@hypothesi/tauri-mcp-server 0.11.2 → 0.13.0

package/dist/driver/webview-interactions.js

@@ -1,7 +1,7 @@
 import { z } from 'zod';
 import { writeFile } from 'node:fs/promises';
 import { resolve } from 'node:path';
-import { executeInWebview, executeInWebviewWithContext, captureScreenshot, getConsoleLogs as getConsoleLogsFromCapture, } from './webview-executor.js';
+import { executeInWebview, executeInWebviewWithContext, executeAsyncInWebview, captureScreenshot, getConsoleLogs as getConsoleLogsFromCapture, } from './webview-executor.js';
 import { SCRIPTS, buildScript, buildTypeScript, buildKeyEventScript } from './scripts/index.js';
 // ============================================================================
 // Base Schema for Window Targeting
@@ -24,14 +24,21 @@ export const WindowTargetSchema = z.object({
 const selectorStrategyField = z.enum(['css', 'xpath', 'text']).default('css').describe('Selector strategy: "css" (default) for CSS selectors, "xpath" for XPath expressions, ' +
     '"text" to find elements by text content, with fallback to placeholder, aria-label, ' +
     'and title attributes. Ref IDs (e.g., "ref=e3") work with any strategy.');
+/**
+ * Optional nth parameter for disambiguating multiple matches.
+ * Required when a text selector matches more than one visible element.
+ */
+const nthField = z.number().int().min(0).optional().describe('Zero-based index to pick one of several matching elements. ' +
+    'Omit when the selector is unique. Required when a text selector matches more than one visible element.');
 // ============================================================================
 // Schemas
 // ============================================================================
 export const InteractSchema = WindowTargetSchema.extend({
-    action: z.enum(['click', 'double-click', 'long-press', 'scroll', 'swipe', 'focus'])
+    action: z.enum(['click', 'double-click', 'long-press', 'scroll', 'swipe', 'focus', 'hover', 'right-click'])
         .describe('Type of interaction to perform'),
     selector: z.string().optional().describe('Element selector: CSS selector (default), XPath expression, text content, or ref ID (e.g., "ref=e3")'),
     strategy: selectorStrategyField,
+    nth: nthField,
     x: z.number().optional().describe('X coordinate for direct coordinate interaction'),
     y: z.number().optional().describe('Y coordinate for direct coordinate interaction'),
     duration: z.number().optional()
@@ -49,6 +56,7 @@ export const ScreenshotSchema = WindowTargetSchema.extend({
     filePath: z.string().optional().describe('File path to save the screenshot to instead of returning as base64'),
     maxWidth: z.number().int().positive().optional().describe('Maximum width in pixels. Images wider than this will be scaled down proportionally. ' +
         'Can also be set via TAURI_MCP_SCREENSHOT_MAX_WIDTH environment variable.'),
+    allowScreenCapture: z.boolean().optional().default(false).describe('Allow an interactive OS screen-sharing permission prompt if native and html2canvas capture fail'),
 });
 export const KeyboardSchema = WindowTargetSchema.extend({
     action: z.enum(['type', 'press', 'down', 'up'])
@@ -56,6 +64,7 @@ export const KeyboardSchema = WindowTargetSchema.extend({
     selector: z.string().optional().describe('Element selector for element to type into (required for "type" action): ' +
         'CSS selector (default), XPath, text content, or ref ID'),
     strategy: selectorStrategyField,
+    nth: nthField,
     text: z.string().optional().describe('Text to type (required for "type" action)'),
     key: z.string().optional().describe('Key to press (required for "press/down/up" actions, e.g., "Enter", "a", "Escape")'),
     modifiers: z.array(z.enum(['Control', 'Alt', 'Shift', 'Meta'])).optional().describe('Modifier keys to hold'),
@@ -66,26 +75,30 @@ export const WaitForSchema = WindowTargetSchema.extend({
     strategy: selectorStrategyField.describe('Selector strategy (applies when type is "selector"): "css" (default), "xpath", or "text".'),
     timeout: z.number().optional().default(5000).describe('Timeout in milliseconds (default: 5000ms)'),
 });
-export const GetStylesSchema = WindowTargetSchema.extend({
-    selector: z.string().describe('Element selector: CSS selector (default), XPath expression, text content, or ref ID'),
-    strategy: selectorStrategyField,
-    properties: z.array(z.string()).optional().describe('Specific CSS properties to retrieve. If omitted, returns all computed styles'),
-    multiple: z.boolean().optional().default(false)
