macOS Defaults
Read and write macOS user defaults and settings.
mcp-server-macos-defaults MCP server
MCP server for reading/writing macOS defaults (settings)
Components
Tools
list-domains:- equivalent to running
defaults domains
- equivalent to running
find:- equivalent to running
defaults find <word>
- equivalent to running
defaults-read:- equivalent to running
defaults read <domain> <key> - if
keyis not provided, the entire domain is read
- equivalent to running
defaults-write:- equivalent to running
defaults write <domain> <key> <value>
- equivalent to running
Quickstart
Install
Claude Desktop
On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
Development/Unpublished Servers Configuration
``` "mcpServers": { "mcp-server-macos-defaults": { "command": "uv", "args": [ "--directory", "/path/to/mcp-server-macos-defaults", "run", "mcp-server-macos-defaults" ] } } ```Published Servers Configuration
``` "mcpServers": { "mcp-server-macos-defaults": { "command": "uvx", "args": [ "mcp-server-macos-defaults" ] } } ```Development
Building and Publishing
To prepare the package for distribution:
- Sync dependencies and update lockfile:
uv sync
- Build package distributions:
uv build
This will create source and wheel distributions in the dist/ directory.
- Publish to PyPI:
uv publish
Note: You'll need to set PyPI credentials via environment variables or command flags:
- Token:
--tokenorUV_PUBLISH_TOKEN - Or username/password:
--username/UV_PUBLISH_USERNAMEand--password/UV_PUBLISH_PASSWORD
Debugging
Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.
You can launch the MCP Inspector via npm with this command:
npx @modelcontextprotocol/inspector uv --directory /path/to/mcp-server-macos-defaults run mcp-server-macos-defaults
Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
Похожие серверы
Kone.vc
спонсорMonetize your AI agent with contextual product recommendations
Claude Server MCP
An MCP server for Claude providing advanced context management, including persistent sessions and project-specific organization.
Puzld MCP
Expose your local AI agent CLIs through one MCP endpoint
Linksee Memory
Local-first cross-agent memory MCP. 6-layer structured brain (goal/context/emotion/impl/caveat/learning) with token-saving file diff cache (86% measured savings on re-reads)
Monarch Money
Access and manage your Monarch Money financial data and operations.
ClickUp
An MCP server for ClickUp, allowing AI assistants to interact with and manage tasks within your ClickUp workspaces.
TideMind
Open-source AI memory layer — a living knowledge graph across all your AI tools and notes. Local-first, SQLite-backed, MCP-native.
Notion
Connects AI assistants to your Notion workspace, allowing you to search, create, and manage content using natural language.
Google Tag Manager
Manage Google Tag Manager accounts, containers, and tags via its API, with built-in Google OAuth.
ActiveCampaign
Built for the next generation of intelligent experiences, ActiveCampaign's remote MCP server makes it easy for AI agents to understand, store, and use customer context across tools, channels, and workflows.
MCP Refchecker
A lightweight MCP server that wraps academic-refchecker, letting Claude verify academic citations against Semantic Scholar, OpenAlex, and CrossRef in real time