MCP server · Social media

YouTube Transcript MCP server

Let your AI pull the captions from a YouTube video so it can read, summarize, or quote them.

Social media For creatives For education Browser Automation

This is a small helper that lets your AI grab the subtitles from a YouTube video. You paste a video link, and your AI can read what was said and work with it. It is handy if you watch talks, tutorials, or interviews and want a summary or a searchable text instead of watching the whole thing.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to an app or service. This one connects your AI to YouTube captions, so when you ask about a video, the AI can go fetch the words spoken in it and bring them back to you.

What this MCP server does

You give your AI a YouTube link, a Shorts link, or just the video ID. The AI passes that to this helper. The helper asks YouTube for the captions of that video and hands the text back to your AI. Your AI then reads that text and answers your question, writes a summary, or pulls out quotes. It can also add timestamps so you know when something was said, and it can leave out sponsor or ad sections by default.

Flow diagram: you ask your AI “Summarize this video: https://youtu.be/ODaHJzOyVCQ”, the YouTube Transcript MCP server connects it to YouTube, and you get back transcript or summary.

Click to zoom

What you can do with it

Get the full transcript of a YouTube video
Summarize a long talk or interview from its captions
Pull out quotes with the moment they were said
Read captions in another language when available
Skip sponsor and ad sections in the transcript
Work with YouTube Shorts links too

Try asking your AI

“Summarize this video for me: https://youtu.be/ODaHJzOyVCQ”
“Give me the transcript of this talk with timestamps”
“What are the three main points in this interview? https://www.youtube.com/watch?v=VIDEO_ID”
“Get the Korean captions for this video if they exist”

What it gives back to you

You get the spoken text of the video back in the chat, either as one block or with timestamps like [0:05] in front of each line. Your AI can then turn that into a summary, a list of key points, or answers to your questions. If the video has no captions or the link is wrong, you get a short error message instead.

Before you start

What you need

The Claude desktop app or another AI app that supports MCP servers
Node.js 18 or newer installed on your computer
For the optional video analysis tool only: a TwelveLabs API key (a kind of password for apps; the site gives you one for free)

Good to know

The transcript tool only reads public captions, so it will not work on private or age-restricted videos, and the optional analyze_video tool sends the video to TwelveLabs and may use up your free quota there.

Install it with your AI

Add YouTube Transcript MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check YouTube Transcript MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.