# ai.bidclub/bidclub

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

- name: ai.bidclub/bidclub
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 80/100 flags: no-repository
- quality: 83/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/ai.bidclub%2Fbidclub
- tools: https://api.protogrid.dev/v1/servers/ai.bidclub%2Fbidclub/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "bidclub": {
      "type": "http",
      "url": "https://bidclub.ai/api/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 85
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% ~updated-65d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 83/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: bidclub_list_episodes (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); bidclub_search_episodes (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); bidclub_feed_index (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 2,423 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 6, about 2,423 tokens to load them all
- tool set hash: d18efe8a993ba6d145bcf395eaa5eb60
- badge: [![protogrid quality](https://protogrid.dev/badge/ai.bidclub/bidclub.svg)](https://protogrid.dev/servers/ai.bidclub/bidclub)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://bidclub.ai/api/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (6)

- `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.
- `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.
- `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.
- `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.
- `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.
- `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.