agentrigs
+ submit rig
~ / rigs / isac322 / kwin-mcp

isac322/kwin-mcp

MCP server for Linux desktop GUI automation on KDE Plasma 6 Wayland -- 30 tools for virtual and live sessions

↗ GitHub ★ 62 MIT updated today 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
~5.2k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
1/5
No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ claude mcp add kwin-mcp -- uv run --directory . python -m kwin_mcp.server
$ npx degit isac322/kwin-mcp/.claude ./rig-kwin-mcp  # inspect, then merge into .claude/

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 kwin-mcp -- uv run --directory . python -m kwin_mcp.server
$ npx degit isac322/kwin-mcp/.claude/skills/check-docs-seo .claude/skills/check-docs-seo
$ npx degit isac322/kwin-mcp/.claude/skills/release-notes .claude/skills/release-notes
$ npx degit isac322/kwin-mcp/integrations/claude-code/skills/kwin-desktop-automation .claude/skills/kwin-desktop-automation
$ curl -fsSL --create-dirs -o .claude/agents/docs-seo.md https://raw.githubusercontent.com/isac322/kwin-mcp/main/.claude/agents/docs-seo.md

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
. · "kwin-mcp" pypi 2.5k

Skills (3)

check-docs-seorelease-noteskwin-desktop-automation

Subagents (1)

docs-seo—

Hooks (1)

eventmatcherruns
PostToolUseBashbash "${CLAUDE_PROJECT_DIR}/.claude/hooks/docs-seo-trigger.sh"

Similar rigs

RAIT-09/obsidian-agent-client
Bring AI agents into Obsidian via Agent Client Protocol (ACP), such as Claude Code, Codex and Gemini CLI.
★ 2,409 project Claude CodeCodexGemini CLI 1 skills 1 hooks 25d ago
Pragmatist 4.8k tok ·
maorcc/gimp-mcp
GIMP MCP server
★ 190 project Claude Code 1 mcp 4mo ago
Pragmatist 3.7k tok ·
lingua-realm/agent-config-ansible
基于Ansible一键同步claude code/codex/...等工具的配置
★ 3 setup Claude CodeCodexGemini CLI 3 skills 3mo ago
Pragmatist 2.9k tok ·
TRIDENT-KR/muster
Org-wide control plane for AI coding agent configuration — one source of truth for AGENTS.md, CLAUDE.md, skills, and MCP config
★ 0 project Claude CodeCodexCursor 2 mcp 1 skills 3mo ago
Pragmatist 19.9k tok ·
copied ✓