tauri-mcp
A generic MCP server that drives a builtTauri app's UI over WebDriver (tauri-driver + msedgedriver on Windows /WebKitWebDriver on Linux): launch the real app, then click, type, scroll, drag,read, and screenshot it like a human — or drop to raw JS when needed.
Not tied to any one project. Point it at any local Tauri app with projectDiror appPath. This server only knows how to drive a window; anythingapp-specific (reading an app's own database or config) belongs in a separateserver of your own.
Tools
All tools are prefixed app_ and operate on a single running session (one appat a time).
Session
| Tool | What it does |
|---|---|
app_launch |
Launch a built Tauri app under WebDriver. projectDir (or appPath) picks which app; TAURI_PROJECT_DIR is the fallback. Hard-errors if the window never renders (see Troubleshooting). |
app_close |
Close the session and stop tauri-driver. |
app_status |
Whether a session is running, and if so the binary + driver port. |
app_force_cleanup |
Kill orphaned tauri-driver/msedgedriver and reset state, when a crashed run left things half-up. |
app_window |
Resize / move / maximize / minimize / fullscreen the window; reports resulting size+position. |
app_reload |
Reload the webview (resets front-end state; backend process keeps its state). |
Acting (mouse / keyboard)
| Tool | What it does |
|---|---|
app_click |
Click by CSS selector or text (visible text / accessible name). button left/right/middle, count 2 for double-click. |
app_click_at |
Left/right/middle click at raw x,y viewport coordinates (canvas / native-drawn UI). |
app_scroll |
Mouse-wheel scroll by a pixel delta (+down/-up, +right/-left); optional selector to scroll a specific pane. |
app_type |
Type value into an input/textarea found by selector or text (placeholder/label); optional Enter. |
app_press_key |
Raw keyboard: any key — literal chars, F1-F12, arrows, Home/End/PageUp/Down, and modifier chords (Ctrl+A, Ctrl+Shift+K). |
app_hover |
Hover an element (by selector or text) to trigger tooltips / hover menus. |
app_select |
Pick an option from a native <select> by optionText/optionValue/optionIndex. |
app_drag |
Drag an element onto another (to) or by a pixel offset — sliders, range inputs, reordering, canvas handles. |
Reading / observing
| Tool | What it does |
|---|---|
app_snapshot |
Title + visible text + every visible interactive element (role, text, selector). The "what can I act on" view. |
app_read |
One element's live state: text, current input value (DOM property, reflects controlled React inputs), tag, displayed/enabled, optional attribute. |
app_wait_for |
Poll until a selector/text appears or disappears — for async loading, toasts, dialogs. |
app_console_logs |
Browser console output (log/warn/error + uncaught exceptions) since launch. |
app_screenshot |
PNG screenshot of the window, or of a single element (selector/text) for focused visual diffing. |
app_list_windows / app_switch_window |
List/switch windows, for apps with more than one WebviewWindow. |
Escape hatch
| Tool | What it does |
|---|---|
app_execute_js |
Run arbitrary JavaScript in the window and return the result. |
app_execute_js is unrestricted: it can read/write any DOM or JS state andinvoke any Tauri backend command directly viaawait window.__TAURI_INTERNALS__.invoke("cmd_name", { arg }) (always presentin Tauri v2, regardless of withGlobalTauri) — anything the app's own frontendcan do, including commands with real side effects (writing config, filesystem,launching processes). No sandboxing beyond what the app's own command handlersenforce. It's also the workaround for OS-native dialogs (see below).
Targeting elements: prefer text
app_snapshot emits positional CSS selectors likediv > div:nth-of-type(3) > button, which break the moment the DOM isrestructured. Wherever a tool takes a target, prefer text (visible text oraccessible name) — app_click({ text: "Browse" }) is how a human would say itand survives layout changes. exact: true requires an exact match; otherwiseit tries exact text, then substring, then ARIA accessible name (coversicon-only buttons with aria-label).
Requirements
- Node 24+ and
npm installonce in this folder. tauri-driver:cargo install tauri-driver --locked.- Windows: Microsoft Edge WebDriver version-matched to your installedWebView2 Runtime (Settings → About Microsoft Edge WebView2, or
HKLM\SOFTWARE\WOW6432Node\Microsoft\EdgeUpdate\Clients\{F3017226-FE2A-4295-8BDF-00C3A9A7E4C5}→pv). A mismatched major version connects fine but silently never leavesabout:blank—app_launchnow detects this and errors.winget install Microsoft.EdgeDriverdoes not reliably match; download the exact versionfromhttps://msedgedriver.microsoft.com/<version>/edgedriver_win64.zipanddrop it at./bin/msedgedriver.exe(checked first) or setEDGEDRIVER_PATH. - The target app must already be built, and not with plain
cargo build— adebug binary points atdevUrland only renders if a Vite dev server is up.Usecargo tauri build --debug --no-bundle(fast) orcargo tauri build --no-bundle(release).app_launchdoes not build for you.
When projectDir/appPath is omitted, app_launch uses the TAURI_PROJECT_DIRenvironment variable; if that is unset too, it returns a clear error. There isno built-in default project.
Run / verify
npm install
# point it at any built Tauri app:
TAURI_PROJECT_DIR=/path/to/tauri-project npm run verify-automation
# or:
TAURI_APP_PATH=/path/to/built/app npm run verify-automation
The verify script launches the app, snapshots it, clicks the first interactiveelement, screenshots, and closes.
Known limitation: OS-native dialogs
WebDriver can only see the webview DOM. Tauri file/folder pickers, messageboxes, and other OS-native dialogs are not part of the DOM and can't beclicked through — a flow that opens one will stall. Workaround: skip the dialogand drive the backend directly with app_execute_js, e.g.
// instead of clicking a "Choose folder" button that opens a native picker:
return await window.__TAURI_INTERNALS__.invoke("set_output_dir", { path: "/some/folder" });
Troubleshooting
app_launcherrors "window never rendered" — msedgedriver/WebView2version mismatch, or a plaincargo buildbinary. See Requirements.- "a session is already running" after a crash —
app_force_cleanup, thenrelaunch. - Selectors keep breaking — target by
textinstead (see above).
Register with Claude Code
Add it to an .mcp.json (project root, or ~/.claude.json for all projects),then restart Claude Code. Tools then appear as tauri:app_launch, etc.
{
"mcpServers": {
"tauri": {
"command": "node",
"args": ["--no-warnings", "/absolute/path/to/tauri-mcp/index.mjs"]
}
}
}
Or via the CLI:
claude mcp add tauri -- node --no-warnings /absolute/path/to/tauri-mcp/index.mjs