"Remote desktop control and assistance tools" matching MCP servers:

Enables LLMs to capture desktop screenshots and control the mouse and keyboard on Linux, including Wayland, through MCP.

Windows desktop-control MCP server: screenshot, window mgmt, mouse/keyboard input, recording.

Let AI agents operate a real USB-connected iPhone from Linux — no Mac, no jailbreak, no paid developer account. Screenshots, taps, swipes, text input, element tree and app control via WebDriverAgent, with CoreDevice HID fallback.

Deterministic, LLM-first control of Word documents (.docx). An agent reads the outline, finds text by phrase, and applies edits as tracked changes and comments in one atomic batch, with a safety layer that refuses edits based on a stale read and rolls back failed batches. It works on .docx files directly, and can also drive an open document in Microsoft Word on Windows or in LibreOffice Writer.

Gives an AI assistant the post-OBBBA federal student loan rules, so it can compute monthly payments under the Repayment Assistance Plan, compare them with standard plans, look up 2026 borrowing limits, and track when SAVE, PAYE and ICR borrowers must move. Results come back as structured JSON with plain-English summaries, effective dates and cited statute or StudentAid.gov sources.

Enables secure, deny-by-default automation of Windows windows with per-action permissions, allowing observation, clicking, typing, and dragging on approved applications while verifying target identity and focus at runtime.

Gives ChatGPT controlled access to local files, terminal sessions, and Windows desktop UI through a local-first policy gateway with workspace-scoped permissions and stable MCP tools.

Search and pull 620+ React and Tailwind sections into your project over MCP.

Educational tools agent by Birkan Yavuz — an A2A + MCP server for classroom tools, with creator attribution in every result. It offers a catalog of 24 real classroom activities, including math visualizers and reading and sight-word tools.

Enables deterministic calculations for AI API and subscription costs, meeting time zones, recurring schedules, and cron next-run previews, returning normalized inputs, units, assumptions, dated sources, and links to results.

Image generation for Claude Code, Claude Desktop and any MCP client, using your existing ChatGPT subscription. Drives the already-signed-in Codex desktop app over the Chrome DevTools Protocol - no API key, and no Codex agent quota. Supports iterative refinement through a reusable conversation. Windows only; requires the Codex desktop app.

Windows desktop automation MCP server — screenshot, mouse, keyboard & UI Automation. Lets LLM agents see and control your Windows desktop directly.

Provides full control of a macOS system, enabling AI agents to execute shell commands, run AppleScript, manage files and processes, and perform human-like GUI interactions such as clicking, dragging, scrolling, and typing, with a screenshot-based perception loop.

Enables AI agents to drive the Arc browser on macOS, including tab management, navigation, page reading, DOM interaction, and JavaScript scripting via AppleScript automation.

Allows AI clients to see and control Windows 10/11 desktops via MCP, with screenshots, UI Automation, Chrome CDP, keyboard/mouse, and terminal using semantic element targeting.

an open-source MCP server that lets Claude Code (or Cursor, Codex, Gemini CLI) work inside the Notion Desktop app you’re already logged in to. No Company Authorise

Pre-alpha P2P remote-control app with a local stdio MCP bridge for paired computers. Users build from source; platform support and host-side approvals apply.

MCP server that routes Claude Desktop chat into Claude Code, enabling headless execution and terminal handoff with session continuity.

Enables AI agents to control the user's Chrome or Firefox browser, leveraging existing sessions for tasks requiring authentication and user handoff.

A Model Context Protocol server that wraps AutoIt functionality, enabling LLMs to automate Windows desktop tasks including mouse/keyboard operations, window management, and UI control interactions.

Enables users to resolve library identifiers and retrieve Context7-compatible documentation through tools that forward requests to the hosted Context7 remote MCP endpoint.

Enables AI agents to control Linux desktops and compositors, including Hyprland/Wayland window management, PipeWire audio routing, systemd diagnostics and self-healing, notifications, screenshots, and optional agent memory.

Enables AI agents to search, filter, and monitor curated AI model API free credits and low-cost token promotions through eight tools, four resources, and three prompts — including finding deals expiring soon, checking eligibility and blocked conditions, and producing daily briefs.

Enables recall of promoted team and org knowledge from GitHub repositories via Claude.ai, supporting search and status checks.

Enables AI agents to query multi-cloud costs, inventory, waste, and commitments across AWS, GCP, Cloudflare, and OVH through read-only MCP tools.

Forwards GitHub tool calls to GitHub's hosted Copilot remote MCP endpoint, enabling repository, branch, file, search, issue, and pull request operations without a local REST client. Exposes a pinned core set of 14 tools authenticated with a personal access token.

An MCP server that connects WhatsApp Web to AI tools like Gemini and Claude, providing chat reading, messaging, and a local CRM with draft-and-approve workflows.

Enables AI assistants to operate a real, logged-in Firefox session through an extension, including tab and history management, page reading, screenshots, and clicking, typing, or scrolling on domains the user approves.

Bridge that lets stdio-only MCP clients connect to remote MCP servers with OAuth and other auth support, enabling local clients to use remote, authorized MCP servers.

MCP tool server that gives any AI agent the ability to search, scrape, and analyze content across the internet.