"macOS" matching MCP servers:

Exposes 28 native tools that let an agent list, search, create, complete and delete Apple Calendar events and reminders, read and compose Mail drafts, inspect and script Safari tabs, and take full-screen, window, region or clipboard screenshots. All actions run through host AppleScript and EventKit with confirmation gates on deletes and never send mail automatically.

A lightweight MCP server that bridges AI agents and macOS, enabling automation of file navigation, application control, UI interaction, browser automation, and system operations.

An MCP server that lets AI assistants see your macOS desktop, capture screenshots, read browser tabs, and preview files via local macOS tools.

Enables macOS system automation, window management, and productivity tools for AI agents, including running AppleScripts, opening apps, retrieving browser tabs, taking screenshots, and controlling system settings.

Give AI agents eyes and hands on macOS.

Enables interaction with Google Chrome tabs through the MCP protocol, allowing clients to retrieve information and control tabs on macOS using AppleScript.

Enables programmatic control of Safari browser on macOS for web automation, testing, and debugging via the Model Context Protocol.

Enables exporting Apple Safari Reading List entries to JSON and adding new items via MCP on macOS.

426+ MCP tools for macOS, all on-device — local AI inference (llama.cpp on Metal), voice, vision OCR, local RAG, browser automation, and ~140 system actions across 26 macOS domains. Nothing leaves your Mac.

Enables MCP agents to control macOS natively with shell, PTY, background Chrome automation, and Accessibility-based desktop control.

Gives AI assistants full macOS desktop control via screenshots, mouse, keyboard, scrolling, and app management.

Provides an MCP server for macOS that allows agents to control a managed browser with accessibility-first actions, visible cursor, and screenshot return.

Native macOS browser (SwiftUI + WKWebView) that exposes an MCP server in-process so AI agents can drive a real local browser with the user's existing logged-in sessions. ~40 tools (navigate, click, fill, screenshot, eval_js, network log, accessibility tree). Local-only with bearer-token auth.

Enables programmatic control of a running macOS cmux terminal, offering tools for workspace inspection, sending keys, notifications, and browser automation.

A native Swift MCP server for full macOS automation, providing 63 tools for controlling windows, browsers, clipboard, screen capture, OCR, input simulation, and more.

Enables MCP clients to run files, processes, shell sessions, browser automation, and native macOS UI actions under explicit workspace permissions and auditable controls.

An unofficial bridge that lets Claude Code control local macOS applications through an existing OpenAI Computer Use installation by launching the signed Codex client and translating MCP compatibility.

Standalone MCP server for desktop GUI automation on macOS and Windows, exposing a unified tool for accessibility-tree snapshots, input, app control, and browser CDP fast path, driven by any MCP host.

macOS desktop automation enabling AI agents to screenshot, switch apps and tabs, click, type, and scroll. Offers two trust levels: read-only screenshot and full UI control.

Turns a Mac into an MCP host exposing terminal, filesystem, browser automation, and macOS controls to approved AI clients via OpenAI's Secure MCP Tunnel.