<div align="center">

# `slide-mcp`

### An MCP server and CLI that lets AI agents generate native PowerPoint decks with slides, tables, and speaker notes.

![License](https://img.shields.io/badge/license-MIT-blue.svg) ![Language](https://img.shields.io/badge/language-python-green.svg) ![Status](https://img.shields.io/badge/status-active-success.svg) [![PyPI](https://img.shields.io/pypi/v/slide-mcp)](https://pypi.org/project/slide-mcp/) [![Python](https://img.shields.io/pypi/pyversions/slide-mcp)](https://python.org)

<img src="demo.gif" alt="Demo" width="700" />

</div>

---

## 🎯 Why?

Trending repos show strong demand for AI-generated presentations and MCP-native agent tools, but most existing solutions are heavyweight pipelines or external services. Developers lack a tiny local adapter that exposes safe PPTX primitives to any MCP client. slide-mcp fills that gap with a single Python module.

**Target audience:** AI agent developers, MCP client users, and automation engineers who need programmatic, local PowerPoint generation inside coding agents, chatbots, or document pipelines.

## ✨ Features

- ✨ **MCP tools for creating decks and adding title, bullet, table, and notes slides**
- ✨ **Local PPTX generation with python-pptx and no external service**
- ✨ **CLI demo and stdio server for fast integration**

## 🚀 Quick Start

```bash
# Install
pip install slide-mcp

# Run
slide-mcp --help
```

## 📦 Installation

### From Source

```bash
git clone https://github.com/YOUR_USERNAME/slide-mcp.git
cd slide-mcp
```

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

# Install in development mode
pip install -e ".[dev]"

# Run tests
pytest -v
```

## 🎬 Demo

The GIF above was recorded using [Charm VHS](https://github.com/charmbracelet/vhs):

```bash
vhs < demo.tape
```

## 📖 Usage

```bash
# Show help
slide-mcp --help

# Common usage examples
slide-mcp --example
```

## 🏗️ Architecture

```mermaid
graph LR
    A[Input] --> B[Core Engine]
    B --> C[Output]
    B --> D[Plugins]
    D --> E[Extensions]
```

## 🤝 Contributing

Contributions are welcome! Please:

1. Fork the repo
2. Create a feature branch (`git checkout -b feature/amazing-feature`)
3. Commit your changes (`git commit -m 'Add amazing feature'`)
4. Push to the branch (`git push origin feature/amazing-feature`)
5. Open a Pull Request

## 📄 License

MIT © 2026 — See [LICENSE](LICENSE) for details.

---

<div align="center">

**If this project helped you, please ⭐ star it!**

[Made with ❤️ and AI](https://github.com)

</div>