MIT-licensed cross-platform desktop automation MCP server: 38 stdio tools mounted into DeepSeek Harness as native tools via the official dsh-nuphus-mcp plugin, with local OCR and BYOK vision.
DSH integration
Native runtime
Author-claimed
Safety audit
Unaudited
Last verified
2026-08-21
License
MIT
01What can it help you accomplish?
Give DeepSeek Harness computer-use MCP tools to control the desktop and Chrome
38 MCP tools (15 desktop + 23 browser) registered in DSH as `mcp__nuphus-mcp__*` — screenshots, window control, mouse/keyboard, Chrome CDP automation
Developers running DeepSeek Harness (dsh) who want their agent to operate the screen, windows and browser hands-free
Automate Chrome workflows from DSH sessions
Browser automation: navigate, snapshot (accessibility tree with `@N` refs), click, type, scroll, extract, screenshot, cookies get/set/import, tabs and downloads
Automation engineers who want an AI agent inside DeepSeek Harness to drive their own Chrome or an external fingerprint browser via CDP
Ground agent actions in what's on screen with vision and local OCR
`desktop_vision` (BYOK screenshot analysis via OpenAI-compatible or Anthropic native API) plus `desktop_perceive` (local PaddleOCR, optional YOLO icon detection) — semantic understanding plus pixel-precise coordinates
Teams building computer-use agents in DSH that need reliable element coordinates without sending screenshots to a hosted vision service
02How to install into DeepSeek Harness
Prerequisites
- Chrome or Edge installed — required for browser tools (the server auto-detects an installed browser)
- macOS only: Accessibility permission (System Settings → Privacy & Security → Accessibility) for desktop input
- Rust toolchain (stable) only if building from source with Cargo — not needed for the npm install path
Installation steps
- 01
Install via npm (recommended, all platforms, prebuilt binaries): `npm install -g @nuphus/nuphus-mcp` — puts the `nuphus-mcp` command on your PATH, no Rust toolchain needed
$ npm install -g @nuphus/nuphus-mcp
- 02
Recommended for DSH — install the official plugin: `npx -p @deepseek-ai/dsh dsh plugin --profile web add github:mrpulor-gh/dsh-nuphus-mcp`
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:mrpulor-gh/dsh-nuphus-mcp
- 03
Manual alternative — mount in DSH's `cordis.yml` as a stdio MCP server via `@deepseek-ai/dsh-mcp-client` (command: nuphus-mcp, args: ["--confirm-write"], toolCallTimeoutMs: 120000)
- 04
Recommended: enable strict confirmation with `--confirm-write` or `NUPHUS_MCP_CONFIRM_WRITE=1` so destructive tools require an explicit `"confirm": true` argument
Verify the integration
- Quick smoke test: `echo '{"jsonrpc":"2.0","id":0,"method":"initialize",...}' | nuphus-mcp` — the server reads newline-delimited JSON from stdin and writes JSON-RPC responses to stdout
03DSH integration and capability boundaries
Official dsh-nuphus-mcp plugin mounts nuphus-mcp into DeepSeek Harness as native tools with zero config (--confirm-write on by default); manual alternative via DSH's built-in stdio MCP client
38 MCP tools over stdio (15 desktop + 23 browser)
JSON-RPC 2.0 requests from any MCP client over stdin→screenshots, window control, mouse/keyboard, clipboard, Chrome CDP automation — one binary, no daemon, no network service
tools physically control screen, windows, mouse and keyboard on the host machineComputer vision pair (desktop_vision + desktop_perceive)
screenshot of the current screen→semantic analysis from your own vision LLM (BYOK) plus local PaddleOCR text elements with pixel coordinates; optional YOLO icon detection
desktop_vision sends screenshots to your own vision LLM endpoint (BYOK API key required)first perceive call downloads OCR/YOLO models into %APPDATA%\Nuphus\models (or NUPHUS_MODELS_DIR)Chrome automation via CDP (managed or external browser)
browser tool calls; optionally NUPHUS_MCP_BROWSER_CDP_URL to attach to an external/fingerprint browser→navigate, click, type, extract, screenshot, cookies, tabs, downloads — with self-healing port re-resolution for fingerprint browsers
launches and manages a Chrome instance by default; attaches to your external browser when NUPHUS_MCP_BROWSER_CDP_URL is set (never kills it on exit)Safety-first write controls
--confirm-write flag or NUPHUS_MCP_CONFIRM_WRITE=1→destructive tools require an explicit "confirm": true argument, otherwise the tool is rejected with isError; path validation for screenshots, uploads and file drags
04Who is it for? When not to use it?
