What is the macOS Internal Tools MCP Server?

The macOS Internal Tools MCP Server is a tool that allows you to integrate macOS system tools directly into your Large Language Model (LLM) client. It enables you to monitor system performance, perform advanced file searches, and manage file tags using native macOS APIs.

What is an MCP Server?

MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. An MCP server acts as a bridge, allowing AI models to access and interact with external data sources and tools.

What are the key features of the macOS Internal Tools MCP Server?

The key features include real-time system monitoring, enhanced file search with regex support, Spotlight integration, tag management, and native macOS integration.

What operating systems are supported?

The server supports macOS 10.15 or later.

What are the installation requirements?

You need macOS 10.15 or later, Node.js 18.0.0 or later, and npm or yarn package manager.

What permissions are required?

Full Disk Access (recommended for file search) and Developer Tools (for process monitoring).

How do I configure Claude Desktop to use this MCP server?

You need to modify the claude_desktop_config.json file by adding the macOS Tools server configuration to the mcpServers object.

Can I use mcp-installer to install this MCP server?

Yes, you can use mcp-installer for simplified installation.

What tools are available in the MCP server?

The available tools are system_performance for monitoring system metrics and enhanced_search for advanced file searching and tagging.

What types of system performance metrics can I monitor?

You can monitor CPU, memory, disk I/O, and network statistics.

Can I search within file contents using this tool?

Yes, you can perform deep content searches using regex or plain text.

How do I manage file tags?

You can create, search, and manage custom file tags using extended attributes.

Is there caching for performance optimization?

Yes, a multi-level caching system, debounced operations, and rate limiting for system calls ensure optimal performance.

Where is the performance history stored?

Performance history is stored in an SQLite database.

What is the license for this MCP server?

The server is released under the MIT License.

What are some example test prompts?

Example prompts include “Show me my current system performance metrics,” “What are the top 5 CPU-consuming processes on my system?,” and “Search for TODO comments in JavaScript files in my current directory.”

What future enhancements are planned?

Future enhancements include GPU monitoring support, network connection analysis, application-specific performance tracking, and integration with Time Machine for file version search.

How does this MCP Server relate to the UBOS platform?

UBOS is a full-stack AI Agent Development Platform that simplifies the creation and management of AI Agents. This MCP Server can be integrated into your AI Agent workflows on the UBOS platform to provide deeper system awareness and control.