Mcp

com.transcriptdockv0.1.2Updated Oct 9, 2026

YouTube and TikTok transcripts: get_video_transcript in one call, jobs, exports, video discovery.

VerifiedStreamable HTTPWeb executableMedia & DesignWeb Search & Scraping

Overview

AI-generated overview

Lets an assistant fetch YouTube and TikTok transcripts, run transcript jobs, export results, and discover videos.

What it does
This server exposes transcript retrieval for YouTube and TikTok videos, with a single-call get_video_transcript tool plus job handling, exports, and video discovery. It can be reached as a remote endpoint or run locally over stdio via the npm package. Authentication can be an API key or an OAuth sign-in.
When to use it
Use it when an assistant needs transcripts or captions from YouTube or TikTok videos, for example to summarize, search, or analyze spoken content, or to batch-process videos and export the text.
Requirements
Either connect to the remote endpoint or run the npm package locally with Node.js over stdio. A workspace API key (TRANSCRIPTDOCK_API_KEY) is required, or the Authorization header with a Bearer workspace API key; without the header, clients sign in with OAuth. The base URL is set via TRANSCRIPTDOCK_BASE_URL. Network access is needed.
Before you install
The server handles a workspace API key (TRANSCRIPTDOCK_API_KEY, or the Authorization Bearer value), which is a secret and should be stored and transmitted carefully. Transcript jobs and exports may write or store data in the workspace. Video URLs or identifiers submitted are sent to the third-party TranscriptDock service.

Installation

In SourceWeft

  1. Open Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "mcp": {
      "type": "http",
      "url": "https://www.transcriptdock.com/mcp"
    }
  }
}

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v0.1.2LatestOct 9, 2026