Office-PowerPoint-MCP
Enables AI assistants to programmatically create, manipulate, and analyze Microsoft PowerPoint presentations with advanced formatting and template management.
README
Office-PowerPoint-MCP
Enterprise-Grade PowerPoint Automation Protocol for AI Assistants
Overview
Office-PowerPoint-MCP is a robust Model Context Protocol (MCP) server designed to enable advanced PowerPoint presentation processing capabilities for AI assistants like Claude Code, Amazon Q Developer, and other MCP-compliant clients.
It provides a standardized interface for AI agents to programmatically create, read, manipulate, and analyze Microsoft PowerPoint presentations (.pptx). By abstracting complex presentation object models into clean API tools, it empowers AI assistants to generate professional presentations, reports, and visual documentation workflows autonomously.
Key Benefits
- Seamless Integration: Optimized for Claude Code and Amazon Q environments
- Rich Formatting: Support for complex layouts, animations, and design controls
- Enterprise Ready: Includes template management, media handling, and professional styling
- Secure: Runs locally with explicit permission controls
Features
1. Presentation Management
- Lifecycle Control: Create, copy, merge, and convert presentations (to PDF)
- Structure Analysis: Extract slide content, metadata, and statistics
- Template System: Apply and manage custom presentation templates
2. Content Engineering
- Advanced Layouts: Create complex slide layouts with multiple content areas
- Rich Media: Insert images, videos, charts, and tables with precise positioning
- Dynamic Text: Precision control over fonts, colors, and paragraph styles
- Interactive Elements: Add animations, transitions, and hyperlinks
3. Design & Styling
- Theme Management: Apply and customize presentation themes
- Master Slides: Create and modify slide masters for consistent branding
- Color Schemes: Implement corporate color palettes and design systems
Getting Started
Prerequisites
- Python 3.10 or higher
uv(recommended) orpippackage manager- Microsoft PowerPoint (for advanced features)
Installation
Option 1: Using uvx (Recommended for ephemeral use)
No installation required. You can run the server directly using uvx.
uvx --from office-powerpoint-mcp-server ppt_mcp_server
Option 2: Local Installation
Clone the repository and install dependencies:
git clone https://github.com/ihatesea69/Office-PowerPoint-MCP.git
cd Office-PowerPoint-MCP
pip install -r requirements.txt
Integration Guide
Claude Code
Add the following to your Claude Code MCP configuration:
{
"mcpServers": {
"powerpoint-server": {
"command": "uvx",
"args": ["--from", "office-powerpoint-mcp-server", "ppt_mcp_server"]
}
}
}
Amazon Q Developer (VS Code / JetBrains)
To integrate Office-PowerPoint-MCP with Amazon Q Developer:
- Open your IDE settings and navigate to Amazon Q > MCP Servers
- Add a new server configuration:
- Name:
powerpoint-automation - Command:
uvx - Args:
--from,office-powerpoint-mcp-server,ppt_mcp_server
- Name:
- Restart your IDE. Amazon Q will now have access to PowerPoint tools
Other MCP Clients
Add the following to your MCP configuration file:
{
"mcpServers": {
"ppt": {
"command": "uvx",
"args": ["--from", "office-powerpoint-mcp-server", "ppt_mcp_server"]
}
}
}
API Reference
The server exposes the following tools to the AI assistant.
Core Operations
| Tool Name | Description |
|---|---|
create_presentation |
Create a new blank or template-based presentation |
get_presentation_info |
Extract metadata and structure information |
list_available_presentations |
Scan directory for valid PowerPoint files |
convert_to_pdf |
Export .pptx to PDF format |
Content & Formatting
| Tool Name | Description |
|---|---|
add_slide |
Insert new slides with specified layouts |
add_text_box |
Add formatted text boxes to slides |
add_image |
Insert images with positioning and scaling |
add_table |
Create structured tables on slides |
add_chart |
Generate charts and graphs |
Design Management
| Tool Name | Description |
|---|---|
apply_theme |
Apply predefined or custom themes |
set_slide_layout |
Change slide layouts and master templates |
format_text |
Apply advanced text formatting options |
add_animation |
Create slide transitions and animations |
Example Usage
# Example: Create a business presentation
presentation = create_presentation("Business Report Q4 2024")
add_slide(presentation, "title_slide", title="Q4 Results", subtitle="Company Performance Review")
add_slide(presentation, "content_slide", title="Key Metrics")
add_chart(presentation, slide_index=1, chart_type="bar", data=sales_data)
apply_theme(presentation, "corporate_blue")
save_presentation(presentation, "Q4_Report.pptx")
Troubleshooting
Common Issues
Permission Denied
- Cause: The server cannot access the file system
- Fix: Ensure the running process has R/W access to the target directory. On Windows, ensure the file isn't open in Microsoft PowerPoint
Template Not Found
- Cause: Using a template that doesn't exist in the system
- Fix: Use
list_available_templatesto see available options, or provide full path to custom templates
Image Insertion Failures
- Cause: Relative paths may be ambiguous
- Fix: Always use absolute paths for images
Debugging
Set the MCP_DEBUG environment variable to 1 to enable verbose logging:
# Windows (PowerShell)
$env:MCP_DEBUG = "1"
# Linux/Mac
export MCP_DEBUG=1
Contributing
We welcome contributions! Please see CONTRIBUTING.md for guidelines.
License
This project is licensed under the MIT License. See LICENSE for details.
Roadmap
- [ ] Advanced animation support
- [ ] Integration with online template libraries
- [ ] Collaborative editing features
- [ ] AI-powered design suggestions
- [ ] Support for PowerPoint Online/Office 365
Built for the AI-Powered Productivity Era.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。