MCP Server

podcasts

com.petabloom/podcasts
Media & Content Search & Research Public & reachable MCP 2025-11-25

What this MCP does

Searches podcast episodes by keywords or topics and retrieves bounded transcript segments.

get_latest_episodes
Get Latest Episodes
Return the most recent transcript-ready episodes across the full podcast catalog.
Read only Idempotent
Input schema
{'type': 'object', 'properties': {'sort': {'enum': ['relevance', 'published_desc', 'published_asc'], 'type': 'string', 'default': 'published_desc', 'description': 'Sort order for results. `relevance` ranks full-text searches first and falls back to newest-first when no query is provided.'}, 'limit': {'type': 'integer', 'default': 5, 'maximum': 50, 'minimum': 1, 'description': 'Maximum number of episodes to return. Must be between 1 and 50.'}, 'cursor': {'type': 'integer', 'default': 0, 'minimum': 0, 'description': 'Zero-based episode offset for pagination. Use the `next_cursor` returned by a prior search/listing call to fetch the next page of results.'}, 'published_after': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Inclusive lower publication-date bound. Accepts YYYY-MM-DD or ISO 8601 datetime.'}, 'published_before': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Inclusive upper publication-date bound. Accepts YYYY-MM-DD or ISO 8601 datetime.'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'required': ['episodes', 'count', 'total_count'], 'properties': {'count': {'type': 'integer', 'description': 'Number of episodes returned on this page.'}, 'episodes': {'type': 'array', 'items': {'type': 'object', 'required': ['show_guid', 'show_title', 'episode_guid', 'episode_title', 'published_date', 'rss_feed_url', 'description'], 'properties': {'show_guid': {'type': 'string', 'description': 'Podcast show GUID.'}, 'show_title': {'type': 'string', 'description': 'Podcast show title.'}, 'description': {'type': 'string', 'description': 'Episode description, truncated for search result display.'}, 'episode_guid': {'type': 'string', 'description': 'Podcast episode GUID.'}, 'rss_feed_url': {'type': 'string', 'description': 'RSS feed URL for the podcast show.'}, 'episode_title': {'type': 'string', 'description': 'Podcast episode title.'}, 'published_date': {'type': 'string', 'description': 'Episode publication timestamp in ISO 8601 format.'}, 'duration_seconds': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Episode duration in seconds when available from the source feed.'}}}, 'description': 'Matching transcript-ready episodes.'}, 'next_cursor': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Cursor to pass to the next search call to retrieve the next page of results, or null if there are no more pages.'}, 'total_count': {'type': 'integer', 'description': 'Total number of matching transcript-ready episodes across all pages.'}, 'total_count_is_approximate': {'type': 'boolean', 'default': False, 'description': 'When true, `total_count` is a lower bound — more matches may exist than were counted. False for exact lexical/date counts; can be true only for semantic results (e.g. the topic-search fallback).'}}}
get_transcript
Get Transcript
Fetch a bounded transcript chunk for a specific episode using its show and episode GUIDs. Use `next_cursor` to continue reading.
Read only Idempotent
Input schema
{'type': 'object', 'required': ['show_guid', 'episode_guid'], 'properties': {'cursor': {'type': 'integer', 'default': 0, 'minimum': 0, 'description': 'Zero-based character offset into the transcript. Use the `next_cursor` returned by a prior get_transcript call to fetch the next chunk.'}, 'max_chars': {'type': 'integer', 'default': 12000, 'maximum': 20000, 'minimum': 100, 'description': 'Target maximum number of transcript characters to return. Chunks prefer natural boundaries and may be slightly shorter. Must be between 100 and 20000.'}, 'show_guid': {'type': 'string', 'minLength': 1, 'description': 'Podcast show GUID returned by `search_episodes` or `get_latest_episodes`.'}, 'episode_guid': {'type': 'string', 'minLength': 1, 'description': 'Episode GUID returned by `search_episodes` or `get_latest_episodes`.'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'required': ['show_guid', 'show_title', 'episode_guid', 'episode_title', 'published_date', 'rss_feed_url', 'text', 'total_chars', 'char_start', 'char_end', 'has_more'], 'properties': {'text': {'type': 'string', 'description': 'Transcript chunk text.'}, 'char_end': {'type': 'integer', 'description': 'Exclusive zero-based end offset of this chunk in the complete transcript.'}, 'has_more': {'type': 'boolean', 'description': 'Whether another get_transcript call is needed to continue reading.'}, 'show_guid': {'type': 'string', 'description': 'Podcast show GUID requested by the client.'}, 'char_start': {'type': 'integer', 'description': 'Inclusive zero-based start offset of this chunk in the complete transcript.'}, 'show_title': {'type': 'string', 'description': 'Podcast show title.'}, 'next_cursor': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Cursor to pass to the next get_transcript call, or null at the end.'}, 'total_chars': {'type': 'integer', 'description': 'Total character count of the complete transcript text.'}, 'episode_guid': {'type': 'string', 'description': 'Podcast episode GUID requested by the client.'}, 'rss_feed_url': {'type': 'string', 'description': 'RSS feed URL for the podcast show.'}, 'episode_title': {'type': 'string', 'description': 'Podcast episode title.'}, 'published_date': {'type': 'string', 'description': 'Episode publication timestamp in ISO 8601 format.'}, 'duration_seconds': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Episode duration in seconds when available from the source feed.'}}}