-        .describe('Whether to get styles for all matching elements (true) or just the first (false)'),
-});
 export const ExecuteJavaScriptSchema = WindowTargetSchema.extend({
     script: z.string().describe('JavaScript code to execute in the webview context. ' +
         'If returning a value, it must be JSON-serializable. ' +
         'For functions that return values, use IIFE syntax: "(() => { return value; })()" not "() => { return value; }"'),
     args: z.array(z.unknown()).optional().describe('Arguments to pass to the script'),
+    timeout: z.number().int().positive().optional().describe('Execution timeout in milliseconds'),
 });
 export const FocusElementSchema = WindowTargetSchema.extend({
     selector: z.string().describe('CSS selector for element to focus'),
+    strategy: selectorStrategyField,
+    nth: nthField,
 });
 export const FindElementSchema = WindowTargetSchema.extend({
     selector: z.string().describe('The selector to find: CSS selector (default), XPath expression, text content, or ref ID (e.g., "ref=e3"). ' +
         'Interpretation depends on strategy.'),
     strategy: selectorStrategyField,
+    nth: nthField,
+    limit: z.number().int().min(1).max(50).optional().default(5)
+        .describe('Maximum number of matches to return. Total match count is always reported.'),
+    properties: z.array(z.string()).optional().describe('Computed CSS properties to include for each match, e.g. ["display","opacity","font-size"].'),
+    visibleOnly: z.boolean().optional().default(true)
+        .describe('Return only rendered elements. Set false to include display:none and off-screen nodes.'),
+    includeHtml: z.boolean().optional().default(false)
+        .describe('Include outerHTML for each match, truncated to 2000 characters.'),
 });
 export const GetConsoleLogsSchema = WindowTargetSchema.extend({
     filter: z.string().optional().describe('Regex or keyword to filter logs'),
@@ -100,7 +113,7 @@ export const DomSnapshotSchema = WindowTargetSchema.extend({
 // Implementation Functions
 // ============================================================================
 export async function interact(options) {
-    const { action, selector, strategy, x, y, duration, scrollX, scrollY, fromX, fromY, toX, toY, windowId, appIdentifier } = options;
+    const { action, selector, strategy, nth, x, y, duration, scrollX, scrollY, fromX, fromY, toX, toY, windowId, appIdentifier } = options;
     // Handle swipe action separately since it has different logic
     if (action === 'swipe') {
         return performSwipe({ fromX, fromY, toX, toY, duration, windowId, appIdentifier });
@@ -110,12 +123,13 @@ export async function interact(options) {
         if (!selector) {
             throw new Error('Focus action requires a selector');
         }
-        return focusElement({ selector, strategy, windowId, appIdentifier });
+        return focusElement({ selector, strategy, nth, windowId, appIdentifier });
     }
     const script = buildScript(SCRIPTS.interact, {
         action,
         selector: selector ?? null,
         strategy: strategy ?? 'css',
+        nth: nth ?? null,
         x: x ?? null,
         y: y ?? null,
         duration: duration ?? 500,
@@ -145,9 +159,11 @@ async function performSwipe(options) {
     }
 }
 export async function screenshot(options = {}) {
-    const { quality, format = 'jpeg', windowId, filePath, appIdentifier, maxWidth } = options;
+    const { quality, format = 'jpeg', windowId, filePath, appIdentifier, maxWidth, allowScreenCapture } = options;
     // Use the native screenshot function from webview-executor
-    const result = await captureScreenshot({ format, quality, windowId, appIdentifier, maxWidth });
+    const result = await captureScreenshot({
+        format, quality, windowId, appIdentifier, maxWidth, allowScreenCapture,
+    });
     // If filePath is provided, write to file instead of returning base64
     if (filePath) {
         // Find the image content in the result
@@ -162,15 +178,15 @@ export async function screenshot(options = {}) {
     return result;
 }
 export async function keyboard(options) {
-    const { action, selectorOrKey, strategy, textOrModifiers, modifiers, windowId, appIdentifier } = options;
+    const { action, selectorOrKey, strategy, nth, textOrModifiers, modifiers, windowId, appIdentifier } = options;
     // Handle the different parameter combinations based on action
     if (action === 'type') {
         const selector = selectorOrKey;
         const text = textOrModifiers;
-        if (!selector || !text) {
