# TranscriptAPI — YouTube transcripts (transcriptapi.io)

> YouTube transcripts, search, channels and playlists for AI agents, by transcriptapi.io.

- name: io.transcriptapi/youtube-transcript
- version: 0.1.1
- connection class: R1 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 94/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.transcriptapi%2Fyoutube-transcript
- tools: https://api.protogrid.dev/v1/servers/io.transcriptapi%2Fyoutube-transcript/tools

**An agent can connect on its own if it already holds `api_key`.** Remote endpoint behind a static API key or header. The registry never sees the value; the agent fills the placeholder.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "youtube-transcript": {
      "type": "http",
      "url": "https://api.transcriptapi.io/mcp",
      "headers": {
        "Authorization": "Bearer ${api_key}"
      }
    }
  }
}
```

Placeholders to fill: `${api_key}`.

## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% +updated-2d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 94/100 (new)

### 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: 100 (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
- pass `tools.annotations`: 5 of 5 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 730 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

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

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 2 of the 7 days needed

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

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: deps.dev does not know transcriptapi-mcp@0.1.1

- tools: 5, about 730 tokens to load them all
- tool set hash: cb8673b91ac6dbf95bb97c525f76f2d0
- badge: [![protogrid quality](https://protogrid.dev/badge/io.transcriptapi/youtube-transcript.svg)](https://protogrid.dev/servers/io.transcriptapi/youtube-transcript)
- 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._

## Dependencies

- npm transcriptapi-mcp@0.1.1: unknown

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://api.transcriptapi.io/mcp (streamable-http, auth api_key ${api_key}, reachable true, uptime30d 1)

## Packages

- npm transcriptapi-mcp@0.1.1 secrets: TRANSCRIPTAPI_KEY

## Tools (5)

- `get_channel_videos`: List the most recent uploads of a YouTube channel, newest first. Accepts a channel id (UC…), a handle (@name) or a channel URL. Returns ids, titles, durations, view counts and publish dates.
- `get_playlist_videos`: List the videos in a YouTube playlist, in playlist order. Accepts a playlist URL (anything with list=…) or the playlist id. Returns ids and titles for get_youtube_transcript.
- `get_youtube_transcript`: Fetch the transcript (captions/subtitles) of a YouTube video as text. Accepts a watch URL, youtu.be link, Shorts link or bare 11-character video id. Returns the spoken text with timestamps grouped in ~30 s blocks by default; format 'text' is prose without timestamps, 'srt'/'vtt' are subtitle files, 'json' is raw segments with start/duration. Works with creator-uploaded and auto-generated captions. translate_to translates the transcript with AI (extra credits, scales with length) — omit unless asked.
- `search_channel_videos`: Search for videos inside one YouTube channel by keyword — 'find the video where <channel> talks about <topic>'. Accepts a channel id, @handle or channel URL.
- `search_youtube`: Search YouTube for videos by keyword. Returns video ids, titles, channel names, durations and view counts. Use a returned id with get_youtube_transcript to read it.