PodLearn
Search 4M+ podcasts & YouTube, transcribe any episode, search transcripts, generate AI lessons.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"podlearn": {
"url": "https://httiyebjgxxwtgggkpgw.supabase.co/functions/v1/mcp-server-streamable"
}
}
}Remote endpoints
https://httiyebjgxxwtgggkpgw.supabase.co/functions/v1/mcp-server-streamablestreamable-httpWhat it can do
Tool inventory
Tools (25)
🟢search_podcasts(query)
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.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Search keywords or a podcast URL"
}
},
"required": [
"query"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢list_podcasts(limit, offset, category)
List podcasts already in the PodLearn library, optionally filtered by category. Returns most-recently-added first. For discovery beyond the library use search_podcasts.
Input Schema
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"default": 20
},
"offset": {
"type": "integer",
"minimum": 0,
"default": 0
},
"category": {
"type": "string",
"description": "Filter by category (e.g. \"Technology\")"
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_podcast_details(podcast_id)
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).
Input Schema
{
"type": "object",
"properties": {
"podcast_id": {
"type": "integer",
"description": "Local podcast id"
}
},
"required": [
"podcast_id"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢search_episodes(query, status, limit, offset)
Cross-podcast episode search by title/description AND parent podcast name/author. Returns local episodes only — for podcasts discoverable on PodcastIndex that aren't yet ingested, use list_feed_episodes instead. `status: "transcribed"` filters to ready-to-read; `status: "untranscribed"` to available-to-transcribe.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Topic, keyword, or host name"
},
"status": {
"type": "string",
"enum": [
"transcribed",
"untranscribed",
"completed",
"processing",
"failed",
"not_started"
]
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"default": 20
},
"offset": {
"type": "integer",
"minimum": 0,
"default": 0
}
},
"required": [
"query"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢list_feed_episodes(feed_id, max, since, before)
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, title, feed_id, podcast_name) — passing feed_id/podcast_name lands the episode under its real show. For episodes already in_library, use start_transcription(episode_id) instead.
Input Schema
{
"type": "object",
"properties": {
"feed_id": {
"type": "string",
"description": "PodcastIndex feed_id (the `id` from a search_podcasts result)"
},
"max": {
"type": "integer",
"minimum": 1,
"maximum": 200,
"default": 20
},
"since": {
"type": "integer",
"description": "Unix seconds — published AFTER"
},
"before": {
"type": "integer",
"description": "Unix seconds — published BEFORE (pagination)"
}
},
"required": [
"feed_id"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢list_episodes(podcast_id, limit, offset, status)
List episodes already in the local DB for a specific podcast. Requires podcast_id (use search_podcasts first if you only have a name). For cross-podcast search use search_episodes; for canonical PodcastIndex listings use list_feed_episodes.
Input Schema
{
"type": "object",
"properties": {
"podcast_id": {
"type": "integer",
"description": "Local podcast_id from search_podcasts"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"default": 20
},
"offset": {
"type": "integer",
"minimum": 0,
"default": 0
},
"status": {
"type": "string",
"enum": [
"completed",
"processing",
"failed",
"not_started"
]
}
},
"required": [
"podcast_id"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_episode_details(episode_id)
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(audio_url, title, feed_id, podcast_name) for a URL not yet in the library.
Input Schema
{
"type": "object",
"properties": {
"episode_id": {
"type": "string",
"format": "uuid"
}
},
"required": [
"episode_id"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢transcribe_url(audio_url, title, podcast_id, feed_id, podcast_name, ...)
Ingest and transcribe an EXTERNAL / arbitrary audio URL — a URL the user pasted, or audio not reachable through the index. Creates a STANDALONE episode row. If the episode is already in the library (it has an episode_id), prefer start_transcription(episode_id) instead — it inherits the episode's existing show, artwork, and feed linkage automatically. Consumes 1 transcription credit, or one unit of subscription quota; the credit is refunded automatically if transcription fails. Pass feed_id / podcast_name when you already know the parent show (e.g. from search_podcasts or list_feed_episodes) so the episode lands under its real show instead of appearing as unidentified "External audio". Returns the new episode_id. Transcription is asynchronous on the fallback path — poll get_episode_details until transcription_status is "completed".
Input Schema
{
"type": "object",
"properties": {
"audio_url": {
"type": "string",
"format": "uri",
"description": "Direct audio URL (mp3, m4a, or platform URL)"
},
"title": {
"type": "string",
"minLength": 1,
"description": "Episode title — shown in the user's library"
},
"podcast_id": {
"type": "integer",
"description": "Existing parent podcast_id, if any"
},
"feed_id": {
"type": "string",
"description": "Optional: local podcasts.id / PodcastIndex feed id of the parent show, if known. Looked up only — never creates a show."
},
"podcast_name": {
"type": "string",
"description": "Optional: exact parent show title, if known and feed_id is unavailable. Matched only when it resolves to EXACTLY ONE existing show."
},
"language": {
"type": "string",
"description": "BCP-47 hint (e.g. \"en\", \"he\"). Auto-detect if omitted."
}
},
"required": [
"audio_url",
"title"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢transcribe_feed(feed_id, max, since, before)
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 subscription quota) — CONFIRM the cost with the user first. Enqueue-and-poll: returns each enqueued episode_id; poll get_episode_details until transcription_status is "completed".
