ai.bidclub/bidclub

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Search 45+ investor podcasts and read transcripts, TL;DRs, digests — bilingual EN/中文, keyless.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "bidclub": {
      "url": "https://bidclub.ai/api/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (6)

• bidclub_list_shows

  List every show in the BidClub library with its id, display name, source language, hosts, and source links. Start here when you need a show id for the show parameter of the other tools.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• bidclub_list_episodes

  List episodes newest first, optionally narrowed to one show. Returns metadata only — titles, deks, dates, durations, participant chips and source links — never the digest or transcript. Use bidclub_get_episode for content.

  Parameters:

  • show — string — Show id from bidclub_list_shows. Omit for the whole library.
  • asset — string — Optional asset tag ids joined by commas (equities, crypto, vc_pe, other). Matches any selected id within this facet and all supplied facets together. Omit for all episodes, including untagged; pass none for no episodes.
  • focus — string — Optional focus tag ids joined by commas (investing, company_building, technical, macro, policy). Matches any selected id within this facet and all supplied facets together. Omit for all episodes, including untagged; pass none for no episodes.
  • limit — integer — Episodes per page.
  • offset — integer — Rows to skip. Page with the returned pagination.next_offset.
  • sector — string — Optional sector tag ids joined by commas (ai_software, semis, robotics, biotech, consumer, finance, blockchain, energy, space_defense). Matches any selected id within this facet and all supplied facets together. Omit for all episodes, including untagged; pass none for no episodes.
  • source_lang — string — Filters by the episode's ORIGINAL language. Chinese digests exist for most English-source episodes, so do NOT set source_lang=ZH just because you want Chinese output — use the lang parameter on bidclub_get_episode instead.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• bidclub_search_episodes

  Full-text search across titles, deks, TL;DRs, digests and transcripts, with a substring sweep that handles Chinese queries the tokenizer cannot segment. Returns up to 20 metadata rows, never content. When the response carries partial: true the query only covered the newest searched_recent episodes, so say so rather than reporting an absence.

  Parameters:

  • q (required) — string — Query text. English words are stemmed; Chinese matches as a substring.
  • len — string — Episode duration bucket.
  • show — string — Show id from bidclub_list_shows.
  • time — string — Restrict to episodes published within this window.
  • asset — string — Optional asset tag ids joined by commas (equities, crypto, vc_pe, other). Matches any selected id within this facet and all supplied facets together. Omit for all episodes, including untagged; pass none for no episodes.
  • focus — string — Optional focus tag ids joined by commas (investing, company_building, technical, macro, policy). Matches any selected id within this facet and all supplied facets together. Omit for all episodes, including untagged; pass none for no episodes.
  • person — string — Exact participant name, matched against the "person:" chips.
  • sector — string — Optional sector tag ids joined by commas (ai_software, semis, robotics, biotech, consumer, finance, blockchain, energy, space_defense). Matches any selected id within this facet and all supplied facets together. Omit for all episodes, including untagged; pass none for no episodes.
  • source_lang — string — Filters by the episode's ORIGINAL language. Chinese digests exist for most English-source episodes, so do NOT set source_lang=ZH just because you want Chinese output — use the lang parameter on bidclub_get_episode instead.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• bidclub_get_episode

  Read one section of an episode. Long sections page deterministically: when the result says truncated: true, call again with offset set to next_offset and concatenate content_md until next_offset is null. Prefer tldr or digest — a transcript can exceed 100,000 characters and is rarely worth paging in full. lang selects the OUTPUT edition, not a catalogue filter; transcripts exist only in the episode's source language, so requesting a different lang for section=transcript always returns the source with lang_fallback: true.

  Parameters:

  • slug (required) — string — Episode slug from a list or search result.
  • lang — string — Output edition. A translated summary is served only when both the TL;DR and the digest translations are complete; otherwise the source edition comes back with lang_fallback: true.
  • offset — integer — Code-point offset into the section. Use the previous next_offset.
  • section — string — meta returns the row with no long markdown at all; tldr is the bullet summary; digest is the structured writeup; transcript is the full text.
  • max_chars — integer — Code points per window. Defaults to 20000 for Latin text and 14000 for Chinese or Japanese text, which cost about one token per character.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• bidclub_feed_index

  The slim catalogue of every episode — one row each, metadata only. Narrow it with show or person; passing both is an error. Large responses are truncated to the newest rows with a note, so filter rather than paging.

  Parameters:

  • show — string — Show id. Mutually exclusive with person.
  • asset — string — Optional asset tag ids joined by commas (equities, crypto, vc_pe, other). Matches any selected id within this facet and all supplied facets together. Omit for all episodes, including untagged; pass none for no episodes.
  • focus — string — Optional focus tag ids joined by commas (investing, company_building, technical, macro, policy). Matches any selected id within this facet and all supplied facets together. Omit for all episodes, including untagged; pass none for no episodes.
  • person — string — Exact participant name. Mutually exclusive with show.
  • sector — string — Optional sector tag ids joined by commas (ai_software, semis, robotics, biotech, consumer, finance, blockchain, energy, space_defense). Matches any selected id within this facet and all supplied facets together. Omit for all episodes, including untagged; pass none for no episodes.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• bidclub_download_links

  Build the download URLs for an episode or a whole show without fetching anything. Hand these to the user, or fetch one yourself when you need a complete transcript in a single request instead of paging it through bidclub_get_episode. Exactly one of slug or show is required.

  Parameters:

  • lang — string — Edition to request in the generated URLs. orig keeps each artifact in its source language.
  • show — string — Show id, for the whole-show zip archives. Mutually exclusive with slug.
  • slug — string — Episode slug. Mutually exclusive with show.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.