MCP SERVERDrive a compiled Electron app — clicks, real keystrokes, drags, dialogs and the main process — using numbered refs instead of guessed selectors.
LABSCO SUMMARY
The ordering is strict and the tools say so themselves — start_app before anything, snapshot before interacting — which is unusual candour for a driver and saves the first hour of confusion. The pairs that look redundant are the ones worth reading twice: type fills a value while keyboard_type dispatches real key events for editors that only listen to keydown, and set_input_files is named as the correct path for upload testing while drop_file states that it does not populate file.path, pushing apps that rely on webUtils.getPathForFile toward eval_main. press_sequence is an alias of keyboard_type kept for backwards compatibility, so new work has a single obvious choice.
A Playwright-backed driver for a compiled Electron app: launch it, read the screen as ref-numbered structure, act through trusted input events, and evaluate JavaScript in the renderer or the main process.
A compiled Electron app on disk, addressed by the absolute path to its main-process entry such as out/main/index.js, and a start_app call before any other tool will drive it. No credentials are configured.
One command — npx electron-driver
USE CASES
Start the app, take a snapshot that numbers what is on screen, and act on those refs instead of guessing at selectors that may not exist in a packaged build.
Send real keystrokes and key sequences rather than setting a field's value, which is the difference between exercising the app's handlers and bypassing them.
Wait on a selector or a condition, check whether something exists before acting on it, and read back the value that is actually in the field.
Handle a native dialog, evaluate in the main process rather than the renderer, read the console, and move between windows — the places a DOM-only driver stops.
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
accessibility_snapshotCapture the accessibility tree of the current page as JSON. Useful for testing screen-reader behaviour, finding elements by role, or auditing for missing ARIA labels. Optionally pass interestingOnly: false to include every node, not just interesting ones.
checkCheck a checkbox or radio button matching a selector. No-op if already checked.
cleanup_screenshotsDelete all screenshots from the current session directory. Useful between test phases to keep storage tidy.
clear_inputClear the value of an input or textarea matching a selector. Equivalent to selecting all and deleting.
clickClick an element. Pass selector (Playwright selector) or ref (from a snapshot). Pass force: true to skip actionability checks when an overlay is in the way.
console_logsReturn recent console messages captured since the app started. Includes renderer console (log/info/warn/error/debug) and main-process stdout/stderr. Pass clear: true to drain the buffer after reading.
dialog_handlerInstall an auto-responder for JavaScript dialogs (alert/confirm/prompt/beforeunload). Once set, the next dialog(s) will be auto-accepted or dismissed without a human. Pass action: "accept" or "dismiss", optional text for prompts, and once: true to auto-uninstall after the first dialog (default true).
dragDrag from one point to another using real Chromium input events (via Playwright's CDP mouse pipeline). Because these are trusted browser events, they automatically generate matching PointerEvents — so React onPointerDown, native pointerdown listeners, setPointerCapture, CSS :hover/:active, and every other pointer consumer all see the drag exactly as they would from a real user. Coordinates are CSS pixels. Pass detectSelector to have the driver measure that element before and after the drag and include the movement delta in the result — the only reliable way to catch drags that silently hit a min/max clamp. If the primary strategy does not move the detect target (and a detectSelector was given), the driver automatically falls back to invoking the React handler directly via fiber-prop access and then dispatching move/up events on both document and window. Disable the fallback with fiberFallback: false. The result includes a strategy field indicating which path worked (pointer-capture or react-fiber).
drop_fileSimulate dropping a file onto a target element by dispatching synthetic drag/drop events with a DataTransfer containing the file contents. Works for apps that read File via web APIs (FileReader, File.text, etc.). Does NOT populate file.path — apps that rely on webUtils.getPathForFile() or legacy file.path must use eval_main to invoke their IPC directly.
elements_listEnumerate elements matching a selector, returning basic info about each (tag, text snippet, id, key attributes, bounding box). Great for "what buttons are on this screen" or "give me all list items". Capped at 50 by default.
eval_mainEvaluate JavaScript in the Electron main process. Pass a FUNCTION BODY — use return to yield a value. The body receives electron (the full Electron module) and arg (your JSON-serializable payload). Supports async/await. Use this to invoke IPC handlers, read paths, or drive windows the renderer cannot reach.
eval_rendererEvaluate JavaScript in the renderer (page) context. Pass a FUNCTION BODY — use return to yield a value. Example: return document.title. Supports async/await. Same contract as eval_main. Pass an arbitrary JSON-serializable arg to be available as the arg variable inside the body.
