Control your Mac with AppleScript MCP server for automation and remote system management
Welcome to the AppleScript MCP Server repository! This project provides an innovative solution by enabling seamless execution of AppleScript commands through a Model Context Protocol (MCP) server, offering complete control over your macOS environment. Whether you're automating tasks, controlling applications, or managing system settings, this tool facilitates robust interactions between various devices and applications.
The AppleScript MCP Server leverages the Model Context Protocol to provide a powerful platform for interacting with Mac systems via HTTP requests. Key features include:
Additionally, this server supports a range of MCP clients, including Claude Desktop, Continue, Cursor, and more.
The architecture of AppleScript MCP Server revolves around the Model Context Protocol (MCP), which acts as a standard interface for AI applications. This protocol ensures seamless communication between the server and various tools and data sources.
graph TD
A[AI Application] -->|MCP Client| B[MCP Protocol]
B --> C[MCP Server]
C --> D[Data Source/Tool]
style A fill:#e1f5fe
style C fill:#f3e5f5
style D fill:#e8f5e8
graph TD
A[Client] -->|Send Request| B[MCP Server]
B -->|Process Request| C[Data Processing & Execution]
C -->|Return Result| D[Client/Tool]
style A fill:#e1f5fe
style B fill:#f3e5f5
style C fill:#f6ecff
style D fill:#f0fff4
To begin using the AppleScript MCP Server, follow these steps:
Clone the Repository
git clone https://github.com/Hassanali4/applescript-mcp.git
cd applescript-mcp
Install Dependencies
npm install
Start the Server
npm start
Once started, your MCP server will be up and running, ready to receive AppleScript commands via HTTP requests.
For instance, an AI workflow can utilize the MCP server to trigger specific actions based on user prompts or predefined scenarios.
curl -X POST http://localhost:3000/execute -d 'tell application "Finder" to make new folder at desktop with properties {name:"Automated Folder"}'
This command creates a new folder named "Automated Folder" in your macOS desktop, demonstrating how AI applications can integrate and execute tasks seamlessly.
curl -X POST http://localhost:3000/execute -d 'tell application "System Events" to keystroke "Q" using command down'
In this scenario, pressing Command+Q
closes the active application, showcasing how such commands can be automated or triggered in response to certain events.
The AppleScript MCP Server offers seamless integration with popular AI clients. The following compatibility matrix highlights supported MCP clients:
MCP Client | Resources | Tools | Prompts | Status |
---|---|---|---|---|
Claude Desktop | ✅ | ✅ | ✅ | Full Support |
Continue | ✅ | ✅ | ❌ | Tools Only |
Cursor | ❌ | ✅ | ❌ | Limited |
The server is optimized for performance and compatibility across various macOS environments. Below are the supported macOS versions:
{
"mcpServers": {
"[server-name]": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-[name]"],
"env": {
"API_KEY": "your-api-key"
}
}
}
}
This sample configuration demonstrates how to define the MCP server setup, including command execution and environment variables.
Q: Can I use AppleScript MCP with other AI clients?
Q: Are there any performance limitations?
Q: How does the data flow work between clients and the server?
Q: What happens if an AppleScript fails execution?
Q: Can I customize the server settings beyond basic configurations?
We welcome contributions from the community! If you have suggestions, bug fixes, or new features, please open an issue or submit a pull request.
git checkout -b feature/YourFeatureName
git commit -m "Add your message here"
git push origin feature/YourFeatureName
For detailed documentation on how to use AppleScript MCP, please refer to the Wiki.
If you need additional support or have questions, feel free to reach out via the Issues tab on GitHub.
We would like to thank the open-source community for their contributions and support. Your efforts make projects like this possible.
This project is licensed under the MIT License. See the LICENSE file for more details.
Feel free to modify the content as needed. Happy scripting! 🍏
Next-generation MCP server enhances documentation analysis with AI-powered neural processing and multi-language support
Learn to connect to MCP servers over HTTP with Python SDK using SSE for efficient protocol communication
Python MCP client for testing servers avoid message limits and customize with API key
Discover easy deployment and management of MCP servers with Glutamate platform for Windows Linux Mac
Explore community contributions to MCP including clients, servers, and projects for seamless integration
Learn how to use MCProto Ruby gem to create and chain MCP servers for custom solutions