Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add plugins/isac322/kwin-mcp/marketplace/plugin marketplace add isac322/kwin-mcpgit clone --depth 1 https://github.com/isac322/kwin-mcpGrade A, and why
kwin-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"$schema": "https://claude.ai/schemas/marketplace.json",
"name": "kwin-mcp",
"owner": {
"name": "Byeonghoon Yoo",
"email": "[email protected]",
"url": "https://github.com/isac322"
},
"metadata": {
"description": "kwin-mcp marketplace — MCP server and skill for Linux KDE Plasma 6 Wayland desktop GUI automation (virtual sessions for headless testing, live sessions for real-desktop / container / kiosk control).",
"version": "0.7.0"
},
"plugins": [
{
"name": "kwin-mcp",
"source": "./integrations/claude-code",
"version": "0.7.0",
"description": "Bundles the kwin-mcp MCP server (uvx kwin-mcp) plus the kwin-desktop-automation skill that teaches session-mode selection, the observe-act-verify loop, US-QWERTY vs Unicode typing, and platform pitfalls (surface-local coordinates, QMenu invisibility, EIS edge limits, clipboard opt-in).",
"category": "automation",
"keywords": [
"mcp",
"kwin",
"kde",
"plasma",
"wayland",
"gui-automation",
"desktop-automation",
"linux",
"linux-desktop",
"ai-agents",
"accessibility",
"at-spi2",
"libei",
"headless-testing",
"live-desktop"
],
"license": "MIT",
"homepage": "https://github.com/isac322/kwin-mcp",
"repository": "https://github.com/isac322/kwin-mcp",
"author": {
"name": "Byeonghoon Yoo",
"email": "[email protected]"
}
}
]
}
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 47 lines scan A a7b5f4b091b2
kwin-mcp is a plugin published in the GitHub repository isac322/kwin-mcp (41 stars, last pushed 29d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
axstream
Fast, verified computer use for coding agents: read the screen as text (200ms), execute batched verified actions, and compile any task done once into a macro that replays in seconds with zero model calls.
axstream
Fast, verified computer use for coding agents — screen-as-text perception, batched verified actions, self-compiling macros.
qa-explore
Agent-based exploratory E2E QA for any web app — explore, verify, learn, and codify a self-growing test suite.
qa-explore
A team of AI agents that test any web app like human QA: explore the live app, screenshot and visually judge rendering + data, capture trace/HAR/console/video evidence, adversarially verify findings, learn from rejected ones, codify them into a self-growing Playwright/Cypress suite — and close the loop by filing…
gnome-ui-plugins
Bundled plugins for GNOME desktop automation through MCP.
gnome-ui-mcp
GNOME Wayland desktop automation via AT-SPI discovery and Mutter input.