MCP Observatory
4m ago Tracked 59,457 Last 4m ago 24h 2,463
npm JavaScript analyzed 0.2.51

wonderwhy-er/DesktopCommanderMCP

v0.2.51
npm

MCP server for terminal operations and file editing

maintainer
wonderwhy-er
licence
MIT
first seen
2026-06-01
last seen
2026-09-17
releases · 30d
6
short id
risk 25/100 · heuristic grade
B low inferred analyzer v33 (current)
  • vulnerabilities attested + 11
  • capability exposure inferred + 22
  • supply-chain attested + 6
  • trust mitigators mixed − 14

attested inferred mixed

The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.

grade last moved 1w ago · see ecosystem CVEs →

risk trajectory 7 movements
  • B · 31 → B · 25
  • B · 23 → B · 31
  • B · 31 → B · 23
  • C · 46 → B · 31
  • C · 59 → C · 46
  • C · 46 → C · 59
  • C · 35 → C · 46
capability exposure grade factor +22
Inferred surface — each links to servers holding it:
vulnerabilities 2 CVEs · grade factor +11
MEDIUM
DesktopCommanderMCP is vulnerable to Uncontrolled Resource Consumption EPSS 0% CVE-2026-10691 CVSS 4.3 affects [{"type":"SEMVER","events":[{"introduced":"0"},{"fixed":"0.2.39"}]}] fixed in 0.2.39 NVD GHSA GHSA GHSA
MEDIUM
DesktopCommanderMCP is vulnerable to SSRF EPSS 0% CVE-2026-10690 CVSS 6.3 affects [{"type":"SEMVER","events":[{"introduced":"0"},{"last_affected":"0.2.37"}]}] NVD GHSA GHSA GHSA
tool safety 2 findings · grade factor +0
  1. low dangerous code

    env-secret-flows-to-network-js: A process environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a ke

  2. low dangerous code

    env-secret-flows-to-network-js: A process environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a ke

skills & danger signals github-tarball
prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed v0.2.51 · analyzer v33 · 7h ago

skills & prompt files 18

other grade factors evidence elsewhere
embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:wonderwhy-er/DesktopCommanderMCP/badge.svg)](https://mcpobservatory.com/servers/github:wonderwhy-er/DesktopCommanderMCP/security)

Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of wonderwhy-er.