"A server for running MCP apps on Windows and Mac" matching MCP servers:

Enables AI coding agents to work inside a disposable Windows guest desktop, where they can run shell commands, launch applications, inspect and operate native GUI controls, perform browser DOM actions, and transfer files. Fresh observations, PNG screenshots, and hashed artifacts let agents verify results without touching the host desktop.

Enables agents to manage and operate macOS VM workspaces through authenticated MCP tools, including lifecycle control, command execution, job monitoring, and access to desktop connection and guest login details.

MCP server that gives AI agents isolated, named Linux computers with stable IDs and lifecycle control. Supports multiple backends like Docker, Fly Machines, Modal, and E2B, with a dashboard for managing sandboxes.

A VMware ESXi/vCenter management server based on MCP (Machine Control Protocol), providing simple REST API interfaces for virtual machine management.

MCP server that integrates with Coolify to let AI assistants manage Coolify instances via a clean toolkit wrapping the official REST API.

MCP server for managing Proxmox VE hosts, providing VM health reports, alerts, and a chat interface via terminal or Cursor.

A Node.js application that provides a JSON-RPC interface to interact with CO2 sensor data, working in both simulation mode and with real Raspberry Pi Pico hardware connections.

Read-only observability MCP for Windows, WSL, Docker, and WSLC.

A virtual Linux desktop as an MCP server, shipped in Docker. Agents drive screen, mouse, keyboard across any GUI — browsers, IDEs, office suites, Wine/Windows apps, legacy software — many in parallel.

Enables AI agents to create and manage BasicDeploy containers with PostgreSQL, S3 storage, and public URLs, including deploying apps, running commands, viewing logs, and sharing containers.

Run AI agents in VM-isolated sandboxes on your Mac.

Manages UTM virtual machines on macOS via AppleScript, enabling cloning, configuration, and control with unique MAC randomization.

Enables running arbitrary JavaScript code in isolated Docker containers with on-demand npm dependency installation, allowing for ephemeral script execution and long-running services with controlled resource limits.

MCP server for controlling a Windows guest VM over WinRM, enabling PowerShell/CMD execution, file transfer, reboot, and KDNET debug configuration, typically paired with kd-mcp.

Enables an AI agent to lease its own Android emulator phone and drive it over stdio: reading the screen, tapping, typing, and opening apps, with every action leaving an audit line and screenshot. Leases keep one agent per phone, and a locked phone stays inert until an operator unlocks it on its own screen.

Controls a real Windows 98 VM through 47 MCP tools, enabling screenshots, mouse/keyboard input, command execution, and file transfers.

Enables AI agents to manage Docker containers, images, Compose stacks, health checks, and logs through a unified MCP interface, ensuring containers stay running with self-healing capabilities.

MCP server for TrueNAS Scale that enables AI assistants to manage storage pools, datasets, apps, VMs, snapshots, and more via the native WebSocket API.

Exposes tools to manage and inspect an OpenMediaVault NAS, running on the NAS and communicating over SSH with any MCP-capable coding harness.

An MCP server that enables agents to attach debugpy to running Python processes inside Docker containers for enhanced debugging and inspection. It provides tools for container autodiscovery, process injection, and generating breakpoint plans based on logs and metadata.

Enables agents to deploy, run, expose, inspect, and manage isolated cloud environments, including databases, caches, browsers, GitHub-hosted apps, and arbitrary OCI images, via MCP tools.

Enables a computer-use agent to see and drive one isolated, sandboxed Linux desktop by exposing Anthropic's computer toolset actions alongside launching apps and listing windows, with screenshots scaled to a 1280-pixel longest side. It runs as a stdio MCP server scoped to a single screen and authenticated by an agent token.

Enables AI agents to spin up real Linux desktops in Docker and drive them by reading windows, pages, and documents as text and acting with tools like opening apps, running menu commands, filling file dialogs, and exporting files. It exposes these capabilities uniformly over MCP, function calling, HTTP, CLI, and Python/TypeScript SDKs, with token-efficient diffs, code mode, and parallel or forked desktops.

Enables AI clients to control an Android emulator via MCP, allowing tasks like tapping, typing, swiping, taking screenshots, and installing apps through natural language commands.

Enables running unknown binaries inside a maximum-hardening, no-network Docker sandbox with fixed containment, and inspecting the exact security boundary and past evidence records.

MCP server that discovers Korean e-Government and financial websites and launches them in a clean disposable Windows Sandbox (or macOS macSandbox) without requiring security software installation. It handles search and sandbox execution, leaving authentication and actual tasks to the user.

Enables AI agents to create, drive, checkpoint, reset and delete resettable Windows and Ubuntu desktop VMs on Apple Silicon Macs, giving them real desktops to click, type and screenshot in plus shell commands, file transfer and port forwarding. All processing is local, so agents can work in isolated guests without leaving the Mac.

A Model Control Protocol server implementation that allows Claude Desktop to use Deepseek models running in Docker, enabling seamless integration between Claude Desktop and Deepseek's language models.

Enables coding assistants to drive iOS Simulators and Android emulators or USB devices for React Native and Expo work, including taking screenshots, reading app and device logs, opening deep links, installing builds, and launching or relaunching apps. It also supports Android-specific actions such as adb reverse for Metro, opening the dev menu, and tapping or typing on screen.

Gives a coding agent its own Docker-hosted Linux desktop with XFCE, Chromium, Blender, LibreOffice, GIMP and a sudo shell, exposing tools for screenshots, mouse and keyboard input, window focus, shell commands, file read/write, opening URLs or GUI apps, and headless Blender renders. The agent can watch and drive that desktop live from a browser while working on the shared project folder.