About io.github.Ask-812/oswright
io.github.Ask-812/oswright is an MCP server published by Ask-812 in the Blockchain category: windows desktop automation that re-reads only what changed: 7x fewer tokens per task.
The repository has 4 stars and 1 forks, with the last commit 7 days ago. Recent commit activity is the strongest signal that reported issues will get attention.
Install
uvx oswrightpip install oswrightThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (43)
atlas_stats- Report what the screen atlas has remembered and how often it helped.
Parameters not published.
click_element- Find text via the cascade and click it. The cheap alternative to `click_text`.
Parameters not published.
click_text- Find text via OCR and click on it. Auto-retries until found or timeout. Returns screenshot.
Parameters not published.
click_ui_element- Click a UI element using the accessibility tree. More reliable than OCR.
Parameters not published.
close_window- Close a window by title (sends WM_CLOSE). Returns screenshot.
Parameters not published.
double_click_text- Find text via OCR and double-click on it. Returns screenshot.
Parameters not published.
fill_field- Find a label, click it, clear, and type a value. Returns screenshot.
Parameters not published.
fill_form- Fill multiple fields in one call. Reduces round-trips.
Parameters not published.
fill_ui_element- Set the value of a UI element (e.g., text box). More reliable than OCR-based fill.
Parameters not published.
find_element- Find on-screen text using the cheapest method that can answer. Reports which cascade rung responded.
Parameters not published.
Show all 43 tools
find_image_on_screen- Find all occurrences of a template image on screen using OpenCV template matching.
Parameters not published.
find_text_on_screen- Find all occurrences of text on screen using OCR. Returns matches with coordinates and confidence.
Parameters not published.
focus_window- Bring a window to the foreground by title. Returns screenshot.
Parameters not published.
get_active_window- Get info about the currently focused window.
Parameters not published.
get_clipboard- Get the current text content of the system clipboard.
Parameters not published.
get_mouse_position- Get the current mouse cursor position.
Parameters not published.
get_ocr_info- Get info about the active OCR backend and available backends.
Parameters not published.
get_screen_info- Get screen dimensions and monitor count.
Parameters not published.
get_ui_tree- Get the accessibility tree of the focused window. Returns all interactive elements with names, types, positions. Deterministic and instant.
Parameters not published.
hover_text- Find text via OCR and hover over it. Returns screenshot.
Parameters not published.
launch_app- Launch an application and optionally wait for it to load. Runs the program directly, never through a shell.
Parameters not published.
list_windows- List all visible windows. Optionally filter by title substring.
Parameters not published.
minimize_window- Minimize a window by title. Returns screenshot.
Parameters not published.
mouse_click- Click the mouse at coordinates or current position. Returns screenshot.
Parameters not published.
mouse_double_click- Double-click at coordinates or current position. Returns screenshot.
Parameters not published.
mouse_drag- Drag from one point to another. Returns screenshot.
Parameters not published.
mouse_move- Move the mouse cursor to screen coordinates.
Parameters not published.
mouse_scroll- Scroll the mouse wheel. Returns screenshot.
Parameters not published.
observe- Report what changed on screen since the last observation. Rescans only the regions that moved. Prefer this over `screenshot` for tracking state.
Parameters not published.
perception_stats- Report how much perception work the model has avoided.
Parameters not published.
press_key- Press a key or combo like `Enter`, `Ctrl+C`, `Alt+Tab`. Returns screenshot.
Parameters not published.
read_model_text- Read on-screen text from the incremental model without re-OCRing the display.
Parameters not published.
read_screen_text- Read ALL visible text on the screen using OCR. Returns every detected text element with position.
Parameters not published.
remember_screen- Remember the current screen so future visits skip reading it. Persists across sessions.
Parameters not published.
right_click_text- Find text via OCR and right-click on it. Returns screenshot.
Parameters not published.
screenshot- Take a screenshot of the screen or a region. Returns the image as native MCP image content. Optionally saves to a file path.
Parameters not published.
screenshot_window- Capture a screenshot of just one window.
Parameters not published.
set_clipboard- Copy text to the system clipboard.
Parameters not published.
type_text- Type text character by character. Returns screenshot.
Parameters not published.
wait_for_change- Wait for the screen to visually change. Takes a baseline screenshot, polls until different.
Parameters not published.
wait_for_text- Wait for text to appear on screen. Polls via OCR.
Parameters not published.
wait_for_text_gone- Wait for text to disappear from screen.
Parameters not published.
wait_for_time- Wait for a specified duration (capped at 30s), then screenshot.
Parameters not published.
Ask AI
Ask AI about io.github.Ask-812/oswright
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.