"Reliable sources for use in training language models" matching MCP servers:

Zero-dependency macOS desktop automation for AI agents. Screenshot, mouse, keyboard, clipboard, and window control via MCP. 18 tools, macOS 13+, one command: npx mac-use-mcp.

MCP server for local Mac desktop control, enabling mouse, keyboard, and screenshot actions for AI agents like Grok and Cursor.

Enables Claude to see and control a real Android phone via MCP, reading the accessibility tree to tap, type, navigate, launch apps, and diagnose connectivity over ADB or cellular.

MCP server for Windows computer use, providing low-token, low-latency automation through UIA/Win32, OCR, and vision. It enables batch actions, shortcuts, isolated desktop execution, and browser control via MCP tools.

Enables a constrained subagent to perform foreground GUI actions on Hyprland—observing, focusing windows, clicking, typing, scrolling, dragging, and managing the clipboard—under per-action approval with lease, audit log, and kill-switch gating.

Enables AI agents to automate both web browsers and native desktop applications through a unified interface, supporting tasks like browsing, clicking, typing, and file clipboard operations via exposed MCP tools.

Enables AI agents to see, locate UI elements, and operate any Windows desktop app through natural language, using accessibility-tree matching with optional vision-model fallback, plus an autonomous visual loop with introspection and meta-learning.

MCP server providing 200x faster macOS computer use via Accessibility API, enabling direct UI automation (click, type, scroll) with ~1s workflows.

Provides native macOS computer control tools including mouse and keyboard simulation, screenshot capture, and application management for MCP-compatible agents. It enables AI assistants to directly interact with the macOS operating system and installed apps through standard tool calls.

Provides safe Linux desktop automation for Codex through focused MCP tools for inspecting, clicking, typing, dragging, and verifying native applications on Wayland and X11.

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.

Enables users to drive a selected Windows application toward a natural-language goal by reading the UI with local OCR/UIA and deciding next actions.

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 downloading content from various social media platforms through a unified API. Provides a single tool to download media from multiple social networks using the Social Download All In One service.

AI-driven browser automation server that implements the Model Context Protocol to enable natural language control of web browsers for tasks like navigation, form filling, and visual interaction.

Enables coding agents to observe and operate Android devices through ADB and uiautomator2, supporting screenshot capture, UI hierarchy access, and actions like tap, swipe, and text input.

Provides desktop automation tools for Windows, enabling mouse and keyboard control, screenshots, clipboard management, and application interaction via the MCP protocol.

MCP stdio server that lets DSH agents see and operate Windows desktop apps via UI Automation, screenshots, mouse/keyboard, OCR, and window management.

Provides AI assistants with a standardized interface to interact with the Todo for AI task management system. It enables users to retrieve project tasks, create new entries, and submit completion feedback through natural language.

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.