"How to Use MacOS" matching MCP servers:

The first open-source MCP server that enables AI to fully control remote macOS systems.

A local MCP server that lets compatible agents use the official, signed Computer Use broker bundled with the OpenAI ChatGPT macOS app.

Facilitates browser automation with custom capabilities and agent-based interactions, integrated through the browser-use library.

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

Enables Claude to delegate tasks to OpenAI expert models (GPT-5.3-Codex and GPT-5.5) as subagents, with orchestration patterns for safe and effective use.

Enables Codex to send text tasks to ChatGPT web, await responses, continue conversations, choose reasoning effort, and manage projects through MCP tools on macOS.

Enables Codex to use an authenticated ChatGPT Web session as a reasoning and coding backend through isolated browser sessions, without granting ChatGPT direct workspace access.

A lightweight, zero-dependency Python MCP server that exposes a single do_everything tool. Any AI agent that supports MCP can use it to offload all language-model work to a local OpenAI-compatible endpoint, reducing cost on the agent's primary LLM.

MCP server that lets you drive Claude Code sessions hands-free by voice from any MCP client, enabling remote models to send prompts, monitor progress, and get results read back.

Enables ChatGPT web to use local tools like file reading, command execution, and patch application through an MCP server over OpenAI Secure MCP Tunnel.

Enables routing tasks to the right specialist agents, assembling the needed context from a layered catalog of agents, skills, knowledge, runbooks, topics, tools, and connectors, while remembering how a business wants work done.

Browser use using Typesafe's Jev model

Enables low-cost agent models to control Windows applications through a compact, state-safe proxy over Open Computer Use, reducing model-visible context by up to 99.8% with support for record/replay and reusable UI component memory.

Teach any AI agent how you use an MCP server – Soft-Landing to your AI integrations

Hybrid computer-use MCP server that automates browsers and native macOS/Linux apps by fusing accessibility trees, Chrome DevTools Protocol, and vision into one structured context. Exposes four composable tools — cel_see, cel_act, cel_think, cel_perceive — that work with any MCP client and run fully offline via Ollama.

Enables direct MCP-based pairing with T3 Code environments, allowing users to manage environments and projects, start and continue turns, and inspect thread history over stdio without requiring T3 Connect or a local turn CLI.

MCP server that routes Claude Desktop chat into Claude Code, enabling headless execution and terminal handoff with session continuity.

Enables MCP clients to use the local Antigravity CLI for natural-language queries, repository analysis, and agent execution, reusing the user's Antigravity subscription without exporting credentials.

MCP server enabling AI agents to control a real Linux browser with live view, human takeover, and safety guardrails.

Exposes vLLM capabilities to AI assistants, enabling chat completions, model management, and platform-aware container control with automatic detection of Docker/Podman and GPU availability across Linux, macOS, and Windows.