"How to obtain an API key" matching MCP servers:

Outbound-only remote shell, detached long-running jobs, and temporary file courier for AI agents. Hosted Streamable HTTP plus stdio via npx -y @aicommander/mcp.

Provides agents with real Linux VMs to run commands, manage files, expose ports, and track costs, all through an ephemeral sandbox service.

Enables an MCP client such as Claude to inspect a Mac's battery, memory, CPU, GPU, disk, and most energy-hungry apps, and to shut down, restart, sleep, or lock the screen now or on a schedule with a cancellable 60-second grace period.

Enables AI tools to open the macOS Maps app and search for places or addresses through a single MCP tool, without requiring a Maps API key.

Enables AI agents to query Windows process, window, and console information via structured JSON instead of screenshots, reducing token usage by 94-98%.

Lightweight MCP server that exposes tools for system information and weather lookup, designed for agent integration via stdio.

Enables an agent to observe and operate desktop apps and browsers through an accessibility-tree-first view, with clicking, typing, scrolling, dragging and waiting tools. Screenshot handling, coordinate mapping and fail-closed safety rules (risk confirmation, deny-listed apps, stale-observation refusal) are enforced inside the server.

Enables MCP clients to capture screenshots and control a Raspberry Pi's Wayland desktop over an existing SSH connection with mouse, drag, scroll, keyboard, and Unicode typing actions. Input tools return fresh screenshots, enforce single-client sessions with idle release, and reject stale or uncertain state until verified.

Enables an AI client to control an Android emulator or USB device over ADB by selecting a device, inspecting the UI hierarchy, and performing taps, swipes, text entry, key presses, and app launches. It relies only on Android platform-tools and exposes a compatible tool surface for phone automation.

A comprehensive MCP server that enables AI models to perform local file operations, command execution, and task management across multiple platforms. It features advanced capabilities like row-level file editing, directory searching, and system monitoring with built-in security filters.

Enables AI agents to list their Raspberry Pi devices and run shell commands on them—including interactive terminal programs via raw keystrokes and screen reads—through the Raspberry Pi Connect web remote shell, with no SSH, port forwarding or open ports required. Sessions persist per device so working directory, environment variables and background jobs survive between calls, and an allow-list limits which Pis the agent may touch.

Pre-alpha P2P remote-control app with a local stdio MCP bridge for paired computers. Users build from source; platform support and host-side approvals apply.

Enables AI agents to install, remove, update, and query apt packages on Linux via MCP tools.

Lets an MCP client observe accessibility/ARIA trees and act on macOS apps and a Playwright browser by element_index, and experimentally drive a real iPhone through iPhone Mirroring using OCR and normalized taps. Runs entirely on the local machine with no API key or telemetry.

Enables AI agents to securely connect to and manage remote servers via SSH, with tools for running commands, file operations, log inspection, service management, and system monitoring under configurable access controls and audit logging.

Enables any MCP-compatible AI, whether in the browser or running locally, to create and edit projects, run terminal commands and long-running jobs, and optionally use Docker, all guarded by a policy engine, workspace jail, authentication, and audit logging.

Enables MCP clients to operate an Android device through constrained ADB tools for device discovery, screenshots, UI inspection, taps, swipes, text entry, key presses, and app package control, without cloud APIs or a built-in language model.

Connects AI agents to an ASUS IPMI expansion card so they can see the host screen, control mouse and keyboard, read sensors, manage power, and update card firmware through MCP tools.

Enables AI models to play the game Peggle by capturing the primary monitor's screen and simulating mouse clicks. It provides tools for visual analysis and coordinate-based interaction to automate gameplay.

Enables AI agents to control Android TVs, TV boxes, phones, and tablets over ADB through MCP tools for scanning and connecting devices, pressing keys, launching apps, opening URLs, searching YouTube, setting alarms and timers, managing volume and power, checking state, and capturing screenshots.

Enables Claude to control an Android phone over ADB by viewing screenshots and UI hierarchy and performing taps, typing, key presses, app launches, alarms/timers, and notification reads, with safe-by-default access modes and gated destructive actions.

A simple MCP server that provides waiting functionality to pause until other tasks finish, with progress reporting and support for CLI or HTTP server with SSE.

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.

A Model Context Protocol server that enables AI clients to inspect and manage an Unraid server via its GraphQL API, with read-only defaults and optional enabled mutations.

Enables any MCP client to manage an fnOS NAS through natural language, covering authentication, files, AI photo search, app center, Docker, downloads, logs, monitoring, network, power, storage, users, and Baidu Netdisk via 83 tools. Built on FastMCP with bundled trim-cli binaries and OAuth 2.0 + PKCE login, it also exposes raw API passthroughs as a fallback.

A local agent that monitors your system clipboard, automatically uploads copied images to Supabase Storage, and replaces the clipboard content with the public URL for immediate sharing.

Enables AI agents to control real cloud phones by reading screens as text, tapping, typing, installing APKs, handing off to humans, and parking devices to stop billing, without ADB or emulators.

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 an AI agent on a Mac to see and operate a real Windows desktop over Tailscale — screenshots, clicking, typing, scrolling, shortcuts, window focus and system info — through a strict, key-protected connection with no shell or file access. Access is limited to nine desktop tools and requires an unlocked interactive Windows session.

Enables Claude Desktop to control mouse, keyboard, and clipboard on Windows, allowing AI-driven computer interaction tasks like clicking, typing, scrolling, and screenshotting.

MCP server for Datto RMM, enabling Claude to interact with devices, sites, alerts, and jobs in your Datto RMM account.

An MCP server that allows users to ping other hosts to check network connectivity and diagnostic information. It enables LLMs to perform network latency tests and host availability checks through a standardized interface.

Enables an AI assistant to read and change parental controls for supervised children, including downtime, daily screen time limits, app rules, device locking, extra time, and contacts. It uses the parent account's Chrome session to access the private API, with every write verified by reading back the state.

Enables MCP-capable AI assistants to control a Windows computer through GUI automation, file and process operations, PowerShell commands, durable background jobs, and binary file transfer with downloadable exports.

Enables strict resource governance for AI agent processes using Linux cgroup v2, enforcing CPU bandwidth, memory limits, and process limits to prevent resource overconsumption, runaway loops, and fork bombs.

Enables an AI agent to operate a spare Android phone through MCP: capture screenshots, inspect UI controls, tap/swipe, input Chinese text, launch apps, and optionally run rooted shell commands or transfer files. It also supports a live web console for remote viewing and control.

Model Context Protocol server for EasyShell: manage hosts, execute scripts, orchestrate multi-host tasks, schedule AI inspections, and access infrastructure operations from AI assistants.

An MCP server that controls self-hosted QEMU macOS VMs on Linux over QMP, letting agents capture screenshots and send clicks, drags, scrolls, typing, and key chords with no guest helper or Accessibility grant required.

Enables MCP-capable agents to join Landfall incident war rooms as live investigators, contributing findings and widgets to the incident timeline in realtime while pulling other investigators' discoveries, with single-use share links or authenticated sessions.

Full computer control for AI agents on macOS — see, click, type, scroll via MCP. Works with any app, all processing on-device with PII protection.