com.petabloom/podcasts

Official5 tools

An MCP server that provides tools to discover and retrieve podcast episodes transcripts.

Discovers and retrieves podcast episode transcripts through MCP server tools.

Captured live from the server via tools/list.

search_episodes

Search indexed podcast episodes by keyword or show name and return the show/episode GUIDs needed for transcript retrieval.

Parameters (8)

querystring
Optional search keywords matched against indexed episode content. Use people, topics, companies, or phrases.
podcast_namestring
Optional podcast title or internal label to narrow results to a specific show.
published_within_hoursany
Filter episodes published in the past X hours. Maximum 168 hours (1 week).
published_afterany
Inclusive lower publication-date bound. Accepts YYYY-MM-DD or ISO 8601 datetime.
published_beforeany
Inclusive upper publication-date bound. Accepts YYYY-MM-DD or ISO 8601 datetime.
sortstring
Sort order for results. `relevance` ranks full-text searches first and falls back to newest-first when no query is provided.
limitinteger
Maximum number of episodes to return. Must be between 1 and 50.
cursorinteger
Zero-based episode offset for pagination. Use the `next_cursor` returned by a prior search/listing call to fetch the next page of results.

get_latest_episodes

Return the most recent transcript-ready episodes across the full podcast catalog.

Parameters (5)

limitinteger
Maximum number of episodes to return. Must be between 1 and 50.
published_afterany
Inclusive lower publication-date bound. Accepts YYYY-MM-DD or ISO 8601 datetime.
published_beforeany
Inclusive upper publication-date bound. Accepts YYYY-MM-DD or ISO 8601 datetime.
sortstring
Sort order for results. `relevance` ranks full-text searches first and falls back to newest-first when no query is provided.
cursorinteger
Zero-based episode offset for pagination. Use the `next_cursor` returned by a prior search/listing call to fetch the next page of results.

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.

Parameters (6)

topicstringrequired
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.
show_guidstring
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_afterany
Inclusive lower publication-date bound. Accepts YYYY-MM-DD or ISO 8601 datetime.
published_beforeany
Inclusive upper publication-date bound. Accepts YYYY-MM-DD or ISO 8601 datetime.
limitinteger
Maximum number of episodes to return. Must be between 1 and 50.
cursorinteger
Zero-based episode offset for pagination. Use the `next_cursor` returned by a prior search/listing call to fetch the next page of results.

get_transcript

Fetch a bounded transcript chunk for a specific episode using its show and episode GUIDs. Use `next_cursor` to continue reading.

Parameters (4)

show_guidstringrequired
Podcast show GUID returned by `search_episodes` or `get_latest_episodes`.
episode_guidstringrequired
Episode GUID returned by `search_episodes` or `get_latest_episodes`.
cursorinteger
Zero-based character offset into the transcript. Use the `next_cursor` returned by a prior get_transcript call to fetch the next chunk.
max_charsinteger
Target maximum number of transcript characters to return. Chunks prefer natural boundaries and may be slightly shorter. Must be between 100 and 20000.

give_feedback

Send structured feedback about bugs, missing data, unclear behavior, or feature requests.

Parameters (1)

feedbackstringrequired
Feedback for the server team. Include the problem, missing capability, or suggested improvement without sensitive user data.

Install

claude_desktop_config.json

{
  "mcpServers": {
    "podcasts": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://podcasts.petabloom.com/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.