DesktopCommanderMCP

This is MCP server for Claude that gives it terminal control, file system search and diff file editing capabilities

Runssource: GitHubhomepageTypeScriptMITcommit ea8e9a47440c

TypeScript, MIT licensed. The project labels itself: agent, ai, code analysis, code generation, gemini cli extension, mcp, terminal ai and terminal automation.

DesktopCommanderMCP runs. An Argusic agent installed it in 5 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

The @wonderwhy-er/desktop-commander MCP server v0.2.48 builds, installs, starts, responds to MCP protocol initialize, and passes its full test suite including real file operations, Excel, PDF, REPL, and process management tests.

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

At a glance

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.02 (measured)
recorded runs
2
last tested
stars
9,713
forks
1,219
open issues
267
watchers
109
size
71 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.

Install time
5 minutes
Cold machine to finish
9 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
Model tokens used
85,946
Exact commit tested
ea8e9a47440c
Container image
sha256:4c3d41857be3

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.

How the result was proved
runs before 2026-09-07 did not record the command used to check the result
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.

**Tests**: The full test suite (`node test/run-all-tests.js`) ran all 50+ test files covering real …
**Server**: The MCP server starts cleanly and responds correctly to MCP protocol `initialize` reque…
The only notable item is a non-blocking deprecation warning from `@supabase/supabase-js` about Node…
2026-09-03T17:26:42.000030Z ERROR codex_core::session: failed to record rollout items: thread 01a06…
tokens used
85,946
Everything is working. Let me compile the final result:
**Install**: `npm install` succeeded (1042 packages, some deprecation warnings but no failures). Bu…
**Tests**: The full test suite (`node test/run-all-tests.js`) ran all 50+ test files covering real …
**Server**: The MCP server starts cleanly and responds correctly to MCP protocol `initialize` reque…
The only notable item is a non-blocking deprecation warning from `@supabase/supabase-js` about Node…
2026-09-03T17:26:42.003689Z ERROR codex_core::session: failed to record rollout items: thread 01a06…

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

  • Reached a running state on a clean machine, with the session recorded.
  • Installed in 5 minutes, faster than the median of the 32 comparable projects Argusic has measured.
  • Nothing broke on the way: zero errors between clone and running.
  • Ran without a GPU, so it does not need one to start.
  • Licensed MIT, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

Of the 33 agent projects Argusic has installed and timed, DesktopCommanderMCP was the 13th fastest to reach a running state, and 25 of 33 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.
  • A quick evaluation: it was running 5 minutes after the clone.
  • Following its own README: the documented path worked with nothing to fix.

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 Runner2/3Runs100.000.02
Argusic Runner1/3Ran out of time0.000.20

Topics (from GitHub)

agentaicode-analysiscode-generationgemini-cli-extensionmcpterminal-aiterminal-automationvibe-coding

Embed the badge

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

[![Tested by Argusic](https://argusic.com/badge/DesktopCommanderMCP.svg)](https://argusic.com/subject/desktopcommandermcp)

Questions

Does DesktopCommanderMCP run?
Yes. DesktopCommanderMCP runs. Argusic installed and launched it on a clean machine in 5 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test DesktopCommanderMCP?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit ea8e9a47440c. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test DesktopCommanderMCP?
The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does DesktopCommanderMCP take to install?
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 DesktopCommanderMCP need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing DesktopCommanderMCP?
Nothing did, in the recorded run: zero errors between clone and running.
How does DesktopCommanderMCP compare with the alternatives?
Of the 33 agent projects Argusic has installed and timed, DesktopCommanderMCP was the 13th fastest to reach a running state, and 25 of 33 reached one at all.
Where is the evidence for DesktopCommanderMCP?
All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion