Full macOS control — drive a Mac like a human: shell, AppleScript, files, and human-like GUI.
A Model Context Protocol server that gives an AI agent full control of a Mac — like a person sitting at it. Shell, AppleScript, files, processes, and human-like GUI control: move, click, double/right-click, drag, scroll, type, and press key combos — with a screenshot + window/screen-size perception loop.
⚠️ This server is full-control by default. It starts in
adminmode with command execution, deletes, and GUI input all enabled. That is powerful and dangerous: anything the agent reads (a web page, an email, a file) could contain a prompt injection that then runs arbitrary code on your Mac. Only connect it to an agent and content you trust. SetMACCTL_SAFE_MODE=trueto flip the whole thing to safe-by-default. If you want safe-by-default as the baseline, use the sibling@dockndevai/mcp-macosinstead.
Part of the dockndevai MCP server suite.
Perceive — screenshot, get_screen_size, list_windows, get_frontmost_app, list_apps, system_info, list_directory, read_file, list_processes, get_clipboard
Operate the desktop like a human — move_mouse, click (left/right/double), drag, scroll, type_text, key_press (with ⌘/⌥/⌃/⇧), activate_app, quit_app, open, set_clipboard, notify, write_file
Full power — run_command (any program, no shell unless you ask for one), run_applescript (AppleScript/JXA — drive any scriptable app), delete_path (→ Trash), kill_process
The classic loop: screenshot → decide → click/type/drag/scroll → screenshot again.
npx -y @dockndevai/mcp-mac-control
macOS only. You'll need to grant the host app (Terminal, your IDE, Claude Desktop, …) macOS permissions the first time each capability is used:
screenshotclick, type_text, drag, scroll, key_press) and list_windowsbrew install cliclickclaude mcp add mac-control -- npx -y @dockndevai/mcp-mac-control
That's it — it's full-control by default. To scope it down, add env flags (see below). See docs/CLIENTS.md for Claude Desktop / Cursor / Codex / VS Code / Windsurf, and .env.example for every variable.
Full control needs no configuration. Everything below is about restricting it:
| Variable | Default | Effect |
|---|---|---|
MACCTL_SAFE_MODE | false | true → read-only, every power gated, confirmations on (safe-by-default) |
MACCTL_MODE | admin | read-only / read-write / admin — caps which tools are registered |
MACCTL_ALLOW_EXEC | true | shell / AppleScript / kill |
MACCTL_ALLOW_DELETE | true | delete to Trash |
MACCTL_ALLOW_INPUT | true | GUI input (mouse/keyboard) |
MACCTL_CONFIRM | false | true → destructive ops pause for human approval via MCP elicitation |
MACCTL_PATH_ALLOWLIST | (empty = anywhere) | confine file ops to these roots |
MACCTL_PROTECTED_PATHS | (empty) | roots readable but never modified/deleted |
MACCTL_COMMAND_ALLOWLIST | (empty = any) | restrict run_command to these programs |
MACCTL_DRY_RUN | false | validate + log writes without executing |
MACCTL_AUDIT_LOG | true | JSON audit line per guarded op, to stderr |
The policy engine (src/security.ts) is the same graduated model as the rest of the suite — this server just ships it wide open by default. See SECURITY.md.
For an extra layer on top of the static rules, this server can consult a local
laya-guard daemon before running a high-risk tool
(run_command, run_applescript, delete_path). The guard classifies the actual command —
deterministic patterns plus a local decision model — as allow / confirm / block. It runs after
the deterministic policy and can only tighten (add a confirm or block), never grant.
| Variable | Default | Effect |
|---|---|---|
MACCTL_GUARD_MODE | off | monitor (log what it would do) / enforce (block or require confirm) |
MACCTL_GUARD_URL | http://127.0.0.1:8799 | the local laya-guard daemon |
MACCTL_GUARD_TIMEOUT_MS | 2000 | per-check timeout |
MACCTL_GUARD_FAIL_CLOSED | confirm | when the daemon is unreachable in enforce mode: confirm or allow |
Run the daemon with pipx install laya-guard && laya-guard. Start in monitor to see what it catches,
then switch to enforce.
npm install
npm run build
echo '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}' | node dist/index.js # list tools
npm test
MIT
Source-derived launch command. Check the maintainer’s required arguments and credentials before running:
npx -y @dockndevai/mcp-mac-controlMerge this template into ~/Library/Application Support/Claude/claude_desktop_config.json. Keep existing servers. Add any arguments, credentials, and permissions required by the maintainer; this template has not been install-tested.
{
"mcpServers": {
"io-github-dockndevai-mcp-mac-control": {
"command": "npx",
"args": [
"-y",
"@dockndevai/mcp-mac-control"
]
}
}
}Restart Claude Desktop completely for changes to take effect. Confirm the server appears connected in the client’s tool list, then try a read-only example from its documentation.
Claude Desktop setup referenceio.github.dockndevai/mcp-mac-control works with any MCP-compatible client. Copy the config snippet from the Configuration section above and add it to the file shown for your client, then restart the application.
~/Library/Application Support/Claude/claude_desktop_config.jsonRestart Claude Desktop completely for changes to take effect.~/.cursor/mcp.jsonRestart Cursor for changes to take effect..vscode/mcp.jsonReload VS Code window for changes to take effect.~/.codeium/windsurf/mcp_config.jsonRestart Windsurf for changes to take effect..mcp.jsonSave at the project root, then start Claude Code in that project and review the MCP server approval prompt. Keep real credentials out of shared files.