Summary
Gives Claude direct access to Windows desktop automation through native APIs instead of visual navigation. You get UI Automation tree inspection for precise element targeting, OCR with word coordinates, mouse and keyboard control, window management, and screenshot capture with configurable quality presets. Also bundles ripgrep for searching across allowed directories. Everything runs as a single binary with no dependencies. The precision approach makes sense when you're automating repetitive desktop workflows or building test scripts where clicking "somewhere near the button" isn't good enough. Windows only for now, with macOS and Linux planned.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →MCP Test Utils
100% AI Code · Human Reviewed
MCP server for automated desktop UI testing. A single binary — no runtime, no dependencies, no installation.
Windows x64 only. macOS and Linux support is planned.
Gives AI agents eyes and hands: screenshots, window management, mouse, keyboard, UI Automation, OCR, file search.
Why
AI agents can trigger actions in applications but can't see the screen. This server bridges that gap:
Agent triggers action → takes screenshot → sees the result →
switches window → clicks a button → verifies → writes report
Fully autonomous, no user involvement required.
Demo
10 tasks. One take. Watch on YouTube →
MCP Test Utils vs Anthropic Computer Use
Claude Cowork now includes built-in Computer Use — Claude takes screenshots and clicks through interfaces visually. It works with zero setup. MCP Test Utils takes a different approach: instead of guessing where to click from a screenshot, it reads the actual UI structure through Windows APIs.
| MCP Test Utils | Computer Use | |
|---|---|---|
| Click precision | Exact — UI Automation API | Visual estimate from screenshot |
| Speed & token cost | Fast, low cost — text responses | Slower, costly — image on every step |
| UI structure | Full tree: roles, states, coordinates | Not available |
| OCR | Word-level coordinates, multi-language | Not available (model vision only) |
| Window management | API-based, window-relative coords | Visual navigation |
| File search | Ripgrep engine built-in | Not available |
| Session logging | JSONL + screenshots | Not available |
| Visual analysis | ✅ Same Claude model, full-res 1:1 | ✅ Same Claude model |
| Setup | Download binary, add to config | Built-in, one toggle |
| Mobile / Dispatch | — | ✅ Tasks from phone |
| Cross-platform | Windows (macOS/Linux planned) | macOS + Windows |
MCP Test Utils is faster, more precise, and cheaper per action. Computer Use is easier to start and works across platforms. They complement each other.
Platforms
| Platform | Status |
|---|---|
| Windows x64 | ✅ Full support |
| macOS arm64 | ⏳ Planned |
| Linux x64 | ⏳ Planned |
Tools (19)
Vision
| Tool | Description |
|---|---|
take_screenshot | Screenshot of the entire desktop with configurable quality |
take_window_screenshot | Screenshot of a specific window (screen or window capture mode) |
read_screen_text | OCR the entire screen (Windows.Media.Ocr) |
read_region_text | OCR a screen region with precise word coordinates |
Window Management
| Tool | Description |
|---|---|
list_windows | List windows with id, title, app, position, size, minimized, focused |
focus_window | Bring a window to front, restore if minimized |
Input
| Tool | Description |
|---|---|
mouse_click | Click (left / right / middle) at screen or window-relative coordinates |
mouse_move | Move cursor to a point |
mouse_drag | Drag from point A to point B |
mouse_scroll | Scroll the mouse wheel |
keyboard_type | Type text (full Unicode — Latin, Cyrillic, CJK, emoji) |
keyboard_press | Press a key (Enter, Tab, F1–F12, arrows, etc.) |
keyboard_shortcut | Key combinations (Ctrl+S, Alt+F4, Ctrl+Shift+P, etc.) |
Structured UI Access
| Tool | Description |
|---|---|
list_ui_elements | UI Automation tree — buttons, fields, menus with exact coordinates |
File Search
| Tool | Description |
|---|---|
search_in_files | Search text or regex in files within allowed directories (like VS Code Find in Files) |
find_files | Find files and directories by name pattern (glob), like "Go to File" |
Agent Guide
| Tool | Description |
|---|---|
get_usage_guide | Compact workflow guide for LLM agents — precision clicking, coordinate metadata, quality tips |
Session Logging
| Tool | Description |
|---|---|
enable_logging | Start recording tool calls to JSONL + screenshots (opt-in) |
disable_logging | Stop recording, get session stats |
Installation
- Download the binary from Releases.
