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 skills add asattelmaier/gnome-ui-mcp --skill troubleshootinggit clone --depth 1 https://github.com/asattelmaier/gnome-ui-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/skills/asattelmaier/gnome-ui-mcp/troubleshooting)<a href="https://agentmods.dev/skills/asattelmaier/gnome-ui-mcp/troubleshooting"><img src="https://agentmods.dev/badge/skills/asattelmaier/gnome-ui-mcp/troubleshooting/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/asattelmaier/gnome-ui-mcp/troubleshooting"><img src="https://agentmods.dev/badge/skills/asattelmaier/gnome-ui-mcp/troubleshooting.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00047 | $0.00747 |
| Opus 5 | $0.00023 | $0.00374 |
| Sonnet 5 | $0.00009 | $0.00149 |
| Haiku 4.5 | $0.00005 | $0.00075 |
Grade D, and why
troubleshooting scanned grade D with 3 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 10d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt install wl-clipboard Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Locate and read the MCP configuration file. Search for `.mcp.json` in the workspace or `~/.claude/settings.local.json`. Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
Locate and read the MCP configuration file. Search for `.mcp.json` in the workspace or `~/.claude/settings.local.json`. How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Troubleshooting Wizard
You are acting as a troubleshooting wizard to help the user configure and fix their GNOME UI MCP server setup. When this skill is triggered, follow this diagnostic process:
Step 1: Find and Read Configuration
Locate and read the MCP configuration file. Search for .mcp.json in the workspace or ~/.claude/settings.local.json.
Check for:
- Incorrect command path or arguments
- Missing environment variables (DBUS_SESSION_BUS_ADDRESS, XDG_RUNTIME_DIR, WAYLAND_DISPLAY)
- Wrong transport setting
Step 2: Triage Common Errors
Error: AT-SPI desktop is not available
AT-SPI accessibility is not enabled or the daemon is not running.
- Enable accessibility:
gsettings set org.gnome.desktop.interface toolkit-accessibility true - Verify the AT-SPI daemon:
ps aux | grep at-spi - Restart the session if needed
Error: GDK display is not available
The server cannot connect to the display.
- Verify
DISPLAYandWAYLAND_DISPLAYare set - If running in Docker, ensure the Wayland socket is mounted
- Check
XDG_RUNTIME_DIRpoints to the correct directory
Error: D-Bus call failed or AccessDenied
The session bus is not reachable or permissions are restricted.
- Verify
DBUS_SESSION_BUS_ADDRESSis set correctly - If in a container, ensure the bus socket is mounted
- Some GNOME Shell introspection APIs require an unsandboxed session
Error: wl-paste not found or wl-copy not found
Clipboard tools need wl-clipboard installed.
sudo apt install wl-clipboard
Error: wayland-info not found
sudo apt install wayland-utils
Symptom: Tools return empty results
- The desktop may have no running applications
- AT-SPI may not expose elements for some apps (Electron, web views)
- Try
pingfirst to verify basic connectivity - Use
screenshotto see the actual desktop state
Step 3: Run Diagnostic Commands
# Verify the server starts
echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"0.1"}}}' | uv run gnome-ui-mcp
# Check AT-SPI
python3 -c "import gi; gi.require_version('Atspi', '2.0'); from gi.repository import Atspi; Atspi.init(); print(f'Desktop count: {Atspi.get_desktop_count()}')"
# Check environment
echo "DISPLAY=$DISPLAY"
echo "WAYLAND_DISPLAY=$WAYLAND_DISPLAY"
echo "XDG_SESSION_TYPE=$XDG_SESSION_TYPE"
echo "DBUS_SESSION_BUS_ADDRESS=$DBUS_SESSION_BUS_ADDRESS"
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.
- 10d ago First seen · 92 lines · 47 tokens per session scan D 08e6e136801d
troubleshooting is a skill published in the GitHub repository asattelmaier/gnome-ui-mcp (1 stars, last pushed 26d ago), licensed MIT. It adds 47 tokens to every session and 747 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, reads agent configuration directories, reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
computer-use
A set of rules for controlling Windows desktop applications through screen observation and simulated mouse and keyboard actions. It also describes how to find and launch installed applications and verify the results.
web-navigator
A browser-automation routing guide for web tasks. It directs navigation, page inspection, and actions such as clicking or filling forms to the appropriate browser tool.
computer-use
Linux/X11 desktop control — inspect, click, type into visible windows via AT-SPI + xdotool. Returns @eN refs from the focused window's accessibility tree.
manage-system
Manage ScreenHand system services — supervisor daemon, memory health, session diagnostics. Start/stop/pause supervisor, install as launchd service, check memory stats, query verified learnings, clear memory, snapshot state. Use when: "start supervisor", "stop supervisor", "pause automation", "resume automation"…
agent-desktop
Reliable computer use via native OS accessibility trees. Use when an AI agent needs to see and operate desktop applications (click buttons, fill forms, navigate menus, read UI state, toggle checkboxes, scroll, drag, type text, take screenshots, manage windows, use clipboard, manage notifications). Covers 59 command…
agent-desktop-ffi
C-ABI bindings over agent-desktop's PlatformAdapter. Consumers (Python ctypes, Swift, Node ffi-napi, Go cgo, C++, Ruby fiddle) link libagentdesktopffi.{dylib,so,dll} and call ad functions directly instead of spawning the CLI binary per call. The canonical observe-act workflow is: adinit → adadaptercreate[withsession]…