agentleFS
aiagentwithdhruvaiagentwithdhruv/skills/mac-control/SKILL.md

mac-control

Skill16 starsChanged 9 months agoMITView on GitHub

MCP server for AI-powered macOS control — apps, display, audio, files, screenshots, clipboard

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No shell=True anywhere

    line 100

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

macOS Control — AI Mac Automation

Give Claude direct control of your Mac through 15 MCP tools. Open apps, toggle dark mode, search files, take screenshots, manage clipboard — all via natural language.

Location

Project: /Users/apple/Aiwithdhruv/AI Development/Claude/Mac-Automation/ MCP Server: Mac-Automation/macos_mcp.py

Tools Reference

System (read-only)

get_system_info()                    # macOS version, chip, RAM, uptime
get_running_apps()                   # All visible running apps
get_disk_usage()                     # Storage per volume

App Control

open_app(app_name="Safari")          # Launch app (validated against /Applications/)
close_app(app_name="Notes")          # Graceful quit via AppleScript
switch_to_app(app_name="Terminal")   # Bring to foreground

Display & Audio

toggle_dark_mode()                   # Switch light <-> dark (instant visual)
set_volume(level=50)                 # 0-100, auto-unmutes

Notifications

send_notification(title="Hey", message="Class starting!", sound="Glass")
play_sound(sound_name="Ping")        # 14 system sounds available

Files & Search

spotlight_search(query="invoice.pdf", folder="~/Documents", limit=20)
open_folder(folder_path="~/Desktop") # Opens in Finder

Clipboard

get_clipboard()                      # Read current clipboard
set_clipboard(text="Hello World")    # Write to clipboard

Screenshot

take_screenshot(region="full")       # Saves PNG to Desktop
take_screenshot(region="window")     # Front window only

Schema

Inputs

NameTypeRequiredDescription
app_namestrvariesApp name without .app (e.g., 'Safari')
levelintvariesVolume 0-100
titlestrvariesNotification title
messagestrvariesNotification body
soundstrnoSound name (default/Glass/Ping/Pop/etc.)
querystrvariesSpotlight search query
folderstrnoFolder to scope search
textstrvariesText for clipboard
regionstrnoScreenshot region (full/window)

Outputs

NameTypeDescription
resultstrHuman-readable result or error message

Credentials

NameTypeRequiredDescription
(none)——No credentials needed — uses local macOS commands

Composable With

  • ghost-browser — screenshot → analyze → automate browser
  • google-mcp — search files → email attachment
  • instantly-campaigns — clipboard → email templates

Cost

Free — stdlib only, no API calls.

Safety

  • Blocked keywords: rm, sudo, shutdown, format, erase, passwd, kill
  • App names validated against /Applications/
  • AppleScript strings sanitized
  • 10s timeout on all commands
  • No shell=True anywhere

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.