give_feedback
Give Feedback
Send structured feedback about bugs, missing data, unclear behavior, or feature requests.
Open world
Input schema
{'type': 'object', 'required': ['feedback'], 'properties': {'feedback': {'type': 'string', 'minLength': 1, 'description': 'Feedback for the server team. Include the problem, missing capability, or suggested improvement without sensitive user data.'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'required': ['status', 'feedback_id', 'message'], 'properties': {'status': {'enum': ['saved', 'logged'], 'type': 'string', 'description': 'Feedback persistence status.'}, 'message': {'type': 'string', 'description': 'Human-readable result summary.'}, 'feedback_id': {'type': 'string', 'description': 'Stable feedback identifier.'}}}
search_episodes
Search Episodes
Search indexed podcast episodes by keyword or show name and return the show/episode GUIDs needed for transcript retrieval.
Read only Idempotent
Input schema
{'type': 'object', 'properties': {'sort': {'enum': ['relevance', 'published_desc', 'published_asc'], 'type': 'string', 'default': 'relevance', 'description': 'Sort order for results. `relevance` ranks full-text searches first and falls back to newest-first when no query is provided.'}, 'limit': {'type': 'integer', 'default': 5, 'maximum': 50, 'minimum': 1, 'description': 'Maximum number of episodes to return. Must be between 1 and 50.'}, 'query': {'type': 'string', 'default': '', 'description': 'Optional search keywords matched against indexed episode content. Use people, topics, companies, or phrases.'}, 'cursor': {'type': 'integer', 'default': 0, 'minimum': 0, 'description': 'Zero-based episode offset for pagination. Use the `next_cursor` returned by a prior search/listing call to fetch the next page of results.'}, 'podcast_name': {'type': 'string', 'default': '', 'description': 'Optional podcast title or internal label to narrow results to a specific show.'}, 'published_after': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Inclusive lower publication-date bound. Accepts YYYY-MM-DD or ISO 8601 datetime.'}, 'published_before': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Inclusive upper publication-date bound. Accepts YYYY-MM-DD or ISO 8601 datetime.'}, 'published_within_hours': {'anyOf': [{'type': 'integer', 'maximum': 168, 'minimum': 1}, {'type': 'null'}], 'default': None, 'description': 'Filter episodes published in the past X hours. Maximum 168 hours (1 week).'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'required': ['episodes', 'count', 'total_count'], 'properties': {'count': {'type': 'integer', 'description': 'Number of episodes returned on this page.'}, 'episodes': {'type': 'array', 'items': {'type': 'object', 'required': ['show_guid', 'show_title', 'episode_guid', 'episode_title', 'published_date', 'rss_feed_url', 'description'], 'properties': {'show_guid': {'type': 'string', 'description': 'Podcast show GUID.'}, 'show_title': {'type': 'string', 'description': 'Podcast show title.'}, 'description': {'type': 'string', 'description': 'Episode description, truncated for search result display.'}, 'episode_guid': {'type': 'string', 'description': 'Podcast episode GUID.'}, 'rss_feed_url': {'type': 'string', 'description': 'RSS feed URL for the podcast show.'}, 'episode_title': {'type': 'string', 'description': 'Podcast episode title.'}, 'published_date': {'type': 'string', 'description': 'Episode publication timestamp in ISO 8601 format.'}, 'duration_seconds': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Episode duration in seconds when available from the source feed.'}}}, 'description': 'Matching transcript-ready episodes.'}, 'next_cursor': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Cursor to pass to the next search call to retrieve the next page of results, or null if there are no more pages.'}, 'total_count': {'type': 'integer', 'description': 'Total number of matching transcript-ready episodes across all pages.'}, 'total_count_is_approximate': {'type': 'boolean', 'default': False, 'description': 'When true, `total_count` is a lower bound — more matches may exist than were counted. False for exact lexical/date counts; can be true only for semantic results (e.g. the topic-search fallback).'}}}
search_episodes_by_topic
Search Episodes by Topic
