DeskCheck
Supports Electron applications with renderer accessibility enabled, allowing UI inspection and interaction plus screenshots and performance measurements.
Uses GNOME/AT-SPI accessibility and fallback full-screen screenshot capture via gnome-screenshot; single-window screenshot support is not yet available.
Supports GTK 3/4 applications through the accessibility tree, enabling UI outlines, actions, screenshots, and performance measurements.
Provides single-window screenshots on KDE Plasma 6 using KWin and Spectacle.
Provides tools for launching, inspecting, interacting with, screenshotting, measuring, and stopping Linux desktop applications.
Collects NVIDIA GPU and VRAM metrics via nvidia-smi alongside CPU, memory, thread, and I/O measurements.
Can capture screenshots and measure performance of raw OpenGL/SDL windows, though these windows do not expose an accessibility UI tree.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
DeskCheck
Let your AI coding agent actually use the Linux desktop app it just wrote.
Claude Code, Cursor, Codex and friends can write a GTK, Qt or Electron app in minutes — and then declare it "done" without ever seeing it run. DeskCheck is an MCP server that gives the agent eyes, hands and a stopwatch for desktop software:
Tool | What the agent gets |
| Starts the app, waits for its window, captures stdout/stderr, reports startup time and early errors — or the crash output if it died. |
| A compact outline of the visible UI from the accessibility tree (buttons, fields, values, states) with short refs like |
| Click, type into fields, focus, or run any accessible action by ref. |
| A screenshot of that app's window (not whatever is in front), downscaled to save tokens. |
| CPU avg/max over the whole process tree, real memory (PSS) and growth, threads, disk I/O, NVIDIA GPU/VRAM — plus plain verdicts: busy loop, leak, continuous redraw. |
| Error-looking lines from the app's output, or the tail. |
| Inspect an app that is already running, by pid or exact name (no |
| Clean shutdown with exit code; list tracked apps. |
Why
The bottleneck of AI coding is no longer writing code, it is verifying it. For web apps
there are browser tools. For desktop apps agents were blind: they guessed from screenshots
of the wrong window, measured CPU by hand in /proc, and never noticed that the app they
wrote burns 14% of a core doing nothing. (That is a real finding from DeskCheck's first test.)
Example session
> app_launch {"command": "python3 main.py"}
app: main-1 pid: 31247
window ready after 0.8s
> app_ui {"find": "save"}
[e1] push button "Save" {disabled} (clickable)
> app_act {"ref": "e1"}
Error: ... (the agent now knows Save is disabled and why its test failed)
> app_measure {"seconds": 5}
CPU: avg 14.0% max 29.5% (100% = one core, 12 available)
memory (PSS): 141.7 MB change +480.0 KB
verdict: Uses 14.0% of one core on average: if the app should be idle, something is
polling, busy-looping or redrawing continuously.Requirements
Linux with Python ≥ 3.10, PyGObject and AT-SPI (
python-gobject+at-spi2-core; present on every GNOME/KDE desktop).Screenshots of a single window: KDE Plasma 6 (uses KWin + Spectacle). Other desktops fall back to full-screen capture with
grim,gnome-screenshotor ImageMagick.GPU metrics: NVIDIA (
nvidia-smi). Everything else works on any GPU.Toolkits: GTK 3/4, Qt 5/6, Electron (
--force-renderer-accessibility), anything screen-reader friendly. Games and raw OpenGL/SDL windows get screenshots and measurements, not a UI tree.
No pip dependencies.
Install
Claude Code:
claude mcp add deskcheck -s user -e PYTHONPATH=/path/to/deskcheck -- python3 -m deskcheckAny other MCP client: run python3 -m deskcheck (stdio transport) with PYTHONPATH pointing
to this folder.
Privacy
Everything runs locally. DeskCheck never sends data anywhere; screenshots and UI text go only to the agent you connected it to.
Contributing
Issues and pull requests are welcome, especially for:
single-window screenshots on GNOME and wlroots compositors,
AMD and Intel per-process GPU usage (DRM fdinfo),
toolkits whose accessibility tree needs extra flags.
License
MIT — free to use, modify and share. Built with the help of Claude Code.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
MCP server that lets your AI assistant build and deploy apps, hosting each one at a live URL.
MCP server for Mint — AI-powered QA that runs your app in a real browser on every PR.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA desktop automation MCP server that enables AI agents to interact with Linux environments through screenshots, window inspection, and input simulation. It provides tools for mouse control, keyboard input, and screen capture using xdotool and XDG Desktop Portals.MIT
- AlicenseBqualityDmaintenanceAn MCP server that provides AI agents with a full Ubuntu desktop environment inside Docker, enabling them to perform complex computer tasks like browsing, coding, testing, and GUI automation.3613MIT
- AlicenseAqualityCmaintenanceCross-platform desktop automation MCP server that lets AI agents capture screenshots, run OCR with UI-element classification, control mouse/keyboard, and launch programs on Linux, macOS, and Windows.202MIT
- AlicenseAqualityBmaintenanceAn MCP server that gives AI agents local Linux desktop control through tools for screenshots, accessibility, mouse, keyboard, and reliable text input.36MIT