+        if (!selector || text === undefined) {
             throw new Error('Type action requires both selector and text parameters');
         }
-        const script = buildTypeScript(selector, text, strategy);
+        const script = buildTypeScript(selector, text, strategy, nth);
         try {
             return await executeInWebview(script, windowId, appIdentifier);
         }
@@ -205,24 +221,8 @@ export async function waitFor(options) {
         throw new Error(`Wait failed: ${message}`);
     }
 }
-export async function getStyles(options) {
-    const { selector, strategy, properties, multiple = false, windowId, appIdentifier } = options;
-    const script = buildScript(SCRIPTS.getStyles, {
-        selector,
-        strategy: strategy ?? 'css',
-        properties: properties || [],
-        multiple,
-    });
-    try {
-        return await executeInWebview(script, windowId, appIdentifier);
-    }
-    catch (error) {
-        const message = error instanceof Error ? error.message : String(error);
-        throw new Error(`Get styles failed: ${message}`);
-    }
-}
 export async function executeJavaScript(options) {
-    const { script, args, windowId, appIdentifier } = options;
+    const { script, args, timeout, windowId, appIdentifier } = options;
     // If args are provided, we need to inject them into the script context
     const wrappedScript = args && args.length > 0
         ? `
@@ -233,7 +233,13 @@ export async function executeJavaScript(options) {
       `
         : script;
     try {
-        const { result, windowLabel, warning } = await executeInWebviewWithContext(wrappedScript, windowId, appIdentifier);
+        const execution = timeout === undefined
+            ? await executeInWebviewWithContext(wrappedScript, windowId, appIdentifier)
+            : {
+                result: await executeAsyncInWebview(buildTimedScript(wrappedScript), windowId, timeout, appIdentifier),
+                windowLabel: windowId ?? 'main',
+            };
+        const { result, windowLabel, warning } = execution;
         // Build response with window context
         let response = result;
         if (warning) {
@@ -248,9 +254,16 @@ export async function executeJavaScript(options) {
         throw new Error(`JavaScript execution failed: ${message}`);
     }
 }
+function buildTimedScript(script) {
+    const trimmed = script.trim();
+    if (/\breturn\b/.test(trimmed) && !trimmed.startsWith('(')) {
+        return `return (async () => { ${trimmed} })();`;
+    }
+    return `return (${trimmed});`;
+}
 export async function focusElement(options) {
-    const { selector, strategy, windowId, appIdentifier } = options;
-    const script = buildScript(SCRIPTS.focus, { selector, strategy: strategy ?? 'css' });
+    const { selector, strategy, nth, windowId, appIdentifier } = options;
+    const script = buildScript(SCRIPTS.focus, { selector, strategy: strategy ?? 'css', nth: nth ?? null });
     try {
         return await executeInWebview(script, windowId, appIdentifier);
     }
@@ -263,8 +276,17 @@ export async function focusElement(options) {
  * Find an element using various selector strategies.
  */
 export async function findElement(options) {
-    const { selector, strategy, windowId, appIdentifier } = options;
-    const script = buildScript(SCRIPTS.findElement, { selector, strategy });
+    const { selector, strategy, nth, limit, properties, visibleOnly, includeHtml, windowId, appIdentifier } = options;
+    await ensureAriaApiLoaded(windowId, appIdentifier);
+    const script = buildScript(SCRIPTS.findElement, {
+        selector,
+        strategy,
+        nth: nth ?? null,
+        limit: limit ?? 5,
+        properties: properties || [],
+        visibleOnly: visibleOnly ?? true,
+        includeHtml: includeHtml ?? false,
+    });
     try {
         return await executeInWebview(script, windowId, appIdentifier);
     }
@@ -277,9 +299,9 @@ export async function findElement(options) {
  * Get console logs from the webview.
  */
 export async function getConsoleLogs(options = {}) {
-    const { filter, since, windowId, appIdentifier } = options;
+    const { lines = 50, level, maxChars = 20000, maxCharsPerEntry = 2000, filter, since, windowId, appIdentifier } = options;
     try {
-        return await getConsoleLogsFromCapture(filter, since, windowId, appIdentifier);
+        return await getConsoleLogsFromCapture({ filter, since, lines, windowId, appIdentifier, level, maxChars, maxCharsPerEntry });
     }
     catch (error) {
         const message = error instanceof Error ? error.message : String(error);

