"Creating a database of novels and screenplays in Google Drive" matching MCP servers:

Enables an AI agent to operate a real computer through ScreenMirror—looking at the screen, acting, and checking its work—while requiring a person's consent for each separately granted capability.

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

Give any LLM agent a real Android or iPhone. 62 MCP tools: tap, swipe, type, screenshot, screen-tree reading, app launch, camera, TTS, crash reports, batched execution. Android via ADB, iPhone via WebDriverAgent, on-device inference, Docker+KVM emulators. Works with Claude Code, Cursor, LangChain, LlamaIndex, and any MCP client. MIT.

Enables local computer diagnostics by sampling CPU, memory, disk, and network activity and displaying the busiest processes in an interactive dashboard. It also supports human-confirmed process-stop proposals while keeping diagnostics local and bounded.

Windows桌面截图与窗口自动化工具，支持后台操作、不抢焦点，可截取窗口/屏幕、模拟鼠标键盘、点击菜单等。

Enables mobile device automation for Android (via ADB) and iOS Simulator (via simctl), allowing you to control devices with natural language through screenshots, UI interactions, text input, and app management.

A TypeScript-based server that enables programmatic management of pseudo-terminal sessions. It allows users to spawn, control, and interact with terminal processes in real-time through the Model Context Protocol.

A Model Context Protocol server that enables execution of AppleScript and JavaScript for Automation scripts on macOS, allowing programmatic control of applications and system functions through a rich knowledge base of pre-defined scripts.

Enables management of visible, interactive terminal sessions across platforms (macOS, Windows, Linux, WSL). Supports creating, executing commands, capturing output, and managing multiple terminal windows simultaneously.

Mac window manager AI agents can drive: see every monitor and window, apply multi-monitor layouts in one call, save and relaunch whole workspaces, snap zones, keep-awake, and annotated screenshots. Backed by a native macOS menu bar app over a local-only loopback API — no cloud, no telemetry.

Enables AI agents to drive a Linux/X11 desktop via AT-SPI accessibility-tree perception and element-level actions, avoiding screenshots and coordinate clicking.

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.

Made for Amiga development: an AI agent builds on the PC and tests on a real Amiga (AmigaOS 2.04+, any 68000) or FS-UAE over the network. Run commands, copy files, take screenshots, drive mouse and keys, click buttons and pick menus by name (MUI, ReAction, GadTools), wait for windows instead of guessing, send ARexx, and check a PiStorm’s temperature or the last crash. 30 tools.

Enables AI assistants to manage local tmux sessions, including creating and controlling sessions, windows, and panes, sending commands, and capturing terminal output.

Enables MCP clients to run Google Antigravity CLI (agy) as durable, detached asynchronous jobs with a permission gate and broker-computed verdicts that do not trust agy's own exit code.

An MCP server for the Arc browser that enables programmatic management of spaces and tabs. It supports actions like listing, creating, and deleting spaces and tabs, as well as focusing spaces and opening URLs via AppleScript.

Enables MCP-compatible clients to manage cron-job.org cron jobs and folders via natural language, including creating, inspecting, updating, and deleting jobs, and reading execution history.

Lets Claude Desktop and Claude Code inspect and drive Windows desktop applications in the background, including clicking, typing, launching, and verifying results, while the user keeps their mouse, keyboard, and foreground window.

Enables AI agents to see and drive Kasm Workspaces desktops by starting and stopping sessions, taking screenshots, and performing clicks, typing, key presses, and scrolling through MCP clients or as a native Hermes Agent plugin.

An MCP server that allows secure execution of macOS terminal commands through Claude or Roo Code with built-in security whitelisting and approval mechanisms.

An MCP server that enables secure execution of shell commands across Windows, macOS, and Linux with built-in whitelisting and approval mechanisms for enhanced security.

SSH MCP Server lets you manage remote Linux servers through natural language in VS Code Copilot Chat. Instead of switching to a terminal and remembering SSH commands

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 file management operations on the desktop including creating, reading, editing, moving, renaming, deleting, and listing files through the Model Context Protocol.

Exposes Codex's Chrome plugin as an MCP server, enabling MCP clients to drive a real, logged-in Chrome browser by navigating, snapshotting the DOM, clicking, typing, taking screenshots, running Playwright, and sending raw CDP commands.

A Model Context Protocol server that enables programmatic control of Moom window layouts on macOS through natural language commands in Claude Desktop.

An MCP server that allows AI agents to drive real Android devices via adb, capturing screenshots, reading the live UI tree, and performing actions like tap, swipe, and type.

A simple MCP server that provides accurate date and time information to Claude models, ensuring they always use the correct current date and time when creating time-sensitive content.

A secure server that enables AI applications to execute shell commands in specified directories, supporting multiple shell types (bash, sh, cmd, powershell) with built-in security features like directory isolation and timeout control.

Enables an AI agent to see and control the screen of an already-running macOS virtual machine over VNC, exposing four tools: screenshot, click, type_text, and key_press. This lets the agent drive a disposable VM's UI directly with its own model, without touching the real desktop or running a separate agent loop.