# YouTube MCP Agent

An MCP (Model Context Protocol) server agent for analyzing YouTube videos, built with OpenAI's Agent SDK. This tool allows you to extract transcripts, generate summaries, create chapter timestamps, and write content based on YouTube videos.

## Requirements

- Python 3.13+
- OpenAI API key
- `uv` package manager (recommended)

## How to run this example

### uv (recommended)

1. **Clone the repository**
   ```bash
   git clone <repository-url>
   cd yt-mcp-agent
   ```

2. **Install dependencies with uv**
   ```bash
   uv sync
   ```

3. **Set up your OpenAI API key**
   
   Create a `.env` file in the root directory:
   ```bash
   echo "OPENAI_API_KEY=your_api_key_here" > .env
   ```

4. **Run the agent**
   ```bash
   uv run main.py
   ```

5. **Interact with agent**
   
   Once running, you can ask the agent to analyze YouTube videos. Try prompts like:
   - "Summarize this: <Youtube Link>"
   - "Generate chapter timestamps with links"
   - "Write me a LinkedIn post about the video"

### Base Python/pip

1. **Clone the repository**
   ```bash
   git clone <repository-url>
   cd yt-mcp-agent
   ```

2. **Create a virtual environment**
   ```bash
   python -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate
   ```

3. **Install dependencies**
   ```bash
   pip install -e .
   ```

4. **Set up your OpenAI API key**
   
   Create a `.env` file in the root directory:
   ```bash
   echo "OPENAI_API_KEY=your_api_key_here" > .env
   ```

5. **Run the agent**
   ```bash
   python main.py
   ```

6. **Interact with the agent**
   
   Once running, you can interact with the agent via the CLI.