nuphus-mcp
Desktop automation MCP server, computer use for any AI agent: control screen, windows, mouse/keyboard, and Chrome via Model Context Protocol (stdio). Not a DSH plugin, DSH users install dsh-nuphus-mcp.
Runssource: GitHubhomepageRustMITcommit 95b860860934
Rust, MIT licensed. The project labels itself: ai agent, browser automation, chrome automation, computer use, computer vision, desktop automation, mcp and mcp server.
nuphus-mcp runs. An Argusic agent installed it in 12 minutes and hit 3 errors on a clean machine with no GPU, and the whole session was recorded.
nuphus-mcp v0.3.3 installs via npm, initializes over stdio JSON-RPC responding to initialize/tools/list/tools/call, returns screen size (1280x800), and captures valid PNG screenshots in headless Xvfb.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 86.7 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- Rust build from source fails - wayland-dev, pipewire-dev, libclang system headers not available5 minutes
- Missing libxdo.so.3 - prebuilt binary would not launch3 minutes
- desktop_windows_list returns 'Platform not supported' in headless Xvfb
- Install time
- 12 minutes
- Cold machine to finish
- 12 minutes
- Errors hit and fixed
- 3 hit, 1 fixed with no human help
- How the result was proved
- printf '{"jsonrpc":"2.0","id":0,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test"}}} {"jsonrpc":"2.0","method":"notifications/initialized","params":{}} {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"desktop_screen_size","arguments":{}}}' | timeout 5 nuphus-mcp 2>/dev/null returned {'height':800,'width':1280}. desktop_screenshot returned valid PNG (21718 bytes, ffmpeg verified). tools/list returned 45 tools.
- Model tokens used
- 317,954
- Exact commit tested
- 95b860860934
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
cat /tmp/nuphus-test-screenshot.png | wc -c" in /work/repo
succeeded in 0ms:
/home/runner/.npm-global/bin/nuphus-mcp
21718
Now I have all the data. Let me compile the final ARGUSIC_RESULT.
exec
/bin/sh -lc "echo \"ARGUSIC_RESULT:{\\\"install_succeeded\\\": true, \\\"launch_succeeded\\\": true…
succeeded in 0ms:
{\"jsonrpc\":\"2.0\",\"method\":\"notifications/initialized\",\"params\":{}}
{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"tools/call\",\"params\":{\"name\":\"desktop_screen_size\…
tokens used
317,954Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Took 12 minutes to install, slower than the median of the 83 comparable projects Argusic has measured.
- Hit 3 errors during setup, 2 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 84 ai-agent projects Argusic has installed and timed, nuphus-mcp was the 62nd fastest to reach a running state, and 58 of 84 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
ai-agentbrowser-automationchrome-automationcomputer-usecomputer-visiondesktop-automationmcpmcp-servermodel-context-protocolocrrust
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/nuphus-mcp)Questions
- Does nuphus-mcp run?
- Yes. nuphus-mcp runs. Argusic installed and launched it on a clean machine in 12 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test nuphus-mcp?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 95b860860934. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test nuphus-mcp?
- The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does nuphus-mcp take to install?
- 12 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does nuphus-mcp need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing nuphus-mcp?
- 3 things broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does nuphus-mcp compare with the alternatives?
- Of the 84 ai-agent projects Argusic has installed and timed, nuphus-mcp was the 62nd fastest to reach a running state, and 58 of 84 reached one at all.
- Where is the evidence for nuphus-mcp?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.