An MCP server that provides tools to discover and retrieve podcast episodes transcripts.
| Endpoint | https://podcasts.petabloom.com/mcp (streamable-http) |
|---|---|
| Registry version | 0.2.8 |
| Now | 5 tools · grade A (92) · pin ts_e18c323730a956a4d13a6a875d6071e8 · protocol 2025-06-18 |
| First / last listed | 2026-10-27 03:51 UTC / 2026-10-27 03:51 UTC |
| Grade over time | 2026-10-27: A (92), 5 tools |
Is this your server? Own a server? ToolFit hosted watch re-checks it every 24 h ($0.25 per 30 days) or 6 h ($0.60) and sends you an HMAC-signed webhook when its tools or grade change: POST https://api.youraitools.co/toolfit/v1/watch. To opt out, see About & opt-out.
Tools: search_episodes get_latest_episodes search_episodes_by_topic get_transcript give_feedback
search_episodes | Search indexed podcast episodes by keyword or show name and return the show/episode GUIDs needed for transcript retrieval. params: query, podcast_name, published_within_hours, published_after, published_before, sort, limit, cursor |
get_latest_episodes | Return the most recent transcript-ready episodes across the full podcast catalog. params: limit, published_after, published_before, sort, cursor |
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 releva params: topic*, show_guid, published_after, published_before, limit, cursor |
get_transcript | Fetch a bounded transcript chunk for a specific episode using its show and episode GUIDs. Use `next_cursor` to continue reading. params: show_guid*, episode_guid*, cursor, max_chars |
give_feedback | Send structured feedback about bugs, missing data, unclear behavior, or feature requests. params: feedback* |
Entries describe changes in tool definitions. They are not statements about a server, its quality or its author. The grade measures how the tool definitions fit model providers (token cost, schema compatibility, confusable names) as scored by the ToolFit engine at the time of the listing. JSON: append .json. Opt-out: how or hello@youraitools.co.