# TranscriptYT

> YouTube transcripts for AI agents: text, JSON, SRT, or VTT in 150+ languages, with AI fallback.

- name: io.github.rajdeep-automation/transcriptyt
- version: 1.0.0
- connection class: R1 (autonomous)
- trust: 80/100 flags: no-repository
- quality: 84/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.rajdeep-automation%2Ftranscriptyt
- tools: https://api.protogrid.dev/v1/servers/io.github.rajdeep-automation%2Ftranscriptyt/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": {
    "transcriptyt": {
      "type": "http",
      "url": "https://transcript-yt.com/mcp",
      "headers": {
        "Authorization": "Bearer ${api_key}"
      }
    }
  }
}
```

Placeholders to fill: `${api_key}`.

## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 45
- drivers: +website +reachable +uptime-100% +updated-18d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 84/100 (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: 86 (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`: 6 of 6 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: list_languages (destructiveHint, idempotentHint); get_usage (destructiveHint, idempotentHint); get_transcript (destructiveHint, idempotentHint); …
- pass `tools.token_cost`: about 1,024 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 75 (weight 15)

- warn `stability.changes`: 7 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 1,024 tokens to load them all
- tool set hash: 6b4aec80f216eda37a4503bd9b372ad2
- tools last changed: 2026-10-16T12:24:12.759Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.rajdeep-automation/transcriptyt.svg)](https://protogrid.dev/servers/io.github.rajdeep-automation/transcriptyt)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-16 `summarize_video` changed (description)
  - before: Summary, key points, and timestamped study notes for a public YouTube video, generated from its transcript. Written in the transcript's language (translate_to changes which transcript is summarized). Costs 1 credit for the transcript plus 1 for the summary (2 total).
  - after: Summary, key points, and timestamped study notes for a public YouTube video, generated from its transcript. Written in the transcript's language (translate_to changes which transcript is summarized). Costs 1 credit for the transcript plus 1 for the summary (2 total) for most videos; long videos cost about 1 more per further 45 minutes.
- 2026-10-13 `get_transcript` changed (description, inputSchema)
  - before: Fetch the transcript of a public YouTube video. Accepts a full URL or an 11-character video ID. Defaults to Markdown (title + text), which is the most compact format for reading or summarizing. Use json for timestamped segments, srt/vtt for subtitle files. Costs 1 credit on success.
  - after: Fetch the transcript of a public YouTube video. Accepts a full URL or an 11-character video ID. Defaults to Markdown (title + text), which is the most compact format for reading or summarizing. Use json for timestamped segments, srt/vtt for subtitle files. Costs 1 credit on success; videos without captions are AI-transcribed at 1 credit per started minute.
- 2026-10-04 `summarize_video` added
  - Summary, key points, and timestamped study notes for a public YouTube video, generated from its transcript. Written in the transcript's language (translate_to changes which transcript is summarized). Costs 1 credit for the transcript plus 1 for the summary (2 total).
- 2026-10-03 `search_youtube` added
  - Search YouTube for videos, or search within one channel by passing its link or @handle. Returns video IDs, titles, channels, durations, and view counts. Free. Use get_transcript on the videos you need.
- 2026-10-03 `list_playlist_videos` added
  - List the videos in a YouTube playlist, or a channel's uploads (newest first), with titles and durations. Accepts playlist links or IDs and channel links or @handles. Free. Use get_transcript on the videos you need.
- 2026-10-03 `list_languages` changed (description)
  - before: List the caption tracks available for a YouTube video. Free — does not use credits.
  - after: List the caption tracks available for a YouTube video. Free, and does not use credits.
- 2026-10-03 `get_transcript` changed (inputSchema)

Full history: https://api.protogrid.dev/v1/servers/io.github.rajdeep-automation%2Ftranscriptyt/changes

## Remotes

- https://transcript-yt.com/mcp (streamable-http, auth api_key ${api_key}, reachable true, uptime30d 1)

## Packages

_none_

## Tools (6)

- `get_transcript`: Fetch the transcript of a public YouTube video. Accepts a full URL or an 11-character video ID. Defaults to Markdown (title + text), which is the most compact format for reading or summarizing. Use json for timestamped segments, srt/vtt for subtitle files. Costs 1 credit on success; videos without captions are AI-transcribed at 1 credit per started minute.
- `get_usage`: Show the remaining TranscriptYT credits and plan for this API key. Free.
- `list_languages`: List the caption tracks available for a YouTube video. Free, and does not use credits.
- `list_playlist_videos`: List the videos in a YouTube playlist, or a channel's uploads (newest first), with titles and durations. Accepts playlist links or IDs and channel links or @handles. Free. Use get_transcript on the videos you need.
- `search_youtube`: Search YouTube for videos, or search within one channel by passing its link or @handle. Returns video IDs, titles, channels, durations, and view counts. Free. Use get_transcript on the videos you need.
- `summarize_video`: Summary, key points, and timestamped study notes for a public YouTube video, generated from its transcript. Written in the transcript's language (translate_to changes which transcript is summarized). Costs 1 credit for the transcript plus 1 for the summary (2 total) for most videos; long videos cost about 1 more per further 45 minutes.