"How to operate a computer and execute commands" matching MCP servers:

An MCP server for tracking and managing AI command usage history using a PostgreSQL database. It enables users to log, search, and view statistics for various AI-related commands and their execution contexts.

A minimal MCP server with get_weather and create_ticket tools, used for testing MCP servers across protocol, unit, eval, transport, and auth layers.

An MCP server that adds a safety layer with eight independent checks and audit logging between a language model and a broker order, supporting both on-disk simulation and live MetaTrader 5 terminals.

Enables AI agents to use a desktop computer with event-driven settling, waiting for the screen to react and stabilize before returning a settled screenshot and verdict.

Computer Use

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 an agent to see and operate a GNOME Wayland desktop like a human, including screenshots, mouse/keyboard control, accessibility tree access, OCR, clipboard, and audio listening.

Enables MCP clients like Claude to query Chinese A-share market data, including K-line charts with forward/backward adjustment, limit-up and limit-down pools, per-stock fund flows, index quotes, and stock news, with automatic symbol normalization and retry handling for throttled data sources.

Provides A-share (Chinese stock market) quantitative analysis through tools for stock screening, northbound capital flow tracking, dragon-tiger list analysis, margin trading, sector analysis, technical indicators, IPO info, and limit-up/down statistics using akshare data.

Open-source computer use MCP server for macOS and Windows, including remote Windows over SSH. Reads accessibility/UI Automation trees and uses Jev for element selection and action verification, with optional screenshot localization for icons and game scenes.

Exposes Anthropic's computer-use action surface (screenshot, click, move, keyboard, clipboard, batch) against a persistent desktop display via MCP stdio protocol. Enables AI agents to control a virtual desktop environment through natural language instructions.

提供A股实时行情、历史K线、财务报表、技术指标等全方位数据查询的MCP服务器，支持盘中即时更新及批量查询。

Enables computer control via mouse, keyboard, OCR, and screen/window management, similar to Anthropic's computer-use.

Safety middleware for AI computer use agents that monitors, enforces policies, and provides guardrails to enable safe desktop interaction.

Gives each agent its own isolated nested Hyprland desktop with a private seat, clipboard and accessibility bus, so it can see the screen and drive a mouse, keyboard, touchpad gestures, windows and apps without touching the user's pointer, focus or windows. Exposes screenshots, zoom, OCR, accessibility-tree control, window management and batched actions as MCP tools, and can optionally act read-only, or with input, on the real desktop.

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 MCP-capable AI agents to control Windows desktops through UI Automation element trees, native screenshots, app launching, batched action sequences, smart waits, and safety gates using normalized coordinates.

MCP server that provides computer control capabilities including mouse movements, keyboard actions, screenshot capture with OCR, and window management through a unified API.

Enables Windows desktop automation via MCP, allowing AI agents to control mouse, keyboard, and screen capture with the same interface as Anthropic's computer-use tool.

Enables AI agents to discover official public data sources, inspect their metadata and endpoint parameters, and execute live queries through a unified response envelope with a 500 ms budget.

A Windows computer-control MCP server for the DeepSeek Harness plugin that lets an agent take screenshots, magnify the view for low-vision assistance, move and click the mouse, type and press keys, enumerate and focus windows, and switch input methods. It also bridges to Krita to drive drawing, pressure-curve, liquify, smudge, and brush operations.

This MCP server provides secure access to databases for AI agents, enforcing authentication, authorization, human approval, logging, and notifications to prevent dangerous actions.

Local MCP server for A-share stock trading via Tonghuashun, offering account/position queries, buy/sell/cancel orders with risk controls and forced user confirmation; currently simulated with a reserved interface for real broker channels.

Enables MCP-speaking clients to control a real desktop via the computer_use tool, including clicking, typing, scrolling, dragging, key combos, app focus, and screen/accessibility capture. It also provides a verdict system that verifies whether input actions had their intended effect, with configurable approval modes.

Relays a result screenshot to Slack so you can review a coding agent's output without opening the app.

An MCP server that enables AI agents to pause and request human approval or information via Slack, Telegram, or macOS dialogs before proceeding with actions.

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

Read-only MySQL MCP server that lets AI agents list tables, describe schemas, and run SELECT/SHOW/EXPLAIN queries with a row cap, bound to a single database for safety.

Enables building and evaluating LangGraph agents over a protocol-level MCP server to measure failure rates across four agent topologies.

Enables coding agents to ask what a window shows and receive a concise JSON answer from a local Ollama model instead of ingesting the full accessibility tree, reducing token usage. It is read-only and supports optional session context, health checks, and model release.