YouTube Transcript MCP Server logo

YouTube Transcript MCP Server

by PraveenKishore

This project implements an MCP server for fetching YouTube video transcripts in various formats. It allows Large Language Models (LLMs) to access YouTube transcripts securely and efficiently.

View on GitHub

Last updated: N/A

What is YouTube Transcript MCP Server?

The YouTube Transcript MCP Server is a tool that provides an interface for fetching YouTube video transcripts. It exposes a tool, fetch_youtube_transcript, which retrieves transcripts for YouTube videos based on the provided video ID, language code, and desired format.

How to use YouTube Transcript MCP Server?

To use the server, you need to clone the repository, install the dependencies using uv sync, and activate the virtual environment. Then, you can launch the MCP inspector using mcp dev src/server.py or integrate it with tools like Claude Desktop or mcp-client-cli by adding the MCP configuration to their respective configuration files.

Key features of YouTube Transcript MCP Server

  • YouTube Transcript Retrieval

  • Flexible Output Formats (plain text or JSON)

  • MCP Integration

  • Support for multiple languages

Use cases of YouTube Transcript MCP Server

  • Enabling LLMs to process YouTube video content

  • Summarizing YouTube videos

  • Analyzing YouTube video content for sentiment or topics

  • Creating educational resources from YouTube videos

FAQ from YouTube Transcript MCP Server

What is MCP?

MCP stands for Model Context Protocol, a standard for enabling communication between LLMs and external tools.

What formats are supported for the transcripts?

The server supports plain text and JSON formats for the transcripts.

How do I configure the server with Claude Desktop?

Add the MCP configuration to the claude_desktop_config.json file. Refer to the provided link for more details.

What is mcp-client-cli?

mcp-client-cli is a simple command-line tool for running LLM prompts and implementing the Model Context Protocol (MCP) client.

What dependencies do I need to install?

You need to install uv and then run uv sync to install the project dependencies specified in the project's configuration files.