OpenNash Podcasts
Server Details
Search transcripts and sourced quotes from business and tech podcasts. Read-only, no key.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 10 tools
The specific tools (get_episode, get_topic, get_transcript, search_facts, search_transcripts) target clearly distinct resource+action pairs, and descriptions explicitly steer agents between them. The generic `search`/`fetch` pair overlaps with the specialized search and get tools, but the descriptions scope it to a specific client (ChatGPT Deep Research) and tell others which to prefer, so confusion risk is limited.
Eight of ten tools follow a clean verb_noun pattern (get_episode, list_shows, search_facts, etc.). The bare `fetch` and `search` break the pattern, though they are a deliberate generic pair, making the deviation minor and readable.
Ten tools is well within the sweet spot for a podcast knowledge server. Each tool maps to a distinct access pattern (browse, read, keyword search) and none appears redundant padding.
Coverage of the domain is strong: shows, episodes, transcripts, topics and fact search are all reachable, with pagination and cross-links between results. The main gap is a dedicated get_show for full show metadata beyond the abbreviated list entry, and no speaker-centric listing, but agents can work around both.
Available Tools
10 toolsfetchFetch (ChatGPT-style)ARead-onlyIdempotentInspect
Get the full text for an id returned by search: an episode's summary and facts, a transcript passage with context, or a topic's facts.
Inputs: id (required). Returns: id, url, text, title, +1 more
get_episodeGet episodeARead-onlyIdempotentInspect
Get an episode's summary, publish date, named speakers and every sourced fact with quote and timestamp.
Inputs: show (required), episode (required). Returns: url, show, facts, title, +8 more
get_topicGet topicARead-onlyIdempotentInspect
Get sourced facts about one company, person or subject across all shows, grouped by episode, 20 facts per page by default. total is the topic's fact count; pass next_offset as offset for the next page.
Inputs: topic (required), limit, offset. Returns: name, slug, facts, total, +4 more
get_transcriptGet transcriptARead-onlyIdempotentInspect
Get a transcript with speakers and timestamps, up to 40 paragraphs (about 12k characters) per page. total is the paragraph count; pass next_offset as offset for the next page.
Inputs: show (required), episode (required), limit, offset. Returns: url, note, show, title, +7 more
list_episodesList episodesARead-onlyIdempotentInspect
List a show's episodes, newest first, with episode_slug, publish date and fact count. Pages via offset/next_offset.
Inputs: show (required), limit, offset. Returns: total, offset, results, next_offset
list_showsList showsARead-onlyIdempotentInspect
List shows with their slug, host and episode count, 25 per page by title. Filter with query; descriptions are shortened.
Inputs: limit, query, offset. Returns: total, offset, results, next_offset
list_topicsList topicsARead-onlyIdempotentInspect
List companies, people and subjects that have topic pages of sourced facts, most facts first. Filter with query; pass a slug to get_topic.
Inputs: limit, query, offset. Returns: total, offset, results, next_offset
searchSearch (ChatGPT-style)ARead-onlyIdempotentInspect
Search facts, transcript passages and topics at once, for clients that only use the generic search/fetch pair (ChatGPT Deep Research). Returns up to 10 ids with a title, link and short snippet; pass an id to fetch for the full text. Other clients should prefer search_facts (quotes with speaker and timestamp) or search_transcripts (raw passages), which page and filter by show.
Inputs: query (required). Returns: hint, results
search_factsSearch factsARead-onlyIdempotentInspect
Keyword search over sourced facts: each hit is a claim with the speaker's exact quote, timestamp, episode and links. Best for 'what did X say about Y' (search 'X Y', not the whole question). Results include show_slug and episode_slug for get_episode or get_transcript. Pages via offset/next_offset; total counts all matches; match says how strictly the keywords matched.
Inputs: query (required), show, limit, offset. Returns: hint, note, match, total, +3 more
search_transcriptsSearch transcriptsARead-onlyIdempotentInspect
Keyword search over full transcripts, returning matching paragraphs with a snippet, speaker, timestamp and a link to the exact paragraph. Use when search_facts finds nothing or you need the surrounding conversation: call get_transcript with show_slug, episode_slug and offset set to the hit's paragraph.
Inputs: query (required), show, limit, offset. Returns: hint, note, match, total, +3 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Search and analyze 50,000+ hours of business podcast transcripts, entities, and speakers.
Search, ask and order podcast transcripts; answers cite the episode and minute.
Search podcast transcripts and summaries. Get the quote, who said it, and the minute.
Search 4M+ podcasts & YouTube, transcribe any episode, search transcripts, generate AI lessons.
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceEnables AI agents to search and retrieve real founder experiences from podcasts, including quotes, decisions, outcomes, lessons, and similar moments.1MIT

Podwiseofficial
AlicenseNot gradedqualityCmaintenanceSearch podcast episodes, pull transcripts, ask questions about an episode and export summaries as Markdown.418MIT- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to search and retrieve the most quotable minutes from long interviews with AI founders, CEOs and researchers, returning each moment with the speaker, show, date, exact words and a link to cite. Supports topic, person, company and date filters, grouped answers to big AI questions, full moment lookups and transcript excerpts for verifying the exact wording.MIT
- AlicenseNot gradedqualityBmaintenanceProvides read-only MCP tools for AI agents and coding assistants to search podcast transcripts and episode metadata, retrieve transcript excerpts, and generate citations. It requires no login or API key.1MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.