YouTube Transcript

v1.0.0Search & Data Extractionstable

An MCP server designed to fetch transcripts for YouTube videos. It enables AI tools to access video text content for tasks like summarization, analysis, and key takeaway extraction.

claude-desktopmcpmcp-serverraycasttranscript
Share:
71
Stars
0
Downloads
0
Weekly
0/5

What is YouTube Transcript?

YouTube Transcript is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server designed to fetch transcripts for youtube videos. it enables ai tools to access video text content for tasks like summarization, analysis, and key takeaway extraction.

An MCP server designed to fetch transcripts for YouTube videos. It enables AI tools to access video text content for tasks like summarization, analysis, and key takeaway extraction.

This server falls under the Search & Data Extraction category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • An MCP server designed to fetch transcripts for YouTube vide

Use Cases

Fetch transcripts from YouTube videos for analysis.
Summarize video content using extracted text.
Extract key takeaways from video transcripts.
cottongeeks

Maintainer

LicenseMIT License
Languagepython
Versionv1.0.0
UpdatedMar 30, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx ytt

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use YouTube Transcript

The ytt-mcp server is a lightweight Python MCP server that fetches transcripts from YouTube videos, enabling AI assistants to read and process video content as plain text. It connects to YouTube's transcript API and returns the full spoken text of any video that has captions available, making it possible for Claude to summarize, analyze, extract key points, or answer questions about video content without the user needing to watch it. This is especially useful for research, note-taking, and content workflows involving YouTube lectures, interviews, or tutorials.

Prerequisites

  • Python 3.10+ installed
  • uv package manager installed (pip install uv or curl -LsSf https://astral.sh/uv/install.sh | sh)
  • An MCP-compatible client such as Claude Desktop or Raycast with AI support
  • Internet access to reach YouTube's transcript API
1

Install the server via uvx

uvx installs and runs ytt-mcp in an isolated environment without requiring a manual pip install. This is the recommended one-command setup.

uvx ytt-mcp
2

Configure Claude Desktop

Add the server to your claude_desktop_config.json. No environment variables are required — just the command and args.

{
  "mcpServers": {
    "ytt-mcp": {
      "command": "uvx",
      "args": ["ytt-mcp"]
    }
  }
}
3

Restart Claude Desktop

Save the config file and restart Claude Desktop. The ytt-mcp server will be started automatically when Claude needs it.

4

Test with a YouTube URL

Paste a YouTube video URL into Claude and ask it to fetch the transcript. The server supports any video that has auto-generated or manually uploaded captions.

5

(Optional) Debug with fastmcp dev

During development, use the fastmcp inspector to test the server locally in a browser interface before connecting it to a client.

uv run fastmcp dev ytt_mcp.py

YouTube Transcript Examples

Client configuration (Claude Desktop)

Minimal configuration for Claude Desktop — no API keys or environment variables needed.

{
  "mcpServers": {
    "ytt-mcp": {
      "command": "uvx",
      "args": ["ytt-mcp"]
    }
  }
}

Prompts to try

Provide a YouTube URL and ask Claude to process the transcript in various ways.

- "Fetch the transcript of https://www.youtube.com/watch?v=dQw4w9WgXcQ and give me a summary"
- "What are the three main points made in this YouTube video: [URL]?"
- "Extract all the action items mentioned in this tutorial video: [URL]"
- "Translate the key ideas from this lecture into bullet points: [URL]"
- "Does the speaker in this video mention any specific tools or frameworks? [URL]"

Troubleshooting YouTube Transcript

Transcript fetch fails or returns empty for a video

Not all YouTube videos have transcripts available. Videos with disabled captions or that are very new may not have a transcript yet. Try a video that shows a 'CC' button in the YouTube player to confirm captions exist.

uvx command not found after installation

Install uv first using 'pip install uv' or the official shell script (curl -LsSf https://astral.sh/uv/install.sh | sh). After installation, ensure ~/.local/bin or the uv install path is on your PATH and restart your terminal.

Server starts but Claude does not use it for YouTube URLs

Claude does not automatically invoke MCP tools — you must explicitly ask it to fetch the transcript. Include the full YouTube URL in your prompt and say 'fetch the transcript' or 'use ytt-mcp to get the transcript of this video'.

Frequently Asked Questions about YouTube Transcript

What is YouTube Transcript?

YouTube Transcript is a Model Context Protocol (MCP) server that mcp server designed to fetch transcripts for youtube videos. it enables ai tools to access video text content for tasks like summarization, analysis, and key takeaway extraction. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install YouTube Transcript?

Follow the installation instructions on the YouTube Transcript GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with YouTube Transcript?

YouTube Transcript works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is YouTube Transcript free to use?

Yes, YouTube Transcript is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Search & Data Extraction MCP Servers

Explore all search & data extraction servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "ytt": { "command": "npx", "args": ["-y", "ytt"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use YouTube Transcript?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides