YouTube MCP server for AI agents

This MCP server provides tools for YouTube video analysis, allowing you to extract transcripts, generate summaries, and query video content using Gemini AI. The server integrates with your AI tools to enable deeper analysis of YouTube content.

Requirements

Python 3.9+
Google Gemini API key
YouTube Data API key

Installation Options

Install via Smithery (Recommended)

To automatically install the YouTube MCP server for Claude Desktop:

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

Manual Local Setup

Clone the repository:

git clone https://github.com/Prajwal-ak-0/youtube-mcp
cd youtube-mcp

Create a virtual environment and install dependencies:

python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
pip install -e .

Create a .env file with your API keys:

GEMINI_API_KEY=your_gemini_api_key
YOUTUBE_API_KEY=your_youtube_api_key

Run the MCP Server:
```
mcp dev main.py
```
Then navigate to Stdio

Configuration for AI Tools

For Go Cursor or Windsurf

Configure your AI tool with this JSON content:

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

Available Tools

The server provides several tools for interacting with YouTube content:

youtube/get-transcript: Extract the full transcript from a YouTube video
youtube/summarize: Generate a concise summary of video content using Gemini AI
youtube/query: Ask specific questions about video content
youtube/search: Find YouTube videos matching specific search terms
youtube/get-comments: Retrieve and analyze comments on a video
youtube/get-likes: Get the number of likes for a specific video

Each tool can be called through your configured AI assistant once the server is running.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.