GNOME UI MCP
io.github.asattelmaier/gnome-ui-mcp ยท version 0.5.0
Community listing. Not installed or verified by cosmic-mcp. Read the source and its permissions before you run it.
GNOME Wayland desktop automation via AT-SPI discovery and Mutter input.
https://github.com/asattelmaier/gnome-ui-mcpQuick facts
- Listing: Community
- Published Jun 26, 08:34 UTC
- Transport: stdio
- Package: oci
ghcr.io/asattelmaier/gnome-ui-mcp:0.5.0 - Listed by cosmic-mcp: Nov 9, 04:25 UTC
Details
- Repository: https://github.com/asattelmaier/gnome-ui-mcp
Setup snippets
Generated from the registry entry. cosmic-mcp has not run or reviewed this server; values in angle brackets are yours to fill in.
Run it locally (oci)
docker run -i --rm 'ghcr.io/asattelmaier/gnome-ui-mcp:0.5.0'Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"gnome-ui-mcp": {
"args": [
"run",
"-i",
"--rm",
"ghcr.io/asattelmaier/gnome-ui-mcp:0.5.0"
],
"command": "docker"
}
}
}Claude Code
claude mcp add 'gnome-ui-mcp' -- docker run -i --rm 'ghcr.io/asattelmaier/gnome-ui-mcp:0.5.0'Cursor (.cursor/mcp.json)
{
"mcpServers": {
"gnome-ui-mcp": {
"args": [
"run",
"-i",
"--rm",
"ghcr.io/asattelmaier/gnome-ui-mcp:0.5.0"
],
"command": "docker"
}
}
}VS Code (.vscode/mcp.json)
{
"servers": {
"gnome-ui-mcp": {
"args": [
"run",
"-i",
"--rm",
"ghcr.io/asattelmaier/gnome-ui-mcp:0.5.0"
],
"command": "docker",
"type": "stdio"
}
}
}Related servers
- docs-mcp Verified domain
Remote MCP server for Tandem docs, install guides, SDKs, workflows, and agent setup help. - spotdb Verified domain
Ephemeral data sandbox for AI workflows with guardrails and security - EXTREMELY agency Verified domain
Your agency of AI agents in your AI app: what agents did, approvals, requests, jobs and reports. - A1 Lane Verified domain
Draft, schedule and publish social posts and videos; delivery receipts, read-back where available. - Auten Verified domain
Computer use for Claude Code, Codex, Cursor or any MCP client: your computer + Android phone (beta) - Auxen Verified domain
Hire AI workers that run on schedule, report back and act with your OK. Or deploy private models.