AI & Agents
Desktop Commander
Source: wonderwhy-er/DesktopCommanderMCP · ★ 6117 · TypeScript
Last updated 2026-06-06 · benchmark measured 2026-10-03 — deterministic & reproducible
Desktop Commander is a local AI agent that executes file, app, and workflow tasks on your computer.
Desktop Commander at a glance
Desktop Commander is a local AI agent that connects AI chat assistants such as ChatGPT, Claude, and Cursor to your own computer so they can read files, run commands, and carry out tasks directly on your machine, for builders, knowledge workers, data analysts, developers, and non-technical users.
Good for
- Organizing, finding, and sorting files in folders like Downloads or large local archives
- Writing, running, and fixing code on your own machine
- Troubleshooting computer problems, such as a program that won't start or a disk that has filled up
Pricing
Free: $0/mo, 10,000 tool calls/month. Pro: $20/mo, unlimited tool calls. Local MCP server is free & open source.
Questions people ask
What does Desktop Commander actually do?
It lets AI chat assistants like ChatGPT, Claude, and Cursor read your files, run commands on your computer, see the results, and continue from there, instead of just generating text.
Does my data get uploaded anywhere?
No, Desktop Commander processes files locally without uploads or cloud round-trips.
Which AI models and apps can I use it with?
It works with any major AI model, including Claude, GPT, Gemini, or local models, and connects to clients like ChatGPT, Claude Desktop/Web, Cursor, VS Code, and Windsurf.
Is there a free version?
Yes, the Free plan is $0/month with 10,000 tool calls per month, and the local MCP server itself is free and open source with no account or monthly limit.
Can I use it from my phone?
Yes, with Remote MCP you can connect from another device, such as your phone, to control your laptop, desktop, or server.
Written by Legit.Show from desktopcommander.app on 2026-10-05. It does not change the score.
Are you the maker of Desktop Commander? Claim this listing. It is free, takes a meta tag, a DNS record or GitHub admin rights, and never changes the score.
Launched something? Add your product, free.
To cite this score: legit.show/s/gh-wonderwhy-er-desktopcommandermcp/2026-10-03. That address never changes; this page moves with every re-measure.
Legit.Show scored Desktop Commander 71/100 on 2026-10-03, measured across all 7 frames from its public surface. legit.show/s/gh-wonderwhy-er-desktopcommandermcp/2026-10-03
Is Desktop Commander production-ready?
Legit.Show scores Desktop Commander 71 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Desktop Commander (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Reliability; its weakest is Privacy. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 66/100
- Accessibility — 90/100
- Security — 25/100How this compares across the catalogue: The Web Security Baseline
- Privacy — 25/100How this compares across the catalogue: The Privacy Gap
- Reliability — 100/100
- Standards — 89/100
- Discoverability — 100/100
What we measured
- No Content-Security-Policy and no HSTS.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 237 ms to first byte.
- Returns a proper 404 for unknown routes.
- 3 of 3 sampled routes reachable.
- No privacy policy found.
- Sets cookies / loads scripts with no consent prompt.
- Discoverable: structured data, sitemap, OpenGraph image, canonical URL.
Who built it
Eduard Ruzga (@wonderwhy_er) · product account @desktopcommandr
Who it's for
Builders · Knowledge workers · Data analysts · Developers · Non-technical users
Pricing
Free: $0/month with 200 messages/week; Pro: $7/month with unlimited messages
Sources and updates
- Description
- Taken from desktopcommander.app's own website on 2026-06-06.
- Operator
- Desktop Commander, as named in desktopcommander.app's terms, privacy page or footer.
- Code
- github.com/wonderwhy-er/DesktopCommanderMCP.
- Benchmark
- Measured by Legit.Show from the live site, the way any visitor sees it — with no access to its code or accounts. Same method for every product, and no AI decides the score. Last checked 2026-10-03.
Put together from public information, without Desktop Commander's involvement. If anything here is wrong, tell us and a person will check it.
Visit Desktop Commander → · Alternatives to Desktop Commander → · How this was measured →