Zeuxis is a local MCP screenshot server that lets AI agents capture the current desktop, windows, cursor regions, and exact rectangles through MCP
Most browser automation work still happens through a UI a human drives. Zeuxis MCP server moves it into the conversation instead. Zeuxis is a local MCP screenshot server that lets AI agents capture the current desktop, windows, cursor regions, and exact rectangles through MCP tools.
Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.
The server publishes 14 tools. What each one is for:
list_monitors — nonelist_windows — focused_only?, include_system_windows?, app_contains?, title_contains?get_runtime_diagnostics — noneget_latest_capture — nonelist_session_artifacts — noneclear_session_artifacts — nonecapture_screen — monitor_id? plus shared capture parameterscapture_active_window — shared capture parameterscapture_cursor_window — include_system_windows? plus shared capture parameterscapture_window — snapshot_id, window_id plus shared capture parameterscapture_cursor_region — size plus shared capture parameterscapture_rect — x, y, width, height plus shared capture parametersConfiguration is passed through the environment: ZEUXIS_ARTIFACT_HMAC_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Plenty of browser automation servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Zeuxis's toolset — list_monitors, list_windows, get_runtime_diagnostics and 11 more — is a fair guide to whether it matches your workflow. It is maintained by bnomei; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| list_monitors | none |
| list_windows | focused_only?, include_system_windows?, app_contains?, title_contains? |
| get_runtime_diagnostics | none |
| get_latest_capture | none |
| list_session_artifacts | none |
| clear_session_artifacts | none |
| capture_screen | monitor_id? plus shared capture parameters |
| capture_active_window | shared capture parameters |
| capture_cursor_window | include_system_windows? plus shared capture parameters |
| capture_window | snapshot_id, window_id plus shared capture parameters |
| capture_cursor_region | size plus shared capture parameters |
| capture_rect | x, y, width, height plus shared capture parameters |
| capture_monitor_region | monitor_id, x, y, width, height plus shared capture parameters |
| delay_ms | integer |
{
"mcpServers": {
"zeuxis": {
"command": "zeuxis",
"args": []
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| ZEUXIS_ARTIFACT_HMAC_KEY | Credential the server authenticates with. | Yes |
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.