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.

• 📝 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

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

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

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

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 MCP Server

   mcp dev main.py

   Navigate to Stdio

   OR

5. Go cursor or windsurf configure with this json content:

   {
     "youtube": {
       "command": "uv",
       "args": [
         "--directory",
         "/absolute/path/to/youtube-mcp",
         "run",
         "main.py",
         "--transport",
         "stdio",
         "--debug"
       ]
     }
   }

• 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

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