Oswright MCP server

Read from the package source without running it. The installed server may list more.

• atlas_stats

  Report what the screen atlas has remembered and how often it helped.

• click_element

  Find on-screen text via the resolution cascade and click it.

• click_text

  Find text on screen using OCR and click on it. Auto-retries until found or timeout. Returns action result and a screenshot of current screen state.

• click_ui_element

  Click a UI element using the accessibility tree (Windows only). More reliable than OCR — finds elements deterministically by their role and name.

• close_window

  Close a window by its title (substring match). Sends WM_CLOSE. This may discard unsaved work in the target application. Returns action result and a screenshot.

• double_click_text

  Find text on screen using OCR and double-click on it. Returns action result and a screenshot of current screen state.

• fill_field

  Find a text label on screen, click it, clear the field, and type a value. Useful for filling form fields by their label text. Returns action result and a screenshot of current screen state.

• fill_form

  Fill multiple form fields in one call. Each field is identified by its label text and filled with the given value. Reduces round-trips for forms. Returns action result and a screenshot of current screen state.

• fill_ui_element

  Set the value of a UI element (e.g., type text into a text box) using the accessibility tree (Windows only). More reliable than OCR-based fill.

• find_element

  Find on-screen text using the cheapest method that can answer.

• find_image_on_screen

  Find all occurrences of a template image on screen. Coordinates are absolute screen coordinates, ready to pass to mouse_click.

• find_text_on_screen

  Find all occurrences of text on screen using OCR. Returns a list of matches with coordinates and confidence. Coordinates are absolute screen coordinates, ready to pass straight to mouse_click.

• focus_window

  Bring a window to the foreground by its title (substring match). Returns the focused window info and a screenshot.

• get_active_window

  Get information about the currently active/focused window. Returns the window title, position, size, and process name.

• get_clipboard

  Get the current text content of the system clipboard. Returns the clipboard text or null if empty.

• get_mouse_position

  Get the current mouse cursor position.

• get_ocr_info

  Get information about the active OCR backend and available backends. Useful for debugging OCR issues.

• get_screen_info

  Get screen dimensions and monitor count.

• get_ui_tree

  Get the accessibility tree of the focused window (or a specific window). Returns all interactive UI elements with their names, types, and positions. This is deterministic and instant — much more reliable than OCR for apps with proper accessibility support (most modern Windows apps).

• hover_text

  Find text on screen using OCR and move the mouse over it (hover). Useful for triggering tooltips, hover menus, or inspecting elements. Returns action result and a screenshot of current screen state.

• launch_app

  Launch an application. Optionally wait for specific text to appear on screen (indicating the app has loaded). Returns a screenshot after launch.

• list_windows

  List all visible windows on the desktop. Optionally filter by title substring. Returns window titles, positions, sizes, and process names.

• minimize_window

  Minimize a window by its title (substring match). Returns action result and a screenshot.

• mouse_click

  Click the mouse at coordinates or current position. Returns action result and a screenshot of current screen state.

• mouse_double_click

  Double-click at coordinates or current position. Returns action result and a screenshot of current screen state.

• mouse_drag

  Drag from one point to another. Returns action result and a screenshot of current screen state.

• mouse_move

  Move the mouse cursor to screen coordinates.

• mouse_scroll

  Scroll the mouse wheel. Returns action result and a screenshot of current screen state.

• observe

  Report what changed on screen since the last observation.

• perception_stats

  Report how much perception work has been avoided. Covers incremental scanning, remembered screens, and predicted actions.

• press_key

  Press a key or key combination. Returns action result and a screenshot of current screen state.

• read_model_text

  Read on-screen text from the incremental model.

• read_screen_text

  Read ALL visible text on the screen using OCR. Returns every detected text element with its position, in absolute screen coordinates that are ready to click.

• remember_screen

  Remember the current screen so future visits skip reading it.

• right_click_text

  Find text on screen using OCR and right-click on it (context menu). Returns action result and a screenshot of current screen state.

• screenshot

  Take a screenshot of the screen or a region. Returns the image as native MCP image content. Optionally saves to a file path.

• screenshot_window

  Take a screenshot of a specific window (by title). Useful for capturing just one application without the rest of the desktop. Returns the image as native MCP image content.

• set_clipboard

  Set text to the system clipboard. Useful for pasting data into applications.

• type_text

  Type text using the keyboard (character by character). Returns action result and a screenshot of current screen state.

• wait_for_change

  Wait for the screen to visually change. Takes a baseline screenshot, then polls until the screen looks different (or timeout). Useful after triggering an action to wait for the UI to update.

• wait_for_text

  Wait for specific text to appear on screen. Polls via OCR until found or timeout.

• wait_for_text_gone

  Wait for text to disappear from screen. Polls via OCR until gone or timeout. Useful for waiting for loading spinners, progress dialogs, etc. to finish.

• wait_for_time

  Wait for a specified amount of time, then take a screenshot. Use sparingly — prefer wait_for_text or wait_for_text_gone instead. Capped at 30 seconds maximum.

• Code scan27 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 3 days ago15/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Oswright: common questions

Is Oswright MCP server safe?

Yes, by our scan: it is graded A (92/100). Read the Oswright safety report

How do I install Oswright?

It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.

Does Oswright need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Oswright maintained?

The last commit was 3 days ago (2026-09-17). The latest release is v0.8.2.

What can I use instead of Oswright?

Servers from other publishers that do the same job: MCP Server for Excel, devcoach MCP server and SimMirror MCP server. Compare all Oswright alternatives.