Skip to content
TranscribeText logo

TranscribeText MCP server

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

read 2026-10-19

← Back to TranscribeText

Whose server it is
  • Registry namecom.transcribetext/transcribeverified in the MCP registry

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

When we asked itchecked 2026-10-19
  • Stateanswerschecked 2026-10-19
  • Tools3
  • Server calls itselftranscribetext
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-19 the server answered initialize and tools/list without a sign-in. First answer in 88 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 3 of the 7 days it takes to judge reliability.

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: 3, the first on 2026-10-19
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
  • Answeredmeasuring3 of the 7 daily checks it takes to print a share
  • Median first answer255 ms
  • Space in an agent's context≈ 533 tokensthe definitions of all its tools (3), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

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 offers3 tools · read 2026-10-19
  • get_youtube_transcript

    Get the transcript of a YouTube video from its link. Returns the captions YouTube has for the video (subtitles uploaded by the creator, or the auto-generated captions) as plain text, with the title, channel and the caption languages…

  • transcribe_tiktok_video

    Transcribe the speech in a TikTok video to text from its link. The spoken language is detected automatically. Usually takes 20 to 60 seconds. Free use is limited per day and per video length; if the transcription is not finished when this…

  • get_transcription_result

    Get the result of a transcription that transcribe_tiktok_video started but did not finish in time. Pass the job_id that call returned.

How to connect

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

{
  "mcpServers": {
    "transcribe": {
      "type": "http",
      "url": "https://transcribetext.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http transcribetext https://transcribetext.com/mcp

Add to CursorAdd to VS Code

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

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.