ai.bidclub/bidclub

Official6 tools

by bidclub

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

Model Context Protocol (MCP) Server: ai.bidclub/bidclub

The ai.bidclub/bidclub MCP server provides search over 45+ investor podcasts and associated content, including transcripts, TL;DRs, and digests. Results are available in bilingual English/中文. The server is described as keyless and exposes 6 tools.

🛠️ Key Features

Search 45+ investor podcasts
Access transcripts, TL;DRs, and digests
Bilingual output: EN/中文
Keyless operation
6 tools

🚀 Use Cases

Find relevant sections across investor podcast transcripts
Use TL;DRs and digests for faster review
Search bilingual investor podcast content (EN/中文)

⚡ Developer Benefits

Centralized MCP toolset (6 tools) for podcast-related retrieval
Structured content types: transcripts, TL;DRs, digests
Multilingual (EN/中文) search results

Captured live from the server via tools/list.

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.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

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.

Parameters4

show	string	optional	Show id from bidclub_list_shows. Omit for the whole library.
source_lang	string	optional	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.
limit	integer	optional	Episodes per page.
offset	integer	optional	Rows to skip. Page with the returned pagination.next_offset.

Raw schema

{
  "type": "object",
  "properties": {
    "show": {
      "type": "string",
      "pattern": "^[a-z0-9][a-z0-9_-]{0,63}$",
      "description": "Show id from bidclub_list_shows. Omit for the whole library."
    },
    "source_lang": {
      "type": "string",
      "enum": [
        "EN",
        "ZH"
      ],
      "description": "Filters by the episode's ORIGINAL language. Chinese digests exist for most English-source episodes, so do NOT set source_lang=ZH just because you want Chinese output — use the lang parameter on bidclub_get_episode instead."
    },
    "limit": {
      "default": 50,
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "description": "Episodes per page."
    },
    "offset": {
      "default": 0,
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991,
      "description": "Rows to skip. Page with the returned pagination.next_offset."
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

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.

Parameters6

q	string	required	Query text. English words are stemmed; Chinese matches as a substring.
time	string	optional	Restrict to episodes published within this window.
person	string	optional	Exact participant name, matched against the "person:" chips.
show	string	optional	Show id from bidclub_list_shows.
source_lang	string	optional	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.
len	string	optional	Episode duration bucket.

Raw schema

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "minLength": 2,
      "maxLength": 100,
      "description": "Query text. English words are stemmed; Chinese matches as a substring."
    },
    "time": {
      "type": "string",
      "enum": [
        "24h",
        "7d",
        "30d"
      ],
      "description": "Restrict to episodes published within this window."
    },
    "person": {
      "type": "string",
      "maxLength": 120,
      "description": "Exact participant name, matched against the \"person:\" chips."
    },
    "show": {
      "type": "string",
      "pattern": "^[a-z0-9][a-z0-9_-]{0,63}$",
      "description": "Show id from bidclub_list_shows."
    },
    "source_lang": {
      "type": "string",
      "enum": [
        "EN",
        "ZH"
      ],
      "description": "Filters by the episode's ORIGINAL language. Chinese digests exist for most English-source episodes, so do NOT set source_lang=ZH just because you want Chinese output — use the lang parameter on bidclub_get_episode instead."
    },
    "len": {
      "type": "string",
      "enum": [
        "lt30",
        "30to60",
        "60to120",
        "gt120"
      ],
      "description": "Episode duration bucket."
    }
  },
  "required": [
    "q"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

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.

Parameters5

slug	string	required	Episode slug from a list or search result.
section	string	optional	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.
lang	string	optional	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	optional	Code-point offset into the section. Use the previous next_offset.
max_chars	integer	optional	Code points per window. Defaults to 20000 for Latin text and 14000 for Chinese or Japanese text, which cost about one token per character.

Raw schema

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "pattern": "^[a-z0-9](?:[a-z0-9-]{0,158}[a-z0-9])?$",
      "description": "Episode slug from a list or search result."
    },
    "section": {
      "default": "digest",
      "type": "string",
      "enum": [
        "meta",
        "tldr",
        "digest",
        "transcript"
      ],
      "description": "meta returns the row with no long markdown at all; tldr is the bullet summary; digest is the structured writeup; transcript is the full text."
    },
    "lang": {
      "default": "EN",
      "type": "string",
      "enum": [
        "EN",
        "ZH"
      ],
      "description": "Output edition. A translated summary is served only when both the TL;DR and the digest translations are complete; otherwise the source edition comes back with lang_fallback: true."
    },
    "offset": {
      "default": 0,
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991,
      "description": "Code-point offset into the section. Use the previous next_offset."
    },
    "max_chars": {
      "type": "integer",
      "minimum": 1000,
      "maximum": 50000,
      "description": "Code points per window. Defaults to 20000 for Latin text and 14000 for Chinese or Japanese text, which cost about one token per character."
    }
  },
  "required": [
    "slug"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

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.

Parameters2

show	string	optional	Show id. Mutually exclusive with person.
person	string	optional	Exact participant name. Mutually exclusive with show.

Raw schema

{
  "type": "object",
  "properties": {
    "show": {
      "type": "string",
      "pattern": "^[a-z0-9][a-z0-9_-]{0,63}$",
      "description": "Show id. Mutually exclusive with person."
    },
    "person": {
      "type": "string",
      "maxLength": 120,
      "description": "Exact participant name. Mutually exclusive with show."
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

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.

Parameters3

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

Raw schema

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "pattern": "^[a-z0-9](?:[a-z0-9-]{0,158}[a-z0-9])?$",
      "description": "Episode slug. Mutually exclusive with show."
    },
    "show": {
      "type": "string",
      "pattern": "^[a-z0-9][a-z0-9_-]{0,63}$",
      "description": "Show id, for the whole-show zip archives. Mutually exclusive with slug."
    },
    "lang": {
      "default": "orig",
      "type": "string",
      "enum": [
        "orig",
        "EN",
        "ZH"
      ],
      "description": "Edition to request in the generated URLs. orig keeps each artifact in its source language."
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Install

Tools (6)

bidclub_list_showsbidclub_list_episodesbidclub_search_episodesbidclub_get_episodebidclub_feed_indexbidclub_download_links

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://bidclub.ai/api/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "bidclub": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://bidclub.ai/api/mcp"
      ]
    }
  }
}

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

Model Context Protocol (MCP) Server: ai.bidclub/bidclub

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

bidclub_list_shows

bidclub_list_episodes

bidclub_search_episodes

bidclub_get_episode

bidclub_feed_index

bidclub_download_links

Install

Remote endpoint

Related servers