YouTube Transcript API MCP Server

@minhleathvn

Basic information

About YouTube Transcript API MCP Server

A MCP server helps to transcript a youtube video

YouTube Transcript API MCP Server config

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

{
  "mcpServers": {
    "youtube_transcript": {
      "command": "python",
      "args": [
        "apps/flask_server.py"
      ]
    }
  }
}

YouTube Transcript API MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is YouTube Transcript API?

YouTube Transcript API is a Python service that provides APIs to fetch and transcribe YouTube video content. It supports both a REST API (Flask) and an MCP server implementation, making it suitable for developers who need to extract video transcripts programmatically.

How to use YouTube Transcript API?

Install dependencies with pip install -r requirements.txt, then start the MCP server with python apps/mcp_server.py. Use the exposed MCP tools such as get_transcript(video_id, language) and extract_transcript(video_id, language) to retrieve transcripts. Alternatively, start the Flask server with python apps/flask_server.py and call its REST endpoints.

Key features of YouTube Transcript API

Fetch transcripts in multiple languages (English, Vietnamese)
Auto-detect and use available transcripts
Fallback to audio transcription via Whisper when captions are missing
Support for both REST API and MCP server interfaces
Automatic language detection with langdetect
Temporary file cleanup after audio processing

Use cases of YouTube Transcript API

Get video transcripts for content analysis or subtitle generation
Automatically fall back to Whisper‑based transcription when no captions exist
Search for YouTube videos and extract their transcripts in one workflow
Integrate transcript extraction into MCP‑compatible tools or Flask web apps

Frequently asked questions

Which languages are supported for transcripts?

English (en) and Vietnamese (vi) are explicitly supported, and the system can auto‑detect other languages using the langdetect library.

How can I get a transcript if no captions are available?

The API falls back to downloading the audio and transcribing it using Whisper (via the `extract_transcript` tool or endpoint).

What are the main dependencies?

Key dependencies include `youtube-transcript-api`, `pytube`, `whisper`, `torch`, `langdetect`, `flask` (for the REST API), and `mcp` (for the MCP server).

How do I run the MCP server versus the REST API?

Run `python apps/mcp_server.py` for the MCP server, or `python apps/flask_server.py` for the Flask‑based REST API. Both are located under the `apps/` directory.

Are there health check or video info endpoints?

Yes, the Flask server exposes `/health` and `/video/info?video_id=<id>` endpoints. The MCP server provides `search_youtube_video(query)` to find videos.

Comments

More Media & Design MCP servers

Shotstack

Shotstack's official MCP server gives AI assistants direct access to the Shotstack video editing API, so you can produce video from a conversation instead of writing Edit JSON by hand. Available tools cover rendering vid

North Noir

Make AI-drawn video from chat. Claude, Cursor or Claude Code plans the film, the model draws every frame in code at 30 fps, and you edit it on a timeline with narration, music and sound effects.

SVGator

Drive your SVGator account from any AI assistant. Prompt an animation, get an editable project back, and export it as SVG, Lottie, GIF, MP4, and more, then open it in the editor to finish by hand.

Kinetune

Turn your songs into lyric videos (9:16, 16:9, 1:1) and Spotify Canvas loops. Find a song, browse Looks, get an exact credit quote, and render only after you say yes.

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