mac-control-mcp

Native Swift MCP server for full macOS automation. 153 tools in one signed .app bundle — no Python, no Node runtime, no Electron. Full list with parameters: docs/TOOLS.md.

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+. Four 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-v<version>.mcpb from the latest release.
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. Install via npm / npx

For clients that are configured with a command line rather than a file path. The npm package mac-control-mcp is a thin launcher: it has no runtime dependencies, and on install it downloads the notarized MacControlMCP.app for that exact version from this repo's GitHub release, verifies it against the published .sha256, refuses any archive entry that escapes the install directory, and re-checks the bundle with codesign --verify --deep --strict, spctl --assess --type execute and a pinned Team ID (A3W973JZ49). The first run therefore pulls ~3 MB; later runs are local.

Claude Desktop — ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "mac-control-mcp": {
      "command": "npx",
      "args": ["-y", "mac-control-mcp"]
    }
  }
}

Claude Code:

claude mcp add mac-control-mcp -- npx -y mac-control-mcp

Cursor — ~/.cursor/mcp.json:

{
  "mcpServers": {
    "mac-control-mcp": {
      "command": "npx",
      "args": ["-y", "mac-control-mcp"]
    }
  }
}

ChatGPT (developer mode, local MCP connector) — mcp.json:

{
  "mcpServers": {
    "mac-control-mcp": {
      "command": "npx",
      "args": ["-y", "mac-control-mcp"],
      "transport": "stdio"
    }
  }
}

Two flags are handled by the launcher itself instead of being forwarded to the binary:

npx -y mac-control-mcp --version    # version of the bundled .app
npx -y mac-control-mcp --app-path   # path to MacControlMCP.app

--app-path is what you need when granting macOS permissions by hand. Note that TCC grants go to the MCP host application that launches this process (Claude Desktop, Cursor, your terminal), not to npx or to the script — run the permissions_status tool once from your client to see which grants are missing and which app they belong to.

MAC_CONTROL_MCP_SKIP_DOWNLOAD=1 skips the download (CI, sandboxed builds); HTTPS_PROXY and NO_PROXY are honoured.

3. Download the prebuilt app

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

1. Download MacControlMCP-v<version>-macos-universal.tar.gz from the latest release.
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-v<version>-macos-universal.tar.gz
# should match MacControlMCP-v<version>-macos-universal.sha256 on the release

4. 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

Selected categories — this table is a curated subset, not the full list. For the complete, auto-generated tool reference (every tool, its description, and its required/optional parameters, regenerated straight from the tool registry so it can't drift), see docs/TOOLS.md.

Which tool when

Several tools overlap in purpose. Based on their actual implementations:

Screen capture — capture_screen vs capture_screen_v2 vs capture_window vs capture_display

• capture_screen — main display (or a rectangular region within it) to a PNG file, returns the file path + width/height. Simple, synchronous, no size limits applied.
• capture_screen_v2 — main display only, but stores the PNG as a content-addressed artifact under ~/.mac-control-mcp/artifacts/<sha256>.png and returns {content_ref, bytes, sha256}. Defaults to inline=false and downscales to max_dimension/max_bytes (4000px / 4MB by default) specifically to avoid blowing up an MCP client's context window with a huge inline image (referenced in its own description as a fix for claude-code issues #13383/#45785). Prefer this one when the image is going back through an LLM context rather than straight to disk.
• capture_window — screenshots one specific window by PID (optionally filtered by title_contains), not the whole display.
• capture_display — screenshots one specific physical display by its index from list_displays, for multi-monitor setups.

Accessibility tree / element lookup — find_element vs find_elements vs query_elements vs list_elements vs get_ui_tree vs ax_tree_augmented