📡 MCP Radar

mrpulor-gh/nuphus-mcp

Desktop automation MCP server — computer use for any AI agent: control screen, windows, mouse/keyboard, and Chrome via Model Context Protocol (stdio)

⭐ 152 stars
⑂ 17 forks
Rust
momentum ▲ 338.0
created 2026-08-01
on radar since 2026-08-03
star trend 27 → 152 since 2026-08-03
ai-agentbrowser-automationchrome-automationclaudecomputer-usecomputer-visiondesktop-automationmcpmcp-servermodel-context-protocolocrrust
View on GitHub ↗Homepage ↗

About nuphus-mcp

Desktop automation MCP server — computer use for any AI agent. See the screen, control windows/mouse/keyboard, and drive Chrome over the Model Context Protocol (stdio). Desktop & browser automation need no API key; OCR runs locally; vision plugs into your own vision LLM (OpenAI-compatible, BYOK).

nuphus-mcp is a lightweight, cross-platform desktop automation MCP server that exposes desktop + browser automation as standard MCP tools. It speaks JSON-RPC 2.0 over stdio — no daemon, no network service, one binary. Claude Desktop, Cursor, VS Code, Copilot, or any MCP client can connect and immediately control the screen, windows, keyboard/mouse, and Chrome — computer use for any AI agent — desktop & browser automation need no API key; local OCR is built in; vision works with your own vision LLM (OpenAI-compatible, BYOK).

🇨🇳 Mainland China mirror: this repo is mirrored on Gitee for fast in-China access (Chinese docs served by default there). 中文文档

- 36 MCP tools (15 desktop + 21 browser) — screenshots, window control, mouse/keyboard, Chrome CDP automation, and more — see TOOLS.md / TOOLS.zh-CN.md for the full reference. - Desktop automation: screen size, screenshot (BMP/base64), window list, window activate/screenshot/move/resize/info, mouse click/drag/scroll/position, keyboard input/hotkey, clipboard write/clean — implemented on the desktop-api crate (xcap + Win32, no Tauri dependency). - Computer vision pair: desktopvision (BYOK — send a screenshot to your own vision model via an OpenAI-compatible API) + desktopperceive (local OCR with PaddleOCR, models auto-downloaded on fir

From the project README.

Maintaining this server?

Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:

[![On MCP Radar](https://mcp.liqiwa.com/badge.svg)](https://mcp.liqiwa.com/s/mrpulor-gh--nuphus-mcp.html)

Related MCP servers

nikships/droid-codex-computer-use

🖱️ Let Factory Droid control your Mac with the Codex app's Computer Use tool. One-command install, no approval forms, works with any Codex install path.

⭐ 3JavaScript
tailscale-mcp/tailscale-mcp

MCP server for Tailscale, backed by the tailscale CLI and control-plane REST API

⭐ 8Rust
nettanvirdev/inertia

inertia-ai: a desktop workspace for AI agents. Chat, built-in tools, MCP and OpenAPI integrations, Docker/Daytona sandboxes with a live desktop, routines and memory. Bring your own model and keys.

⭐ 7Rust
naman-sharma12345/kimo

MCP-first AI video editor in Rust/C++. Every operation is an AI-callable tool.

⭐ 6Rust
menot-you/n-memory

Memory your agent can trust — every answer carries its source; when it doesn't know, it says so. Hermetic, local, MCP.

⭐ 5Rust
leandrodaf/3d-new-era-ai

Open-source home design and floor plan editor in Rust (a Sweet Home 3D alternative) with a built-in MCP server: your AI agent draws walls, furnishes rooms, checks lighting and ergonomics, and renders

⭐ 4Rust

📬 Get the weekly radar in your inbox

The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.