Good for
- Developers running DeepSeek Harness (dsh) who want their agent to operate the screen, windows and browser hands-free
- Automation engineers who want an AI agent inside DeepSeek Harness to drive their own Chrome or an external fingerprint browser via CDP
- Teams building computer-use agents in DSH that need reliable element coordinates without sending screenshots to a hosted vision service
Not for
- Desktop control is full on Windows (Win32); on macOS desktop input requires Accessibility permission; on Linux window/input capabilities are partial.
- The server can physically control the machine it runs on; by default write tools run without confirmation, so enabling --confirm-write (or NUPHUS_MCP_CONFIRM_WRITE=1) is strongly recommended.
05Compatibility, maintenance and safety notes
- Desktop control is full on Windows (Win32); on macOS desktop input requires Accessibility permission; on Linux window/input capabilities are partial.
- The server can physically control the machine it runs on; by default write tools run without confirmation, so enabling --confirm-write (or NUPHUS_MCP_CONFIRM_WRITE=1) is strongly recommended.
- Desktop & browser automation need no API key, but desktop_vision requires a BYOK vision endpoint, and the first desktop_perceive call downloads OCR/YOLO models from the network.
MIT · actively maintained (latest release v0.1.12, 2026-08-17)
06Frequently asked questions
How do I connect nuphus-mcp to DeepSeek Harness?
Recommended: install the official dsh-nuphus-mcp plugin — `npx -p @deepseek-ai/dsh dsh plugin --profile web add github:mrpulor-gh/dsh-nuphus-mcp`. It mounts nuphus-mcp into DSH as native tools with zero config and --confirm-write on by default. Alternatively, mount it manually in DSH's cordis.yml via the built-in `@deepseek-ai/dsh-mcp-client` as a stdio MCP server.
Native tools or plain MCP — which mode does DSH use?
Both work. The official plugin mounts the 38 tools natively into DSH; the manual route plugs nuphus-mcp in as a plain stdio MCP server, registering tools as `mcp__nuphus-mcp__*`. Either way, run DSH in the desktop session of the machine you want controlled.
Do I need any API key?
Desktop and browser automation need none. Only `desktop_vision` requires your own vision model (BYOK, OpenAI-compatible or Anthropic native via NUPHUS_MCP_VISION_* env vars); `desktop_perceive` runs PaddleOCR locally and auto-downloads its models on first call.
What platforms are supported?
Browser tools are full on Windows and macOS and available on Linux. Desktop tools are full on Windows (Win32), require Accessibility permission on macOS, and are partial on Linux. Prebuilt binaries ship for Windows x64/arm64, macOS arm64 and Linux x64/arm64 via npm.
How do I keep write operations safe?
The server can physically control the machine it runs on. Enable strict confirmation with `--confirm-write` or `NUPHUS_MCP_CONFIRM_WRITE=1` so destructive tools require an explicit "confirm": true argument; the dsh plugin ships with --confirm-write on by default.
07Related DSH workflows
ruflo
by ruvnet
🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
reactive-resume
by amruthpillai
A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!
everos
by evermind-ai
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
yao
by yaoapp
✨ All your agents and workspaces in one place, on every device you own. Track tasks on a board, accessible from desktop, mobile, browser, or API. Self-hosted.
08Data and sources
It mounts nuphus-mcp into DSH as native tools with zero config — `--confirm-write` on by default, no code change needed:
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:mrpulor-gh/dsh-nuphus-mcp
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-08-21. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.