Keynote-MCP
A Model Context Protocol server that enables AI assistants to control Keynote presentations through AppleScript automation, supporting slide operations, theme-aware content management, and export functions.
README
Keynote-MCP
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.
Features
- Presentation Management: Create, open, save, close presentations
- Slide Operations: Add, delete, duplicate, move slides
- Theme-Aware Content: Professional content placement using Keynote's design elements
- Modular Architecture: Maintainable codebase with specialized AppleScript modules
- Export Functions: Screenshots, PDF export
Quick Setup
-
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
- System Preferences > Security & Privacy > Privacy
- Add Terminal and Python to Accessibility permissions
- Add Python to Automation permissions for Keynote
-
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.
Available Tools (26 total)
Presentation Management
create_presentation- Create new presentationopen_presentation- Open existing presentationsave_presentation- Save presentationclose_presentation- Close presentation
Slide Operations
add_slide- Add new slidedelete_slide- Delete slideduplicate_slide- Copy slidemove_slide- Reorder slides
Content Management
add_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 elements
Export & Capture
screenshot_slide- Take slide screenshotexport_pdf- Export as PDF
Theme-Aware Features
Our latest update includes theme-aware content management that uses Keynote's built-in design elements for professional-looking presentations with consistent styling.
📚 Documentation
Comprehensive documentation is available in the docs/ directory:
- 📖 Documentation Index - Complete documentation overview
- 🏗️ Modular Architecture - AppleScript modular structure
- 🎨 Theme-Aware Content - Best practices for theme elements
- 🗺️ Project Roadmap - Future development plans and features
Quick Links
- Getting Started: Follow the Quick Setup section above
- For Developers: Modular Architecture
- Best Practices: Theme-Aware Content
💡 Usage Examples
Theme-Aware Content (Recommended)
# 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})
Manual Content Placement
# 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
})
🚀 What's New in This Fork
This enhanced version includes significant improvements over the original:
✨ Major Enhancements
- 🏗️ Modular Architecture: Split monolithic AppleScript into 5 specialized modules for better maintainability
- 🎨 Theme-Aware Content: Smart content placement using Keynote's built-in design elements
- 📚 Comprehensive Documentation: Complete guides in the
docs/folder - 🔧 Enhanced Integration: Improved Python-AppleScript modular execution
- 🌍 Internationalization: All Chinese comments translated to English
🎯 Key Benefits
- Professional Results: Theme-aware functions create presentations with consistent styling
- Better Performance: Modular loading only loads necessary AppleScript code
- Easier Maintenance: Specialized files for different functionality areas
- Developer Friendly: Complete documentation and architecture guides
Credits: This fork is based on the original keynote-mcp by @easychen. We've enhanced it with modern architecture and professional content management features.
License
MIT License
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.