📡 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)

105 stars
11 forks
Rust
momentum ▲ 372.0
created 2026-08-01
on radar since 2026-08-03
star trend 27 → 105 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

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
systempromptio/systemprompt-demo

AI Governance Infrastructure — open gateway demo. Self-hosted systemprompt.io gateway in a single Rust binary: policy, audit trails, and cost attribution on every AI request, with the Systemprompt Bri

⭐ 3Rust
korovin-aa97/talkthrough-mcp

MCP server: turn narrated screen recordings into agent-ready data — local Whisper transcript, scene keyframes, OCR, wall-clock anchoring. Record your screen, talk — your AI agent files the bugs.

⭐ 12Python
anshupriyan/cli-bridge

MCP server for Claude Desktop and other Model Context Protocol clients — sandboxed filesystem access (read/write/edit/search) plus Dev Mode-gated shell command execution, scoped to a single workspace

⭐ 12TypeScript
12122J/mcpvet

MCP security scanner — vet a Model Context Protocol server before you add it to Claude Code, Cursor, or Windsurf. Grades it A–F, catching credential theft, tool-poisoning, and install-script payloads

⭐ 10JavaScript
hoangann2000/figma-mcp-console

MCP server that lets your AI assistant read and write Figma in real time — no API token, no rate limits. Works with Claude, Cursor, Copilot, Codex and any MCP client.

⭐ 9Go

📬 Get the weekly radar in your inbox

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