Skip to content
TranscriptAPI logo

TranscriptAPI MCP server

Which servers in the official MCP registry are TranscriptAPI's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-21

← Back to TranscriptAPI

Whose server it is
  • Registry nameio.transcriptapi/youtube-transcriptverified in the MCP registry

The registry name sits under transcriptapi.io. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-21
  • Stateanswerschecked 2026-10-21
  • Tools5
  • Server calls itselftranscriptapi
  • Server version0.1.0
  • Protocol version2025-06-18

On 2026-10-21 the server answered initialize and tools/list without a sign-in. First answer in 503 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: Pull timestamped transcripts from YouTube videos into structured JSON; Search YouTube videos by keyword or within a single channel; Bulk-transcribe recent uploads from a channel or a playlist.
  • Checked on 1 of the 7 days it takes to judge reliability.

Once connected

  • For "Pull timestamped transcripts from YouTube videos into structured JSON", the likely first call is get_youtube_transcript.
  • For "Search YouTube videos by keyword or within a single channel", the likely first call is search_youtube.
  • For "Bulk-transcribe recent uploads from a channel or a playlist", the likely first call is get_channel_videos.
  • Parameters are untyped or undescribed in 5 of 5 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 1, the first on 2026-10-21
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • What an agent can do with it3 of 3 use cases
  • Use207 npm downloads a week
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer1246 ms
  • Space in an agent's context≈ 676 tokensthe definitions of all its tools (5), which an agent carries on every turn
  • Tool definitionsB · 83 of 100
  • Typed results5 of 5 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 5 of 5

What an agent can do with it

  • can do · Pull timestamped transcripts from YouTube videos into structured JSON
  • can do · Search YouTube videos by keyword or within a single channel
  • can do · Bulk-transcribe recent uploads from a channel or a playlist

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers5 tools · read 2026-10-21
  • 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'…

  • 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.

  • 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.

  • 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.

  • 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.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "youtube-transcript": {
      "type": "http",
      "url": "https://api.transcriptapi.io/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http transcriptapi https://api.transcriptapi.io/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://api.transcriptapi.io/mcp as a custom connector in the settings.

Also shipped through: npm

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.