Advertise
MCP.so
Sign In

YouTube Transcript Server MCP Server

@MCP-Mirror

Repository

Basic information

Category

Media & Design

Transports

stdio

Author

MCP-Mirror

About YouTube Transcript Server MCP Server

Mirror of

#youtube#transcript#mcp-server

YouTube Transcript Server MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "kimtaeyoon83_mcp-server-youtube-transcript": {
      "command": "npx",
      "args": [
        "@smithery/cli",
        "install",
        "@kimtaeyoon83/mcp-server-youtube-transcript",
        "--client",
        "claude"
      ]
    }
  }
}

YouTube Transcript Server MCP Server tools

1

Extract transcripts from YouTube videos

Overview

What is YouTube Transcript Server?

YouTube Transcript Server is a Model Context Protocol (MCP) server that enables retrieval of transcripts (captions/subtitles) from YouTube videos. It provides a simple interface – the get_transcript tool – for AI assistants like Claude to extract video transcripts by URL or video ID, with optional language selection.

How to use YouTube Transcript Server?

Install via Smithery (npx @smithery/cli install @kimtaeyoon83/mcp-server-youtube-transcript --client claude) or using mcp-get. For Claude Desktop, add the server configuration to your claude_desktop_config.json using the npx command as shown in the README. Then invoke the get_transcript tool with a YouTube URL or video ID and an optional language code (e.g., "en", "ko").

Key features of YouTube Transcript Server

  • Single tool get_transcript for transcript extraction
  • Supports multiple YouTube URL formats and video IDs
  • Language-specific retrieval with default English
  • Returns detailed metadata with the transcript
  • Robust error handling for invalid URLs and unavailable transcripts

Use cases of YouTube Transcript Server

  • Extracting English subtitles from a tutorial video in Claude Desktop
  • Retrieving Korean captions from a YouTube video for translation
  • Accessing video transcript content for summarization or analysis
  • Obtaining transcript metadata (languages available, timestamps) programmatically

Frequently asked questions

1

What does the server do?

It provides a tool called `get_transcript` that retrieves the transcript (captions/subtitles) of a YouTube video when given a valid video URL or ID and an optional language code.

2

What are the runtime requirements?

Node.js 18 or higher and npm/yarn are required for development and running the server.

3

Where does the transcript data come from?

The server retrieves transcripts directly from YouTube's public caption/subtitle data; no local storage is involved.

4

Are there any limitations on transcript availability?

Yes – the server returns an error if the video has no captions, if the requested language is unavailable, or if the URL/ID is invalid.

5

What transport and authentication does the server use?

The server communicates over stdio (standard input/output) as per the MCP protocol. No authentication or API keys are required.

Comments

More Media & Design MCP servers

SceneF — California + Hawaii Movie Showtimes

SceneF

Built by movie lovers, for movie lovers and their assistants. SceneF puts every screen in California and Hawaii on one board — 33 regions, from San Francisco's single-screen neighborhood houses and nightly repertory cale

Uwear.ai

Uwear.ai

Run complete AI fashion photoshoots from ChatGPT, Claude, or Codex. Turn flat-lay, packshot, and mannequin product images into catalog-ready on-model photos and video with saved art direction, automatic QA, and catalog-s

GOJI

GOJI Agency

A remote MCP server from GOJI, a full-service digital agency in Melbourne, Australia. Nine tools over published material: a 104-term plain-English glossary, a 14-chapter guide to AI visibility, seven long-form guides inc

AI Manga & Anime Generator - Mangii MCP

AAAIStudio

Public Mangii MCP metadata (ai.mangii/manga). Remote Streamable HTTP at mcp.mangii.ai.

PixelDojo

PixelDojo

Generate images, video, audio and short films with 140+ AI models from any MCP client. PixelDojo picks the right model (Flux, Seedream, Seedance, Veo, Kling, WAN, Nano Banana, GPT Image), renders it and returns download

Advertise