Input Schema
{
"type": "object",
"properties": {
"feed_id": {
"type": "string",
"description": "PodcastIndex feed id (from a search_podcasts / list_feed_episodes result)"
},
"max": {
"type": "integer",
"minimum": 1,
"maximum": 25,
"description": "Max episodes to enqueue (default 10, cap 25)"
},
"since": {
"type": "integer",
"description": "Optional unix-seconds; only episodes published AFTER"
},
"before": {
"type": "integer",
"description": "Optional unix-seconds; only episodes published BEFORE (page back)"
}
},
"required": [
"feed_id"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪start_transcription(episode_id)
Kick off transcription on an episode ALREADY in the library. Use only when the episode row exists and transcription_status is not "completed". Inherits the episode's existing show, artwork, and feed linkage automatically — no need to pass podcast context. For audio not yet in the library, use transcribe_url. COSTS 1 CREDIT (or subscription quota).
Input Schema
{
"type": "object",
"properties": {
"episode_id": {
"type": "string",
"format": "uuid"
}
},
"required": [
"episode_id"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_transcription(episode_id, offset, max_chars)
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>`. For focused look-up (a topic, quote, timestamp) prefer search_transcription.
Input Schema
{
"type": "object",
"properties": {
"episode_id": {
"type": "string",
"format": "uuid"
},
"offset": {
"type": "integer",
"minimum": 0,
"description": "Character offset to start from (default 0). Use next_offset from a prior page."
},
"max_chars": {
"type": "integer",
"minimum": 2000,
"maximum": 120000,
"description": "Max characters to return this call (default & max 120000)."
}
},
"required": [
"episode_id"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢search_transcription(episode_id, query)
Keyword search WITHIN a single episode's transcript. Returns matching chunks with surrounding context. Use instead of get_transcription when the user asked about a specific topic — server does this faster + cheaper on context.
Input Schema
{
"type": "object",
"properties": {
"episode_id": {
"type": "string",
"format": "uuid"
},
"query": {
"type": "string",
"minLength": 1,
"description": "Topic, phrase, or speaker name"
}
},
"required": [
"episode_id",
"query"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_transcription_segments(episode_id)
Fetch timestamped transcript segments. Use when the user wants timestamps — "jump to where they discuss X", chapter boundaries, durations of specific parts.
Input Schema
{
"type": "object",
"properties": {
"episode_id": {
"type": "string",
"format": "uuid"
}
},
"required": [
"episode_id"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢list_lessons(limit, offset)
List the calling user's saved AI-generated lessons.
Input Schema
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"default": 20
},
"offset": {
"type": "integer",
"minimum": 0,
"default": 0
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_lesson_content(lesson_id)
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.
Input Schema
{
"type": "object",
"properties": {
"lesson_id": {
"type": "string",
"format": "uuid"
}
},
"required": [
"lesson_id"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪generate_lesson(episode_id)
Generate a structured AI lesson (summary, key takeaways, sections) from a completed transcription. Requires the episode to have transcription_status "completed". Consumes 1 credit, or one unit of subscription quota, on first generation for an episode; subsequent calls return the cached lesson at no cost.
Input Schema
{
"type": "object",
"properties": {
"episode_id": {
"type": "string",
"format": "uuid"
}
},
"required": [
"episode_id"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_subscription_status
Get the caller's subscription plan + active/expired status + period end.
Input Schema
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_user_credits
Get the caller's remaining transcription credits.
Input Schema
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_episode_usage(limit, offset)
Get the caller's episode-access usage stats — how many episodes they've transcribed/read this billing period.
Input Schema
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"default": 20
},
"offset": {
"type": "integer",
"minimum": 0,
"default": 0
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_saved_items
List the caller's saved/bookmarked episodes and lessons.
Input Schema
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡save_item(item_type, item_id)
Bookmark an episode or lesson for the caller.
Input Schema
{
"type": "object",
"properties": {
"item_type": {
"type": "string",
"enum": [
"episode",
"lesson"
]
},
"item_id": {
"type": "string",
"description": "UUID of the episode or lesson to save"
}
},
"required": [
"item_type",
"item_id"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🔴remove_saved_item(saved_item_id)
Permanently remove a saved/bookmarked episode or lesson from the caller's collection. The saved_item_id comes from get_saved_items.
Input Schema
{
"type": "object",
"properties": {
"saved_item_id": {
"type": "string",
"format": "uuid"
}
},
"required": [
"saved_item_id"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡generate_linkedin_post(lesson_id, episode_id)
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.
Input Schema
{
"type": "object",
"properties": {
"lesson_id": {
"type": "string",
"format": "uuid"
},
"episode_id": {
"type": "string",
"format": "uuid"
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢search_youtube(query, max)
Discover YouTube videos by topic/keyword across all of YouTube. Use when the user wants to learn from a talk/interview/lecture and has no URL — especially when search_podcasts / search_episodes find nothing (much long-form content is YouTube-first). NO COST: pure discovery. Returns rows with a ready-to-transcribe `url`; to ingest one, confirm cost and call transcribe_url(url, title).
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"max": {
"type": "integer",
"minimum": 1,
"maximum": 25
}
},
"required": [
"query"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢browse_episodes(query, limit)
Open an interactive episode picker (card grid with thumbnails) 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.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Optional title/host filter"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 40,
"default": 12
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}Community
Evidence