Skip to content

TranscriptYT MCP server

io.github.rajdeep-automation/transcriptytrajdeep-automationstreamable-httpv1.0.0Scanned

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

6 tools: 6 only read.

Tools: 0 delete, 0 irreversible, 0 write, 6 read.
  • Reads private data · 1
  • Reads text others write · 6
  • Can send data out · 4
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

Decide which of this server's tools your agent can use.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the TranscriptYT MCP server can do

The TranscriptYT MCP server is published by the GitHub account rajdeep-automation. It has 6 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.

1 tool reads private data (summarize_video); 6 tools bring in text other people can write (get_transcript, list_languages, list_playlist_videos and 3 more); 4 tools can send data out of your system (get_transcript, list_languages, list_playlist_videos and 1 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 21, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

6 tools

Only reads 6Show 6 read-only tools
  • get_transcriptFetch the transcript of a public YouTube video.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "get_transcript" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe 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
    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).

    Annotations the server declares

    • title: Get YouTube transcript
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • get_usageShow the remaining TranscriptYT credits and plan for this API key.Reads text others writeNo findings

    Why it is in this group

    • The name "get_usage" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Show the remaining TranscriptYT credits and plan for this API key. Free.

    Annotations the server declares

    • title: Check credits
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • list_languagesList the caption tracks available for a YouTube video.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "list_languages" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe 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
    List the caption tracks available for a YouTube video. Free, and does not use credits.

    Annotations the server declares

    • title: List caption languages
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • list_playlist_videosList the videos in a YouTube playlist, or a channel's uploads (newest first), with titles and durations.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "list_playlist_videos" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe 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
    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.

    Annotations the server declares

    • title: List playlist or channel videos
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • search_youtubeSearch YouTube for videos, or search within one channel by passing its link or @handle.Reads text others writeNo findings

    Why it is in this group

    • The name "search_youtube" says "search": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Search YouTube videos
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • summarize_videoSummary, key points, and timestamped study notes for a public YouTube video, generated from its transcript.Reads private dataReads text others writeCan send data outNo findings

    Why it is in this group

    • The name "summarize_video" says "summarize": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "note": it reads notes.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe 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
    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.

    Annotations the server declares

    • title: Summarize a YouTube video
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

24 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write6
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out4
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__transcriptyt__summarize_video"
    ]
  }
}

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:10 UTC, unchanged since Nov 6, 2026. No credentials were sent and no tool was called. What is looked at.

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
not observed
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

  1. Nov 6, 2026
    • RFC 9728 protected resource metadata: none to https://transcript-yt.com/.well-known/oauth-protected-resource/mcp
    • Authorization servers: none to https://transcript-yt.com
    • Dynamic client registration: not observed to yes
    • Client ID metadata documents: not observed to yes

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools1 changed.~1 changedView diff
  2. Tools6 changed.~6 changedView diff
  3. PostureRemote posture changed. 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 ->…View diff
    • RFC 9728 protected resource metadata: none to https://transcript-yt.com/.well-known/oauth-protected-resource/mcp
    • Authorization servers: none to https://transcript-yt.com
    • Dynamic client registration: not observed to yes
    • Client ID metadata documents: not observed to yes

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http transcriptyt https://transcript-yt.com/mcp --header 'Authorization: <your-authorization>'
claude mcp add --transport http transcriptyt https://transcript-yt.com/mcp --header 'Authorization: <your-authorization>'

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.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": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as transcriptyt. Review it before you use it.

Capability tags behind 6 rules
  • 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

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.rajdeep-automation/transcriptyt/verify?hash=c269fda1928d63c025e95149cbde1ae3fa2ba5f804d74af3ea5f3655e2183f06" | jq -e '.changed == false'

Pinned hash c269fda1928d, from Nov 21, 2026, 02:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.rajdeep-automation/transcriptyt/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.rajdeep-automation/transcriptyt
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.rajdeep-automation/transcriptyt.svg)](https://radar.anlyon.com/servers/io.github.rajdeep-automation/transcriptyt)

Source: MCP Registry. Synced Oct 21, 2026, 18:45 UTC.

TranscriptYT MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the TranscriptYT MCP server safe?

No scan can promise that. What its definitions show: 6 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.

Can the TranscriptYT MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the TranscriptYT MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the TranscriptYT MCP server have?

6 tools: 6 read. get_transcript, list_languages, list_playlist_videos, search_youtube, summarize_video and get_usage.

Does the TranscriptYT MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the TranscriptYT MCP server send data to outside services?

4 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): get_transcript, list_languages, list_playlist_videos and summarize_video.

Has the TranscriptYT MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 21, 2026. Every change is on this page and in its Atom feed.