package/dist/manager/mobile.js

@@ -1,9 +1,10 @@
 import { z } from 'zod';
 import { execa } from 'execa';
 export const ListDevicesSchema = z.object({});
+const DEVICE_LIST_TIMEOUT_MS = 5000;
 async function getAndroidDevices() {
     try {
-        const { stdout } = await execa('adb', ['devices', '-l']);
+        const { stdout } = await execa('adb', ['devices', '-l'], { timeout: DEVICE_LIST_TIMEOUT_MS });
         return stdout
             .split('\n')
             .slice(1)
@@ -20,7 +21,7 @@ async function getIOSSimulators() {
         return [];
     }
     try {
-        const { stdout } = await execa('xcrun', ['simctl', 'list', 'devices', 'booted']);
+        const { stdout } = await execa('xcrun', ['simctl', 'list', 'devices', 'booted'], { timeout: DEVICE_LIST_TIMEOUT_MS });
         return stdout
             .split('\n')
             .filter((line) => { return line.trim().length > 0 && !line.includes('== Devices =='); });

package/dist/monitor/logs.d.ts

@@ -2,28 +2,40 @@ import { z } from 'zod';
 export declare const ReadLogsSchema: z.ZodObject<{
     source: z.ZodEnum<["console", "android", "ios", "system"]>;
     lines: z.ZodDefault<z.ZodNumber>;
+    level: z.ZodOptional<z.ZodEnum<["log", "debug", "info", "warn", "error"]>>;
+    maxChars: z.ZodDefault<z.ZodOptional<z.ZodNumber>>;
+    maxCharsPerEntry: z.ZodDefault<z.ZodOptional<z.ZodNumber>>;
     filter: z.ZodOptional<z.ZodString>;
     since: z.ZodOptional<z.ZodString>;
     windowId: z.ZodOptional<z.ZodString>;
     appIdentifier: z.ZodOptional<z.ZodUnion<[z.ZodString, z.ZodNumber]>>;
 }, "strip", z.ZodTypeAny, {
     lines: number;
+    maxChars: number;
+    maxCharsPerEntry: number;
     source: "android" | "ios" | "console" | "system";
     filter?: string | undefined;
+    since?: string | undefined;
     windowId?: string | undefined;
     appIdentifier?: string | number | undefined;
-    since?: string | undefined;
+    level?: "error" | "log" | "debug" | "info" | "warn" | undefined;
 }, {
     source: "android" | "ios" | "console" | "system";
     filter?: string | undefined;
     lines?: number | undefined;
+    since?: string | undefined;
     windowId?: string | undefined;
     appIdentifier?: string | number | undefined;
-    since?: string | undefined;
+    level?: "error" | "log" | "debug" | "info" | "warn" | undefined;
+    maxChars?: number | undefined;
+    maxCharsPerEntry?: number | undefined;
 }>;
 export interface ReadLogsOptions {
     source: 'console' | 'android' | 'ios' | 'system';
     lines?: number;
+    level?: 'log' | 'debug' | 'info' | 'warn' | 'error';
+    maxChars?: number;
+    maxCharsPerEntry?: number;
     filter?: string;
     since?: string;
     windowId?: string;

