agentrigs
+ submit rig
~ / rigs / wonderwhy-er / DesktopCommanderMCP

wonderwhy-er/DesktopCommanderMCP

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

↗ GitHub ★ 9,950 mit updated 2d ago project Claude Code Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~7.1k tokens
Heavy · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ claude mcp add desktop-commander -- npx -y @wonderwhy-er/desktop-commander@latest
$ npx degit wonderwhy-er/DesktopCommanderMCP/skills ./rig-desktopcommandermcp/skills

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ claude mcp add desktop-commander -- npx -y @wonderwhy-er/desktop-commander@latest
$ npx degit wonderwhy-er/DesktopCommanderMCP/plugins/claude/skills/ai-tools-setup .claude/skills/ai-tools-setup
$ npx degit wonderwhy-<redacted>-health-check .claude/skills/computer-health-check
$ npx degit wonderwhy-<redacted>-commander-overview .claude/skills/desktop-commander-overview
$ npx degit wonderwhy-<redacted>-base .claude/skills/knowledge-base
$ npx degit wonderwhy-<redacted>-vault .claude/skills/obsidian-vault
$ npx degit wonderwhy-<redacted> .claude/skills/terminal

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

MCP servers (1)

serversourceest. tokens
Desktop Commander · "desktop-commander" npm 7.0k

Skills (6)

ai-tools-setupcomputer-health-checkdesktop-commander-overviewknowledge-baseobsidian-vaultterminal

Similar rigs

ravila4/claude-adhd-skills
Claude Code skills and hooks for staying organized with AI agents.
★ 157 collection Claude Code 4 skills 7mo ago
Minimalist 1.3k tok ·
nada-r/agent-template
Agent-ready TypeScript starter — Fastify + Zod, AGENTS.md rules, one-command verification gate, secret scanning, agent memory files
★ 0 project Claude CodeCodex 4 skills 3 agents 2 hooks 2mo ago
Pragmatist 2.5k tok ·
DojoCodingLabs/code-sensei
🥋 Claude Code plugin that teaches programming while you vibecode — contextual explanations, micro-quizzes, and belt progression. Free & open source by Dojo Coding.
★ 9 project Claude Code 10 skills 7mo ago
Skill Collector 102 tok ·
AI-Business-Tools/claude-code
Claude Code skills for business and education: Beamer slide generation, knowledge management, AI deliberation, document analysis, and writing voice.
★ 5 project Claude Code 14 skills 14d ago
Skill Collector 2.7k tok ·
copied ✓