"Free and open-source GPS without an API" matching MCP servers:

Model-agnostic computer-use tools over MCP, enabling screen capture and automated actions (click, type, scroll) via natural language tool calls.

Lets AI agents see and control desktop applications through the accessibility layer, enabling clicking, typing, scrolling, dragging, and window/app management across macOS, Windows, and Linux entirely on the local machine.

Enables AI agents to control macOS via the ZCode CUA 0.5.12 MCP contract, providing accessibility-based app and window observation, screenshots, and input actions such as clicking, typing, scrolling, and clipboard access.

MCP server for CachyOS connecting ChatGPT in developer mode to inspect and operate files, terminal, processes, apps, clipboard, and KDE/Wayland desktop.

Enables AI agents to observe and control the user's live desktop by listing apps, reading accessibility trees, and performing clicks, typing, scrolling, dragging, and other input actions with per-action approvals and local audit archives.

Enables ChatGPT conversations to drive a paired Windows PC by reading and writing files, running interactive terminals, automating desktop UI, and composing or editing DOCX documents in WordCraft, all through 42 MCP tools. Access is secured with OAuth, device pairing, approved folders, and locally managed permissions for sensitive actions.

Enables the model to observe and control the live desktop via accessibility trees and screenshots, performing actions like clicking, typing, scrolling, dragging, and setting values.

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 AI agents to manage a Canonical Landscape estate, including inventory, alerts, patching, and script execution, with built-in safety layers to prevent accidental destructive actions.

Parse, validate, and explain cron expressions with pay-per-call via x402 (USDC on Base L2), returning next run times in any timezone.

Enables agents to control a physical iPhone from macOS through local phone tools, including USB capture, Bluetooth HID, and AssistiveTouch interactions. It also exposes relay tools for remote access over Streamable HTTP with optional OAuth.

This MCP server enables an AI agent to control a Windows PC through human-like interactions such as screen capture, OCR, mouse, keyboard, and navigation, without using shortcut APIs.

An open-source MCP server that lets any coding agent operate your computer like a person does—reading the UI through accessibility trees, clicking and typing in the background, showing an agent pointer, zooming into regions, and driving your signed-in Chrome on macOS, Windows, and Linux.

MCP server for macOS desktop automation enabling screenshot, click, type, scroll, and more. Retina-aware, supports CJK text input and multi-monitor, works with any MCP client without API keys.

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

MCP server that lets AI clients manage a Qinglong (qinglong) panel via natural language, covering crons, environment variables, scripts, subscriptions, logs, configs, and dependencies through its Open API.

Enables Claude AI to open files and directories with system default applications or specified apps, and reveal items in macOS Finder.

An MCP server that enables Claude to access Windows screenshots from WSL2, allowing users to easily share screenshots with Claude Code without manually navigating complex file paths.

MCP server that lets an AI assistant see and control an Android phone over ADB: screenshots, UI dump, tap, swipe, type, keys, open apps. Safety guards: device allowlist, sensitive-app block, raw shell off by default, rate limit.

Enables interaction with macOS Siri Shortcuts via the Model Context Protocol, allowing users to list, open, and run shortcuts dynamically with optional inputs.