mouse-mcp

Hardware mouse MCP server for AI agents on Windows x64. USB HID control and voice dictation; requires compatible uMouse hardware and firmware. 面向 AI 智能体的硬件鼠标 MCP:USB HID 控制与语音听写,需要兼容的 uMouse 设备与固件。

Runs with mockssource: GitHubhomepageTypeScriptMITcommit 279feeb486c4

TypeScript, MIT licensed. The project labels itself: ai agents, computer use, desktop automation, hardware, hid, mcp, mcp server and model context protocol.

mouse-mcp runs, with stand-ins for the services it depends on. An Argusic agent installed it in 0.5 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

TypeScript build succeeds, all 257 unit tests pass (0 failures, 21 skipped), all 39 inject tests pass, MCP server starts and responds to protocol handshake with 22 tools and correct version 0.1.0; Windows native SDK DLL and hardware are not available on this Linux x64 platform

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 92 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.07 (measured)
recorded runs
1
last tested
stars
542
forks
2
open issues
0
watchers
0
size
9 MB
created
last push

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.

Time lost to each failure while testing mouse-mcp, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • T01 voice-typer test (voice-typer.test.mjs) failed on Linux: snapshotFocus() returns undefined on non-Windows platforms, but the test asserted entries[0].focus was truthy0.1 minutes
Install time
under a minute
Cold machine to finish
4 minutes
Errors hit and fixed
1 hit, 1 fixed with no human help
How the result was proved
npm test exited 0 with 257 tests passed, 0 failed, 21 skipped; node mcp/test/inject.test.mjs exited 0 with 39 passed; MCP server responded to initialize with correct serverInfo and tools/list returned 22 tools; npm run smoke: 11/17 passed, 6 skipped (no Windows SDK)
Model tokens used
128,919
Exact commit tested
279feeb486c4
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
Behaviour against real services
this run was verified against stand-in services only

Watch the session

The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.

A recording of attempt 1, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

MCP Server: responds to initialize, tools/list with 22 tools
exec
/bin/sh -lc 'cat /work/repo/mcp/test/voice-typer.test.mjs | grep -A1 "focus"' in /work/repo
 succeeded in 0ms:
      assert.ok(entries[0].focus, '焦点快照记录');
    } else {
      assert.equal(entries[0].focus, undefined, '非 Windows 平台无焦点快照');
    }
Now I need to check the time. Let me estimate the total runtime.
tokens used
128,919
Now I need to check the time. Let me estimate the total runtime.

Replay 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

  • Installed in 0.5 minutes, faster than the median of the 123 comparable projects Argusic has measured.
  • Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed MIT, as reported by its host.

What did not, or is not known

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 124 ai-agents projects Argusic has installed and timed, mouse-mcp was the 13th fastest to reach a running state, and 95 of 124 reached one at all.

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

tested byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs with mocks92.000.07

Topics (from GitHub)

ai-agentscomputer-usedesktop-automationhardwarehidmcpmcp-servermodel-context-protocolmouse-controlsonicloudspeech-to-texttypescriptumouseusb-hidvoice-inputwindows

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/mouse-mcp.svg)](https://argusic.com/subject/mouse-mcp)

Questions

Does mouse-mcp run?
mouse-mcp runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 1 minutes, hitting 1 error on the way, and recorded the session.
How did Argusic test mouse-mcp?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 279feeb486c4. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test mouse-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 mouse-mcp take to install?
0.5 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 mouse-mcp need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing mouse-mcp?
1 thing 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 mouse-mcp compare with the alternatives?
Of the 124 ai-agents projects Argusic has installed and timed, mouse-mcp was the 13th fastest to reach a running state, and 95 of 124 reached one at all.
Where is the evidence for mouse-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.

Discussion