \(title, summary, key takeaways, structured sections\). Use to retrieve prior synthesis — for creating a NEW one call generate\_lesson.
- `generate\_lesson`: Generate a structured AI lesson \(summary, key takeaways, sections\) from a completed transcription. Requires the episode to have transcription\_status "completed". Consumes 1 credit, or one unit of subscription quota, on first generation for an episode; subsequent calls return the cached lesson at no
- `get\_subscription\_status`: Get the caller's subscription plan + active/expired status + period end.
- `get\_user\_credits`: Get the caller's remaining transcription credits.
- `get\_episode\_usage`: Get the caller's episode-access usage stats — how many episodes they've transcribed/read this billing period.
- `get\_saved\_items`: List the caller's saved/bookmarked episodes and lessons.
- `save\_item`: Bookmark an episode or lesson for the caller.
- `remove\_saved\_item`: Permanently remove a saved/bookmarked episode or lesson from the caller's collection. The saved\_item\_id comes from get\_saved\_items.
- `generate\_linkedin\_post`: Turn an already-generated lesson into a LinkedIn-ready share post. Pass lesson\_id directly OR episode\_id \(uses the most recent lesson generated by the caller for that episode\). Lesson must exist — chain after generate\_lesson if needed.
- `search\_youtube`: Discover YouTube videos by topic/keyword across all of YouTube. Use when the user wants to learn from a talk/interview/lecture and has no URL — especially when search\_podcasts / search\_episodes find nothing \(much long-form content is YouTube-first\). NO COST: pure discovery. Returns rows with a ready
- `browse\_episodes`: Open an interactive episode picker \(cards with show, title, and status\) for the user to pick an episode to read. On hosts that render MCP Apps the grid is clickable; everywhere else a markdown table is returned. Optional query filters by title/host.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html