CCM
/MCP
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
adelelo13 avatar

mac-control-mcp

adelelo13/mac-control-mcp
15STDIOregistry active
Summary

A native Swift binary that lets Claude drive macOS through 63 tools spanning Accessibility APIs, window management, screen capture with OCR, Safari and Chrome tab control, synthetic input events, Spotlight search, and system toggles. It's developer-ID signed and notarized, ships as a one-click .mcpb bundle, and runs without Node or Python. The Accessibility bridge alone gives you read/write access to UI trees across every running app, which means you can automate workflows that would otherwise need brittle AppleScript or paid macro tools. File output is restricted to user directories and Desktop to prevent path traversal. Reach for this when you want Claude to operate your Mac the way a user would, clicking buttons and reading windows instead of calling APIs.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →

mac-control-mcp

CI License: MIT Platform Notarized MCP Registry

Native Swift MCP server for full macOS automation. 63 tools in one signed .app bundle — no Python, no Node runtime, no Electron.

mac-control-mcp driving Safari: open tab, type query, capture window, OCR, Spotlight search — all via MCP stdio

Gives any MCP-compatible client (Claude Desktop, Claude Code, Cursor, etc.) the ability to:

  • Read and mutate the Accessibility tree of any running app
  • Drive Safari and Chrome (tabs, navigation, JS eval)
  • Capture the screen, a display, or a specific window (ScreenCaptureKit)
  • OCR what's on screen
  • Click, type, scroll, drag, send key events
  • Control windows (move / resize / fullscreen / minimize / main)
  • Manage the clipboard
  • Launch / activate / quit apps
  • Search Spotlight's index (NSMetadataQuery) and launch results
  • Toggle dark mode, volume, list displays, inspect menus

Install

Requires macOS 14.0+. Three options, in order of simplicity:

1. One-click install (Claude Desktop, recommended)

The server is published as an MCP Bundle — a zip with a manifest.json that Claude Desktop reads directly:

  1. Download mac-control-mcp-v0.2.6.mcpb from the release page.
  2. Double-click the .mcpb file. Claude Desktop opens an install dialog.
  3. Click Install. The server is registered under the name mac-control-mcp and available immediately in new chats.
  4. First tool call triggers the macOS TCC consent prompts (Screen Recording, Accessibility, Apple Events). Grant all three once — the bundle is Developer-ID signed and notarized, so grants persist across updates.

It's also listed on the official MCP Registry as io.github.AdelElo13/mac-control-mcp, so any MCP client that supports the registry will find it by searching for "mac-control".

2. Download the prebuilt app

If you don't use Claude Desktop or want manual control:

  1. Download MacControlMCP-v0.2.6-macos-universal.tar.gz.
  2. Extract and move MacControlMCP.app to ~/Applications/.
  3. Point your MCP client at the binary inside:
{
  "mcpServers": {
    "mac-control-mcp": {
      "type": "stdio",
      "command": "/Users/you/Applications/MacControlMCP.app/Contents/MacOS/MacControlMCP"
    }
  }
}

Add that block to ~/Library/Application Support/Claude/claude_desktop_config.json (Claude Desktop) or ~/.claude.json → mcpServers (Claude Code).

Verify the download with the published SHA-256:

shasum -a 256 MacControlMCP-v0.2.6-macos-universal.tar.gz
# should match MacControlMCP-v0.2.6-macos-universal.sha256 on the release

3. Build from source

For contributors or if you want to tweak the code. Requires Swift 6 / Xcode 16+:

git clone https://github.com/AdelElo13/mac-control-mcp.git
cd mac-control-mcp
./scripts/build-bundle.sh

Produces ~/Applications/MacControlMCP.app/Contents/MacOS/MacControlMCP. Without a Developer ID cert in your keychain it'll fall back to ad-hoc signing (works for local use, TCC grants reset on every rebuild).

To re-sign + re-notarise an existing Apple Developer account:

# one-time: store notary credentials in keychain
xcrun notarytool store-credentials "mac-control-mcp" \
    --apple-id "you@example.com" --team-id "XXXXXXXXXX"

