modelscope·@betancur/keynote-mcp
暂无描述。
A Model Context Protocol (MCP) server that enables AI assistants to control Keynote presentations through AppleScript automation.
** This is an enhanced fork** featuring modular architecture, theme-aware content management, and comprehensive documentation improvements.
Clone the repository
git clone https://github.com/betancur/keynote-mcp.git
cd keynote-mcp
Install dependencies
pip install -r requirements.txt
Grant macOS permissions
Configure Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"keynote": {
"command": "python3",
"args": ["/path/to/keynote-mcp/mcp_server.py"]
}
}
}
Test the server
python3 test_server.py
Note: Make sure Keynote is installed and you have appropriate permissions for automation.
create_presentation - Create new presentationopen_presentation - Open existing presentationsave_presentation - Save presentationclose_presentation - Close presentationadd_slide - Add new slidedelete_slide - Delete slideduplicate_slide - Copy slidemove_slide - Reorder slidesadd_text_box - Add text to slideadd_image - Add image to slideset_slide_content - Set content using theme elements (recommended)get_slide_default_elements - Check available theme elementsscreenshot_slide - Take slide screenshotexport_pdf - Export as PDFOur latest update includes theme-aware content management that uses Keynote's built-in design elements for professional-looking presentations with consistent styling.
Comprehensive documentation is available in the docs/ directory:
# Create new presentation
result = await call_tool("create_presentation", {
"name": "My Presentation"
})
# Add slide with theme-aware content
result = await call_tool("add_slide", {
"title": "Welcome",
"layout": "Title & Content"
})
# Set content using theme elements (automatic positioning & styling)
result = await call_tool("set_slide_content", {
"title": "Project Overview",
"subtitle": "Q4 2024 Results",
"bullet_points": ["Revenue up 15%", "New markets entered", "Team expansion"]
})
# Check what theme elements are available
result = await call_tool("get_slide_default_elements", {"slide_number": 1})
# Add text to specific position
result = await call_tool("add_text_box", {
"text": "Custom positioned text",
"x": 100,
"y": 200
})
# Add image with precise placement
result = await call_tool("add_image", {
"image_path": "/path/to/image.jpg",
"x": 300,
"y": 150
})
This enhanced version includes significant improvements over the original:
docs/ folderCredits: This fork is based on the original keynote-mcp by @easychen. We've enhanced it with modern architecture and professional content management features.
MIT License
一个由FastMCP驱动的服务器,用于通过编程方式创建、编辑和渲染PowerPoint(PPTX)演示文稿,具有幻灯片创建、内容插入和PNG渲染等功能。
赋予AI代理在项目背景下使用灵活的MCP工具安全读取和提取PDF文件中的信息(文本、元数据、页数)的能力。
一种模型上下文协议服务器,通过 Graph API 实现与 Microsoft 365 服务(Excel、日历、邮件、OneDrive、Teams 等)的交互,使人工智能助手能够通过自然语言管理 Microsoft 365 资源。
暂无描述。
暂无描述。
暂无描述。