existsFast check for whether any element matches, plus the count. Pass selector or ref. Does not wait.
focused_elementReturn information about the currently focused element: tag, id, classes, text snippet, and bounding box. Returns { focused: false } if nothing meaningful has focus (document.body).
get_attributeRead an attribute from the first matching element. Pass selector or ref.
get_bboxGet the bounding box of the first matching element in CSS pixels. Pass selector or ref. Useful before drag operations.
get_computed_styleRead computed CSS property values from the first element matching a selector. Returns { exists, styles } where styles is an object mapping each requested property to its computed value. Example properties: "background-color", "font-family", "display".
get_textRead the text content of the first matching element. Pass selector or ref. Does not wait.
get_valueRead the current value of a form input, textarea, or select. Pass selector or ref.
hoverHover the mouse over an element. Pass selector or ref. Pass force: true to skip actionability checks when an overlay intercepts.
infoGet current window title, URL, viewport size (populated from window.innerWidth/innerHeight), uptime, and devicePixelRatio.
keyboard_typeType a literal string as real keyboard events. Unlike type (which uses fill), this dispatches per-character keydown/keypress/keyup events — works with CodeMirror, contenteditables, editors, and anything that listens to keydown. Optionally focus a selector first.
pressPress a keyboard key or chord in the window. Examples: "Escape", "Enter", "Control+S", "Shift+Tab", "Control+Shift+P".
press_sequenceAlias for keyboard_type with no focus selector. Types a literal string into the currently focused element as keyboard events. Kept for backwards compatibility.
screenshotCapture a full-page PNG of the current window. Returns the absolute path. Pass name to control the filename (without extension).
scrollScroll an element (if selector is given) or the window (if not). Pass x/y for an absolute scroll position, or dx/dy for a delta from the current position. Use scroll_into_view instead if you just want to make an element visible.
scroll_into_viewScroll the first element matching a selector into view if needed. Safe to call even if the element is already visible.
select_optionSelect an option in a <select> dropdown. Pass value (the option's value attribute), label (its visible text), or index (zero-based). At least one must be provided.
set_input_filesSet files on an <input type="file"> without triggering the native file picker. This is the CORRECT way to test file upload UI in Electron — much more reliable than drop_file. Pass one or more absolute file paths.
snapshotReturn a structured text representation of the visible page with numbered refs. Each interactive or labelled element gets a [ref] number that can be passed to click, type, hover, get_text, and other tools instead of a selector — eliminating selector-guessing round-trips. Call this FIRST before interacting with a page to see what is on screen. The snapshot is an accessibility-tree-based representation similar to Playwright MCP's browser_snapshot.
start_appLaunch an Electron app via Playwright. Must be called before any other driving tool. Pass the absolute path to the compiled main process entry (e.g. out/main/index.js). Wipes the screenshots directory on each fresh start. Detects the single-instance-lock failure mode and gives a helpful hint.
stop_appClose the running Electron app cleanly. Safe to call even if no app is running.
switch_windowMake a different BrowserWindow the "current" one that subsequent tools drive. Pass index (from windows_list) or titleMatch (substring of window title). The driver will focus the target window and route all future click/type/eval calls to it.
typeFill a text input, REPLACING existing content. Pass selector or ref. Uses Playwright's fill. For keyboard-level typing (CodeMirror, contenteditables), use keyboard_type instead.
uncheckUncheck a checkbox matching a selector. No-op if already unchecked.
waitPause for N milliseconds. Prefer wait_for_selector or wait_for when possible.
wait_forPoll a JavaScript predicate in the renderer until it returns truthy, then return its value. The predicate is a function body; use return to yield a value. Example body: return document.querySelectorAll(".item").length >= 3.
wait_for_selectorWait until an element matching a selector appears (or reaches a given state: attached/detached/visible/hidden). Returns element count and the bounding box of the first match so you do not need a follow-up eval. Honours timeoutMs (default 5000).
windows_listList every BrowserWindow the app has open, with title, URL, id, and whether it is focused/minimized/maximized. For single-window apps this returns one entry.
BEFORE YOU INSTALL
39 tools when we connected. snapshot is undocumented (accessibility_snapshot is a separate tool), and press_sequence is an alias for keyboard_type.
Node 18+
CONTEXT COST
Rated by the size of the 39 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
npx electron-driver{
"mcpServers": {
"electron-driver": {
"command": "npx",
"args": [
"electron-driver"
]
}
}
}claude mcp add electron-driver --scope user -- npx electron-driverMCP servers
electron-stagewright
apireno
opentabs-dev