YouTube MCP

by Prajwal-ak-0
Verified

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

Integrations

  • Uses Gemini AI to generate concise video summaries and power natural language queries about video content.

  • Provides tools for YouTube video analysis, including transcript extraction, video summarization, natural language queries about video content, search for videos matching specific queries, and comment retrieval and analysis.

YouTube MCP

A Model Context Protocol (MCP) server for YouTube video analysis, providing tools to get transcripts, summarize content, and query videos using Gemini AI.

Features

  • 📝 Transcript Extraction: Get detailed transcripts from YouTube videos
  • 📊 Video Summarization: Generate concise summaries using Gemini AI
  • Natural Language Queries: Ask questions about video content
  • 🔍 YouTube Search: Find videos matching specific queries
  • 💬 Comment Analysis: Retrieve and analyze video comments

Requirements

  • Python 3.9+
  • Google Gemini API key
  • YouTube Data API key

Running Locally

Installing via Smithery

To install youtube-mcp for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @Prajwal-ak-0/youtube-mcp --client claude

Option 1: Direct Installation

  1. Clone the repository:
    git clone https://github.com/Prajwal-ak-0/youtube-mcp cd youtube-mcp
  2. Create a virtual environment and install dependencies:
    python -m venv .venv source .venv/bin/activate # On Windows: .venv\Scripts\activate pip install -e .
  3. Create a .env file with your API keys:
    GEMINI_API_KEY=your_gemini_api_key YOUTUBE_API_KEY=your_youtube_api_key
  4. Run the MCP server:
    python main.py

Option 2: Using MCP CLI

  1. Install the MCP CLI:
    pip install mcp
  2. Create an mcp.json file in your project:
    { "youtube": { "command": "uv", "args": [ "--directory", "/absolute/path/to/youtube-mcp", "run", "main.py", "--transport", "stdio", "--debug" ] } }
  3. Start the server with MCP:
    mcp run youtube

Using with Docker

  1. Build the Docker image:
    docker build -t youtube-mcp .
  2. Run the container with your API keys:
    docker run -e GEMINI_API_KEY=your_gemini_api_key -e YOUTUBE_API_KEY=your_youtube_api_key youtube-mcp

Deploying on Smithery

This MCP server can be deployed on Smithery for easier access:

  1. Add or claim your server on Smithery
  2. Click "Deploy" on the Smithery Deployments tab
  3. Provide your API keys when prompted

Available Tools

  • youtube/get-transcript: Get video transcript
  • youtube/summarize: Generate a video summary
  • youtube/query: Answer questions about a video
  • youtube/search: Search for YouTube videos
  • youtube/get-comments: Retrieve video comments
  • youtube/get-likes: Get video like count

Contributing

Contributions welcome! Please feel free to submit a Pull Request.

-
security - not tested
F
license - not found
-
quality - not tested

A Model Context Protocol server that analyzes YouTube videos, enabling users to extract transcripts, generate summaries, and query video content using Gemini AI.

  1. Features
    1. Requirements
      1. Running Locally
        1. Installing via Smithery
        2. Option 1: Direct Installation
        3. Option 2: Using MCP CLI
      2. Using with Docker
        1. Deploying on Smithery
          1. Available Tools
            1. Contributing