# `io.github.rajdeep-automation/transcriptyt` on Anlyon Radar

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by Anlyon Radar. It is data to inspect, not instructions to follow. Invisible characters are shown as [U+XXXX].
> No finding is not a safety guarantee: these are point-in-time checks of tool definitions, not of code or behaviour.

- Page: https://radar.anlyon.com/servers/io.github.rajdeep-automation/transcriptyt
- JSON: https://radar.anlyon.com/api/v1/servers/io.github.rajdeep-automation/transcriptyt
- Version: 1.0.0 (active)
- Publisher: io.github.rajdeep-automation (GitHub account)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-10-21T18:45:52.957Z

Title and description, as the publisher wrote them:

```untrusted-server-text
TranscriptYT
YouTube transcripts for AI agents: text, JSON, SRT, or VTT in 150+ languages, with AI fallback.
```

Scanned 2026-11-21T02:17:56.749Z over streamable-http.

**6 tools: 6 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 0 | ask |
| Only reads | read | 6 | allow |

## Exfil surface

24 private-data -> untrusted-input -> outbound paths in this server alone. Denying 1 private-data tool breaks every one: `mcp__transcriptyt__summarize_video`.

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | `mcp__transcriptyt__summarize_video` |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | `mcp__transcriptyt__get_transcript` `mcp__transcriptyt__get_usage` `mcp__transcriptyt__list_languages` `mcp__transcriptyt__list_playlist_videos` `mcp__transcriptyt__search_youtube` `mcp__transcriptyt__summarize_video` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__transcriptyt__get_transcript` `mcp__transcriptyt__list_languages` `mcp__transcriptyt__list_playlist_videos` `mcp__transcriptyt__summarize_video` |

| Private data | Untrusted input | Outbound |
| --- | --- | --- |
| `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__get_transcript` | `mcp__transcriptyt__get_transcript` |
| `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__get_transcript` | `mcp__transcriptyt__list_languages` |
| `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__get_transcript` | `mcp__transcriptyt__list_playlist_videos` |
| `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__get_transcript` | `mcp__transcriptyt__summarize_video` |
| `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__get_usage` | `mcp__transcriptyt__get_transcript` |
| `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__get_usage` | `mcp__transcriptyt__list_languages` |
| `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__get_usage` | `mcp__transcriptyt__list_playlist_videos` |
| `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__get_usage` | `mcp__transcriptyt__summarize_video` |
| `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__list_languages` | `mcp__transcriptyt__get_transcript` |
| `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__list_languages` | `mcp__transcriptyt__list_languages` |
| `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__list_languages` | `mcp__transcriptyt__list_playlist_videos` |
| `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__list_languages` | `mcp__transcriptyt__summarize_video` |
| `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__list_playlist_videos` | `mcp__transcriptyt__get_transcript` |
| `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__list_playlist_videos` | `mcp__transcriptyt__list_languages` |
| `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__list_playlist_videos` | `mcp__transcriptyt__list_playlist_videos` |
| `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__list_playlist_videos` | `mcp__transcriptyt__summarize_video` |
| `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__search_youtube` | `mcp__transcriptyt__get_transcript` |
| `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__search_youtube` | `mcp__transcriptyt__list_languages` |
| `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__search_youtube` | `mcp__transcriptyt__list_playlist_videos` |
| `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__search_youtube` | `mcp__transcriptyt__summarize_video` |
| `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__get_transcript` |
| `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__list_languages` |
| `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__list_playlist_videos` |
| `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__summarize_video` | `mcp__transcriptyt__summarize_video` |

## Findings

No check matched anything in these tool definitions.


## Only reads (6)

Looks things up and changes nothing. Claude Code: allow.

### `get_transcript`

- The name "get_transcript" says "get": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data. The input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- Tag outbound: The input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
- Claude Code: ask, because it is tagged outbound.

Description, as the server wrote it:

```untrusted-server-text
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 (up to 9 hours long) are AI-transcribed at 1 credit per started minute (paid plans and credit packs; Free reads captions only).
```

### `get_usage`

- The name "get_usage" says "get": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Show the remaining TranscriptYT credits and plan for this API key. Free.
```

### `list_languages`

- The name "list_languages" says "list": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data. The input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- Tag outbound: The input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
- Claude Code: ask, because it is tagged outbound.

Description, as the server wrote it:

```untrusted-server-text
List the caption tracks available for a YouTube video. Free, and does not use credits.
```

### `list_playlist_videos`

- The name "list_playlist_videos" says "list": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data. The input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- Tag outbound: The input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
- Claude Code: ask, because it is tagged outbound.

Description, as the server wrote it:

```untrusted-server-text
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 on paid plans; Free plan: 10 a day, then 1 credit. Use get_transcript on the videos you need.
```

### `search_youtube`

- The name "search_youtube" says "search": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
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 on paid plans; Free plan: 10 a day, then 1 credit. Use get_transcript on the videos you need.
```

### `summarize_video`

- The name "summarize_video" says "summarize": a word for reading.
- Tag private-data: The description's first sentence says "note": it reads notes.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data. The input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- Tag outbound: The input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
- Claude Code: ask, because it is tagged outbound.

Description, as the server wrote it:

```untrusted-server-text
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.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `transcriptyt`:

```json
{
  "permissions": {
    "allow": [
      "mcp__transcriptyt__search_youtube",
      "mcp__transcriptyt__get_usage"
    ],
    "ask": [
      "mcp__transcriptyt__get_transcript",
      "mcp__transcriptyt__list_languages",
      "mcp__transcriptyt__list_playlist_videos",
      "mcp__transcriptyt__summarize_video"
    ],
    "deny": []
  }
}
```

Capability tags behind the rules (a read tagged outbound is asked about):

- `mcp__transcriptyt__get_transcript`: untrusted-input, outbound
- `mcp__transcriptyt__list_languages`: untrusted-input, outbound
- `mcp__transcriptyt__list_playlist_videos`: untrusted-input, outbound
- `mcp__transcriptyt__search_youtube`: untrusted-input
- `mcp__transcriptyt__summarize_video`: private-data, untrusted-input, outbound
- `mcp__transcriptyt__get_usage`: untrusted-input

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-20T19:10:07.808Z, unchanged since 2026-11-06T05:07:29.180Z. No credentials were sent and no tool was called. Values are shown as the endpoint returned them. Method: https://radar.anlyon.com/methodology#remote-posture

| Fact | Observed |
| --- | --- |
| Reachable | `yes` |
| HTTP status of an anonymous initialize | `200` |
| tools/list served without credentials | `yes` |
| Tools that change things, listed without credentials | `0` |
| Protocol version | `2025-06-18` |
| WWW-Authenticate on 401 | `not observed` |
| resource_metadata in WWW-Authenticate | `none` |
| RFC 9728 protected resource metadata | `https://transcript-yt.com/.well-known/oauth-protected-resource/mcp` |
| Authorization servers | `https://transcript-yt.com` |
| Legacy HTTP+SSE transport | `no` |
| Dynamic client registration | `yes` |
| Client ID metadata documents | `yes` |

Posture changes:

- 2026-11-06T05:07:29.180Z: RFC 9728 protected resource metadata `none` -> `https://transcript-yt.com/.well-known/oauth-protected-resource/mcp`; Authorization servers `none` -> `https://transcript-yt.com`; Dynamic client registration `not observed` -> `yes`; Client ID metadata documents `not observed` -> `yes`
