How does this server differ from macOS Activity Monitor?
It exposes data via the MCP protocol for LLM consumption rather than a graphical interface, and uses `ps` and `lsof` for real-time snapshots.
@Pratyay
基本信息
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mac-monitor-mcp": {
"command": "uv",
"args": [
"tool",
"install",
"."
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
MacOS Resource Monitor MCP Server is a Model Context Protocol server that identifies resource-intensive processes on macOS across CPU, memory, and network usage. It is designed for users who want to monitor system resources via an LLM or other MCP client.
Install globally with uv tool install . or run from source with python src/mac_monitor/monitor.py. Then start the server, which exposes three tools: get_resource_intensive_processes(), get_processes_by_category(), and get_system_overview().
It exposes data via the MCP protocol for LLM consumption rather than a graphical interface, and uses `ps` and `lsof` for real-time snapshots.
macOS operating system, Python 3.10 or later, and the MCP server library (`mcp`).
Data is collected on each tool invocation using built-in macOS command-line utilities `ps` and `lsof`; no persistent storage is used.
The `get_resource_intensive_processes()` tool only returns the top 5 processes per category. Network monitoring counts connections without measuring bandwidth.
The server uses the Model Context Protocol standard; the README does not specify transport details or authentication requirements.

Model Context Protocol Servers

Health by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
评论