- Add it to your MCP client config. Example below is for Claude Desktop — for other clients, refer to their documentation.
Claude Desktop: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"test-utils": {
"command": "D:\\path\\to\\mcp-test-utils.exe"
}
}
}
- Restart Claude Desktop.
- In chat, try: "Take a screenshot" — the agent will return an image of your desktop.
With Logging and File Search (optional)
{
"mcpServers": {
"test-utils": {
"command": "D:\\path\\to\\mcp-test-utils.exe",
"env": {
"MCP_LOG_DIR": "D:\\path\\to\\logs",
"MCP_LOG_MAX_MB": "500",
"MCP_LOG_RETAIN_DAYS": "30",
"MCP_SEARCH_DIRS": "D:\\Projects\\app1;D:\\Projects\\app2"
}
}
}
}
Quality Presets
Screenshots support configurable quality to balance detail and token cost:
| Preset | Scale | Format | Use Case |
|---|---|---|---|
full | 100% | JPEG q90 | Maximum detail |
standard | 50% | JPEG q70 | Balanced (default) |
compact | 50% | PNG | When PNG is needed |
minimal | 25% | Grayscale | Lowest token cost |
custom | 10–100% | JPEG / PNG / Grayscale | Full control |
Environment Variables
| Variable | Description | Default |
|---|---|---|
MCP_LOG_DIR | Path for log sessions. Without it, logging tools are hidden | — |
MCP_LOG_MAX_MB | Session size limit (warning on exceed) | 500 |
MCP_LOG_RETAIN_DAYS | Auto-delete sessions older than N days. 0 to disable | 30 |
MCP_SEARCH_DIRS | Allowed directories for search_in_files (; on Windows, : on macOS/Linux). Without it, the tool is hidden | — |
How It Works
MCP Test Utils is a JSON-RPC 2.0 server communicating over stdin/stdout. Any MCP-compatible client launches the binary, sends tool calls, and receives structured responses (text, base64 images). Tested with Claude Desktop.
The server uses native Windows APIs directly — Win32 GDI for screenshots, SendInput for mouse and keyboard, UI Automation COM API for element inspection, WinRT Windows.Media.Ocr for text recognition. File search uses the ripgrep engine (grep-regex, grep-searcher, ignore) — cross-platform, no external dependencies. No PowerShell, no external tools, no network access.
Use Cases
- Automated QA — agent navigates the app, clicks through flows, takes screenshots at each step, writes a test report
- Desktop automation — fill forms, copy data between windows, run workflows
- Accessibility audit — scan UI Automation tree for missing labels or roles
- Visual regression — screenshot comparison across releases
- Data extraction — OCR text from applications that don't expose APIs
- Code search — find patterns across multiple projects without leaving the agent session
Security
- Responds only to requests from the MCP client
- Opens no network ports
- Writes nothing to disk (except opt-in logging)
- Sends no data externally
- Screenshots capture the entire screen — make sure no sensitive information is visible
- File search is sandboxed — only directories in
MCP_SEARCH_DIRSare accessible
Support us
Free and unrestricted. If you find it useful — jeenyjai.github.io
License
Copyright 2026 JeenyJAI. All rights reserved.
🚀 Created with Claude
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Configuration
MCP_LOG_DIRDirectory for logging sessions (opt-in). Without it, logging tools are hidden.
MCP_LOG_MAX_MBdefault: 500Session size limit in MB. Warning on exceed.
MCP_LOG_RETAIN_DAYSdefault: 30Auto-delete log sessions older than N days. 0 to disable.
MCP_SEARCH_DIRSAllowed directories for search_in_files (semicolon-separated). Without it, the tool is hidden.
Categories
Registryactive
Packagehttps://github.com/JeenyJAI/mcp-test-utils/releases/download/v3.10.1/mcp-test-utils.exe
TransportSTDIO
UpdatedApr 6, 2026