Semantic topic search across the podcast catalog. Unlike `search_episodes` (which does lexical/keyword matching), this tool understands meaning: a query for 'AI safety' will match episodes about 'AI alignment', 'AGI risk', or 'frontier model evaluation' even if they don't contain the exact phrase. Returns ranked episodes with the matched topic phrases so you can explain *why* each result is relevant before fetching the transcript. Best for conceptual or thematic queries — use `search_episodes` instead when the user is looking for a specific person, product, or verbatim phrase.
Read only Idempotent
Input schema
{'type': 'object', 'required': ['topic'], 'properties': {'limit': {'type': 'integer', 'default': 5, 'maximum': 50, 'minimum': 1, 'description': 'Maximum number of episodes to return. Must be between 1 and 50.'}, 'topic': {'type': 'string', 'maxLength': 300, 'minLength': 1, 'description': "Semantic topic to find episodes about. Free-form phrasing welcome — the server embeds this string and finds episodes whose extracted topic phrases are closest in meaning. Good examples: 'AI safety', 'EU AI Act regulation', 'GPU supply constraints', 'Theo Epstein on roster construction'. Distinct from `search_episodes`, which performs lexical keyword matching."}, 'cursor': {'type': 'integer', 'default': 0, 'minimum': 0, 'description': 'Zero-based episode offset for pagination. Use the `next_cursor` returned by a prior search/listing call to fetch the next page of results.'}, 'show_guid': {'type': 'string', 'default': '', 'description': 'Optional canonical show GUID (as returned by `search_episodes` or `get_latest_episodes` in the `show_guid` field) to restrict topic search to a single podcast. Leave empty to search across all shows.'}, 'published_after': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Inclusive lower publication-date bound. Accepts YYYY-MM-DD or ISO 8601 datetime.'}, 'published_before': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Inclusive upper publication-date bound. Accepts YYYY-MM-DD or ISO 8601 datetime.'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'required': ['episodes', 'count', 'query', 'total_count'], 'properties': {'count': {'type': 'integer', 'description': 'Number of episodes returned on this page.'}, 'query': {'type': 'string', 'description': 'The topic query that was embedded and searched.'}, 'episodes': {'type': 'array', 'items': {'type': 'object', 'required': ['show_guid', 'show_title', 'episode_guid', 'episode_title', 'published_date', 'rss_feed_url', 'description', 'matched_topics', 'best_similarity'], 'properties': {'show_guid': {'type': 'string', 'description': 'Podcast show GUID.'}, 'show_title': {'type': 'string', 'description': 'Podcast show title.'}, 'description': {'type': 'string', 'description': 'Episode description, truncated for search result display.'}, 'episode_guid': {'type': 'string', 'description': 'Podcast episode GUID.'}, 'rss_feed_url': {'type': 'string', 'description': 'RSS feed URL for the podcast show.'}, 'episode_title': {'type': 'string', 'description': 'Podcast episode title.'}, 'matched_topics': {'type': 'array', 'items': {'type': 'object', 'required': ['phrase', 'similarity'], 'properties': {'phrase': {'type': 'string', 'description': 'The extracted topic phrase that matched. Useful for explaining to the user why this episode came back for their query.'}, 'similarity': {'type': 'number', 'description': 'Cosine similarity between the query and this topic phrase, in [0.0, 1.0]. Higher is more semantically similar.'}}}, 'description': 'Topic phrases from this episode that matched the query, ordered by similarity (best first). Use these to summarize *why* the episode is relevant before fetching the full transcript.'}, 'published_date': {'type': 'string', 'description': 'Episode publication timestamp in ISO 8601 format.'}, 'best_similarity': {'type': 'number', 'description': 'Similarity of the strongest topic match — the value the episodes were sorted by.'}, 'duration_seconds': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Episode duration in seconds when available from the source feed.'}}}, 'description': 'Episodes ranked by best topic-phrase similarity to the query.'}, 'next_cursor': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Cursor to pass to the next search call to retrieve the next page of results, or null if there are no more pages.'}, 'total_count': {'type': 'integer', 'description': 'Number of matching episodes, counted over the nearest-match candidate window rather than the whole catalog. When `total_count_is_approximate` is true, treat this as a lower bound — broad queries may have more matches than reported.'}, 'total_count_is_approximate': {'type': 'boolean', 'default': False, 'description': 'True when the candidate window was exhausted, so `total_count` undercounts the true number of matches. When false, `total_count` is exact. Refine the query for tighter results if this is true and you need a complete set.'}}}
Added
give_feedback
Sept. 21, 2026, 2:48 a.m.
Added
get_transcript
Sept. 21, 2026, 2:48 a.m.
Added
search_episodes_by_topic
Sept. 21, 2026, 2:48 a.m.
Added
get_latest_episodes
Sept. 21, 2026, 2:48 a.m.
Added
search_episodes
Sept. 21, 2026, 2:48 a.m.