# subsequent builds:
NOTARIZE_PROFILE=mac-control-mcp ./scripts/build-bundle.sh

Tool surface

CategoryTools
Permissionspermissions_status, request_permissions
Accessibilityfind_element(s), query_elements, list_elements, get_ui_tree, get_element_attributes, set_element_attribute, read_value, perform_element_action, wait_for_element, scroll_to_element
App lifecyclelist_apps, launch_app, activate_app, quit_app, force_quit_app, wait_for_app, focused_app
Windowslist_windows, focus_window, move_window, resize_window, set_window_state, wait_for_window, move_window_to_display
Inputclick, mouse_event, drag_and_drop, scroll, type_text, press_key, press_key_sequence, key_down, key_up, convert_coordinates
Menusclick_menu_path, list_menu_paths, list_menu_titles
Browserbrowser_list_tabs, browser_get_active_tab, browser_navigate, browser_new_tab, browser_close_tab, browser_eval_js
Screencapture_screen, capture_window, capture_display, ocr_screen
Clipboardclipboard_read, clipboard_write, clipboard_clear
Spotlightspotlight_search, spotlight_open_result
Systemset_volume, set_dark_mode, list_displays
File dialogsfile_dialog_set_path, file_dialog_select_item, file_dialog_confirm, file_dialog_cancel, wait_for_file_dialog

Total: 63 tools.

Security model

  • Tools that write files (capture_*, ocr_screen) validate output_path via a strict allow-list — only the user-scoped temp dir (NSTemporaryDirectory()) and ~/Desktop, ~/Documents, ~/Downloads, ~/Pictures are accepted. Symlinks at the target path are rejected to prevent redirection. /tmp is deliberately excluded because it's shared across users and opens a TOCTOU window.
  • AppleScript string interpolation for browser_eval_js wraps user code in (0, eval)(…) via JSON.stringify, so quotes/newlines/unicode can't break out of the wrapper.
  • No network calls. Everything is local system integration.

Status (verified in the current release)

ScopeState
Unit / integration test suite63 tests in 11 suites, all green locally and on CI (macos-15)
Live tool probe43 of the 63 tools exercised end-to-end via real MCP stdio against the running binary, all pass
Destructive tools (volume, dark mode, force_quit_app, drag_and_drop, file_dialog_*)Verified live in a reversible way
Code signingDeveloper ID Application (A3W973JZ49) with hardened runtime
Apple notarizationAccepted by Apple Notary Service, ticket stapled, spctl reports source=Notarized Developer ID
Gatekeeper flowExtracted + launched with the com.apple.quarantine xattr set; no right-click-open needed
MCP RegistryPublished as io.github.AdelElo13/mac-control-mcp v0.2.6 — distributed as an .mcpb bundle for one-click install
ArchitecturesUniversal binary (arm64 + x86_64). Intel slice compiles cleanly but has not been runtime-verified on actual Intel hardware
move_window_to_displaySkipped — requires a 2+ display setup

If you run into an untested path, please open an issue with the reproduction — happy to fix fast.

Caveats

  • Cross-origin iframes block browser_eval_js — same-origin policy, not a limitation of the tool. Use AX coords or synthetic CGEvents for content inside embedded iframes from other origins.
  • First-run TCC prompts are unavoidable. macOS requires the user to grant Screen Recording, Accessibility and Apple Events the first time. The usage-description strings in Info.plist make the consent dialogs show up with a clear reason, but you still need to click Allow in System Settings once.

Development

# Run the test suite (63 tests in 11 suites)
swift test

# Build without packaging
swift build -c release

# Live probe the running binary via MCP stdio
python3 scripts/mcp-sweep.py  # if included

License

MIT — see LICENSE.

Contributing

Issues and pull requests welcome. Adversarial reviews especially — prior releases went through 11 rounds of external review before shipping.

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Categories
Web & Browser AutomationAutomation & WorkflowsMobile Development
Registryactive
Packagehttps://github.com/AdelElo13/mac-control-mcp/releases/download/v0.8.1/mac-control-mcp-v0.8.1.mcpb
TransportSTDIO
UpdatedApr 22, 2026
View on GitHub

More from adelelo13

  • Neuromcp4
  • Neurohive1

Related Web & Browser Automation MCP Servers

View all →
aybelatchane avatar
Terminal MCP Server

aybelatchane/mcp-server-terminal

MCP server for AI agents to interact with terminal applications. Think Playwright for terminals.
15
kimimgo avatar
viznoir

kimimgo/viznoir

Cinema-quality science visualization for AI agents — headless VTK via MCP.
13
cap-of-tea avatar
GDD - AI-Controlled Browser Farm

cap-of-tea/gdd

AI-controlled browser farm: N isolated Chromium instances with 36 MCP tools
10
jakeliume avatar
WebPeel

jakeliume/webpeel

Fetch any web page as clean, AI-ready markdown with smart HTTP-to-browser escalation.
10
sh6drack avatar
Zen Mcp

sh6drack/zen-mcp

MCP server for Zen Browser automation via WebDriver BiDi
10
0ics-srls avatar
ui-ticket-mcp

io.github.0ics-srls/ui-ticket-mcp

Human-to-AI code review bridge. Review UI in the browser, AI agents fix code via MCP.
8