mcp-server-youtube-transcript

MCP.Pizza Chef: kimtaeyoon83

The mcp-server-youtube-transcript is a Model Context Protocol server designed to provide seamless access to transcripts, captions, and subtitles of YouTube videos. It enables applications and AI models to fetch video text content directly through a simple, structured interface, facilitating enhanced content understanding, summarization, and analysis. This server integrates easily with MCP clients and hosts, supporting real-time context feeding for LLMs like GPT-4, Claude, and Gemini. Installation is streamlined via Smithery, making it accessible for developers building AI-enhanced workflows that require video transcript data.

Use This MCP server To

Fetch YouTube video transcripts for AI summarization Extract subtitles for language translation workflows Provide video captions as context for chatbots Enable content indexing and search of YouTube videos Support accessibility tools with video transcript data Integrate video text into knowledge bases Automate extraction of video dialogue for analysis

README

MseeP.ai Security Assessment Badge

YouTube Transcript Server

smithery badge

A Model Context Protocol server that enables retrieval of transcripts from YouTube videos. This server provides direct access to video captions and subtitles through a simple interface.

mcp-server-youtube-transcript MCP server

Installing via Smithery

To install YouTube Transcript Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @kimtaeyoon83/mcp-server-youtube-transcript --client claude

Components

Tools

  • get_transcript
    • Extract transcripts from YouTube videos
    • Inputs:
      • url (string, required): YouTube video URL or video ID
      • lang (string, optional, default: "en"): Language code for transcript (e.g., 'ko', 'en')

Key Features

  • Support for multiple video URL formats
  • Language-specific transcript retrieval
  • Detailed metadata in responses

Configuration

To use with Claude Desktop, add this server configuration:

{
  "mcpServers": {
    "youtube-transcript": {
      "command": "npx",
      "args": ["-y", "@kimtaeyoon83/mcp-server-youtube-transcript"]
    }
  }
}

Install via tool

mcp-get A command-line tool for installing and managing Model Context Protocol (MCP) servers.

npx @michaellatman/mcp-get@latest install @kimtaeyoon83/mcp-server-youtube-transcript

Awesome-mcp-servers

awesome-mcp-servers A curated list of awesome Model Context Protocol (MCP) servers.

Development

Prerequisites

  • Node.js 18 or higher
  • npm or yarn

Setup

Install dependencies:

npm install

Build the server:

npm run build

For development with auto-rebuild:

npm run watch

Testing

npm test

Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector for development:

npm run inspector

Running evals

The evals package loads an mcp client that then runs the index.ts file, so there is no need to rebuild between tests. You can load environment variables by prefixing the npx command. Full documentation can be found here.

OPENAI_API_KEY=your-key  npx mcp-eval src/evals/evals.ts src/index.ts

Error Handling

The server implements robust error handling for common scenarios:

  • Invalid video URLs or IDs
  • Unavailable transcripts
  • Language availability issues
  • Network errors

Usage Examples

  1. Get transcript by video URL:
await server.callTool("get_transcript", {
  url: "https://www.youtube.com/watch?v=VIDEO_ID",
  lang: "en"
});
  1. Get transcript by video ID:
await server.callTool("get_transcript", {
  url: "VIDEO_ID",
  lang: "ko"
});
  1. How to Extract YouTube Subtitles in Claude Desktop App
chat: https://youtu.be/ODaHJzOyVCQ?si=aXkJgso96Deri0aB Extract subtitles

Security Considerations

The server:

  • Validates all input parameters
  • Handles YouTube API errors gracefully
  • Implements timeouts for transcript retrieval
  • Provides detailed error messages for troubleshooting

License

This MCP server is licensed under the MIT License. See the LICENSE file for details.

mcp-server-youtube-transcript FAQ

How do I install the mcp-server-youtube-transcript?
You can install it easily via Smithery using the command `npx -y @smithery/cli install @kimtaeyoon83/mcp-server-youtube-transcript`.
Does this server support transcripts from all YouTube videos?
It supports videos that have captions or subtitles available, either auto-generated or uploaded by the creator.
Can this server be used with different LLM providers?
Yes, it is compatible with any MCP client and works seamlessly with LLMs like OpenAI's GPT-4, Anthropic's Claude, and Google's Gemini.
Is the transcript data retrieved in real-time?
Yes, the server fetches transcripts directly from YouTube in real-time, ensuring up-to-date content.
What formats are the transcripts provided in?
Transcripts are typically provided as plain text or structured JSON, depending on the client request.
Is there any authentication required to use this server?
Generally, no authentication is needed for public YouTube videos with available transcripts.
Can this server handle multiple transcript requests concurrently?
Yes, it is designed to handle multiple requests efficiently for scalable applications.
How secure is the mcp-server-youtube-transcript?
The server follows MCP principles for secure and scoped interactions, ensuring safe data handling.