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

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.

An MCP server that provides AI agents with a full Ubuntu desktop environment inside Docker, enabling them to perform complex computer tasks like browsing, coding, testing, and GUI automation.

Enables models to remotely control computers over an MCP link, running commands, managing files, automating desktops and browsers, transferring data, and coordinating durable tasks across sessions.

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.

MCP server enabling AI agents to control a real Linux browser with live view, human takeover, and safety guardrails.

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.

Pixel-level browser automation MCP server that drives a real Chrome browser using screenshots as vision input and OS-level mouse/keyboard as output, evading anti-bot detection.

Enables AI agents to operate local desktops and Chromium browsers through MCP tools, unifying accessibility trees, physical input, screenshots, DOM/ARIA, visual grounding, and result verification.

Enables AI hosts to drive cross-platform desktop GUI automation and browser control, providing tools to read, click, type, send shortcuts, screenshot, and verify GUI elements and web pages.

Enables MCP agents to drive the user's already-open Chrome profile through a Manifest V3 extension and loopback bridge, listing and controlling existing tabs, capturing screenshots, and sending clicks, typing, drags and key holds via an independent on-page cursor without moving the system mouse. It also supports form filling, console and network inspection, read-only or confirmed JavaScript execution, file and PDF downloads, and game-style screenshot/action loops with snapshot recovery and an emergency stop.

Provides a JSON-RPC computer use runtime for macOS, exposing 7 MCP tools (observe/act/inspect/session/cancel/trace) as image content blocks so external agents like Claude Code, Pi, OpenCode, or Codex CLI can capture screenshots and drive the desktop with clicks, keys, and typing while enforcing session locking, stale-frame protection, and trace redaction server-side.

An MCP server that enables browser control agents to plan and execute UI tasks using Gemini Computer Use.

Enables fast, precise control of web browsers and the physical desktop through MCP, combining DOM and native OS accessibility targeting with vision-based fallback and human-like mouse movement. Supports clicking, typing, scrolling, dragging, and drawing on canvas or paint applications across Linux, Windows, and macOS.

Enables users to discover jobs by target titles and countries, rank job descriptions by skill coverage across all imported resumes, generate tailored ATS-ready resumes and cover letters, and fill and submit requested application batches through a signed-in AI host with browser access.

Enables OpenCode to safely automate and verify Windows desktop and web browser interactions through 83 MCP tools, including UI automation, screenshots, visual diffing, workflow recording, and secret handling, with strict allowlist-based security.

Gives AI assistants full macOS desktop control via screenshots, mouse, keyboard, scrolling, and app management.

Enables users to record, review, verify, and expose permitted browser workflows as callable MCP tools with typed inputs, isolated Chromium verification, and approval-gated writes.

MCP server that gives any LLM a managed Docker workspace with live browser, terminal, code execution, document skills, and autonomous sub-agents.

An unofficial bridge that lets Claude Code control local macOS applications through an existing OpenAI Computer Use installation by launching the signed Codex client and translating MCP compatibility.

Standalone MCP server for desktop GUI automation on macOS and Windows, exposing a unified tool for accessibility-tree snapshots, input, app control, and browser CDP fast path, driven by any MCP host.

Enables converting webpages into structured JSON using CSS-selector schemas, with anti-bot handling and support for protected pages.

Enables converting any webpage to clean LLM-ready markdown, with extraction, article, and news modes, using a real browser with anti-bot handling.

Fetches a URL and returns the main content as clean Markdown, using plain HTTP when possible and headless Chromium for JavaScript-rendered or bot-protected pages.

MCP server that converts web page URLs to Markdown via the Zyla API.

Enables AI agents to fetch one or many web pages concurrently and receive clean, LLM-ready Markdown with navigation, ads and boilerplate stripped away, plus extracted metadata such as title, description, author, Open Graph tags and canonical URL. It runs locally over stdio with no API key or account, requiring only a single command.

Fetches website content and converts it to Markdown format with AI-powered content cleanup, ad removal, and full OpenAPI/Swagger specification support for easy processing by AI assistants.

Converts X (Twitter) posts into JSON, PDF, PNG, Markdown, or Slack/Discord messages using public endpoints, no API key or login required.

Enables AI agents to control a Playwright-driven browser through natural-language instructions, including page interaction and live browser task execution.

It enables AI agents to call a small set of reliable, permission-aware tools generated from an existing website through the Model Context Protocol, without rebuilding the site.

MCP server that fetches remote or local HTML resources and converts them to Markdown, enabling AI clients to summarize or process web content.