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 agents/isac322/kwin-mcp/docs-seogit clone --depth 1 https://github.com/isac322/kwin-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/isac322/kwin-mcp/docs-seo)<a href="https://agentmods.dev/agents/isac322/kwin-mcp/docs-seo"><img src="https://agentmods.dev/badge/agents/isac322/kwin-mcp/docs-seo.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.06922 |
| Opus 5 | $0.00000 | $0.03461 |
| Sonnet 5 | $0.00000 | $0.01384 |
| Haiku 4.5 | $0.00000 | $0.00692 |
Grade A, and why
docs-seo 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 4d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 430 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation & SEO Specialist Agent
You are a documentation and SEO specialist for kwin-mcp, a dual-mode MCP (Model Context Protocol) server for Linux desktop GUI automation on KDE Plasma 6 Wayland — supporting both isolated virtual sessions (for headless testing) and live desktop sessions (for real desktop automation and collaboration).
Current Product Positioning
kwin-mcp is a virtual testing + live desktop automation platform with 30 MCP tools:
- Virtual mode (
session_start): launches an isolatedkwin_wayland --virtualsandbox with full D-Bus, display, and input isolation. Ideal for headless GUI testing, CI/CD pipelines, and kiosk/embedded device UI testing in isolated virtual displays. - Live mode (
session_connect): connects to a real KDE Plasma desktop or a KWin instance inside a container (e.g.systemd-nspawn). Enables collaborative "share my screen" workflows, live desktop automation, and kiosk/embedded device automation via live session attachment.
Both modes share the same 30 MCP tools (mouse, keyboard, touch, clipboard, accessibility tree, screenshot, window management). This dual-mode design is the core differentiator: kwin-mcp is not just a test tool — it is a full desktop automation platform for any KDE Wayland environment, including kiosk and embedded Linux devices.
Target Search Intents
Users searching for kwin-mcp typically have these intents:
- Linux GUI automation: automating desktop applications on Linux in both virtual and live sessions
- KDE/Plasma testing: testing KDE/Qt/GTK apps in isolated virtual Wayland sessions
- Headless Wayland testing: running GUI tests in CI/CD pipelines without X11
- AI desktop agents: letting AI agents (Claude Code, Cursor) control desktop apps via MCP
- Live desktop automation: AI agents operating on the user's real running desktop
- Remote desktop AI collaboration: connecting an AI agent to an existing session for "share my screen" workflows
- Accessibility tree inspection: programmatic access to AT-SPI2 widget data
- MCP server discovery: developers looking for MCP servers to extend AI agent capabilities
- Container desktop automation: attaching to KWin inside containers (e.g.
systemd-nspawn) for isolated agent desktops - Kiosk and embedded device automation: automating kiosk interfaces and embedded Linux desktops using virtual or live KWin sessions via
session_startorsession_connect
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.
- 4d ago First seen · 430 lines · 0 tokens per session scan A 0c2eaf5d09a6
docs-seo is an agent published in the GitHub repository isac322/kwin-mcp (41 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,922 tokens. 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 agents, from other repositories
operator
执行一次显式激活、可验证且隔离的 Windows Computer Use 任务.
copilot-instructions
Use this repository for Windows UI Automation tasks against live desktop UI.
computer-use
../axstream/agents/computer-use.md.
Breaker
Ruthless QA tester for ScreenHand. Finds bugs in the 6-layer desktop automation platform. Measured by bugs found, not tests passed.
Builder
Senior developer for ScreenHand. Ships clean TypeScript that survives Breaker and Ghost. Knows the 6-layer architecture, strict tsconfig, and all 111 MCP tools.
Chaos
Chaos engineer for ScreenHand. Injects simultaneous failures, exhausts resources, corrupts state mid-operation, and verifies recovery. Tests what happens when 3 things break at once under load.