package/dist/monitor/logs.js

@@ -47,19 +47,25 @@ function findAdbPath() {
 export const ReadLogsSchema = z.object({
     source: z.enum(['console', 'android', 'ios', 'system'])
         .describe('Log source: "console" for webview JS logs, "android" for logcat, "ios" for simulator, "system" for desktop'),
-    lines: z.number().default(50),
+    lines: z.number().int().positive().default(50),
+    level: z.enum(['log', 'debug', 'info', 'warn', 'error']).optional()
+        .describe('Only return entries at this console level.'),
+    maxChars: z.number().int().min(500).max(100000).optional().default(20000)
+        .describe('Maximum characters in the response. Entries are truncated and the oldest are dropped to fit.'),
+    maxCharsPerEntry: z.number().int().min(100).max(20000).optional().default(2000)
+        .describe('Maximum characters kept from each log entry.'),
     filter: z.string().optional().describe('Regex or keyword to filter logs'),
     since: z.string().optional().describe('ISO timestamp to filter logs since (e.g. 2023-10-27T10:00:00Z)'),
     windowId: z.string().optional().describe('Window label for console logs (defaults to "main")'),
     appIdentifier: z.union([z.string(), z.number()]).optional().describe('App port or bundle ID for console logs. Defaults to the only connected app or the default app if multiple are connected.'),
 });
 export async function readLogs(options) {
-    const { source, lines = 50, filter, since, windowId, appIdentifier } = options;
+    const { source, lines = 50, level, maxChars = 20000, maxCharsPerEntry = 2000, filter, since, windowId, appIdentifier } = options;
     try {
         let output = '';
         // Handle console logs (webview JS logs)
         if (source === 'console') {
-            return await getConsoleLogs({ filter, since, windowId, appIdentifier });
+            return await getConsoleLogs({ lines, level, maxChars, maxCharsPerEntry, filter, since, windowId, appIdentifier });
         }
         if (source === 'android') {
             const adbPath = findAdbPath();
@@ -134,16 +140,42 @@ export async function readLogs(options) {
                 return `Error reading system logs: ${e}`;
             }
         }
+        // Apply level filter
+        if (level) {
+            const levelPrefix = `[ ${level.toUpperCase()} ]`;
+            output = output.split('\n').filter((line) => { return line.includes(levelPrefix); }).join('\n');
+        }
+        // Apply regex filter
         if (filter) {
             try {
                 const regex = new RegExp(filter, 'i');
-                return output.split('\n').filter((line) => { return regex.test(line); }).join('\n');
+                output = output.split('\n').filter((line) => { return regex.test(line); }).join('\n');
             }
             catch (e) {
                 return `Invalid filter regex: ${e}`;
             }
         }
-        return output;
+        // Apply character budget
+        const outputLines = output.split('\n');
+        let budget = maxChars, dropped = 0;
+        const finalLines = [];
+        for (let i = outputLines.length - 1; i >= 0; i--) {
+            let line = outputLines[i];
+            if (line.length > maxCharsPerEntry) {
+                line = line.slice(0, maxCharsPerEntry) + '…[' + (line.length - maxCharsPerEntry) + ' more chars]';
+            }
+            if (line.length > budget) {
+                dropped = i + 1;
+                break;
+            }
+            budget -= line.length + 1; // +1 for newline
+            finalLines.unshift(line);
+        }
+        if (dropped > 0) {
+            finalLines.unshift('[ ' + dropped + ' older entries dropped to fit maxChars=' + maxChars +
+                '. Narrow with level, filter, or since. ]');
+        }
+        return finalLines.join('\n');
     }
     catch (error) {
         return `Error reading logs: ${error}`;

package/dist/tools-registry.js

@@ -7,7 +7,7 @@ import { listDevices, ListDevicesSchema } from './manager/mobile.js';
 import { manageDriverSession, ManageDriverSessionSchema, } from './driver/session-manager.js';
 import { readLogs, ReadLogsSchema } from './monitor/logs.js';
 import { executeIPCCommand, manageIPCMonitoring, getIPCEvents, emitTestEvent, getBackendState, manageWindow, ExecuteIPCCommandSchema, ManageIPCMonitoringSchema, GetIPCEventsSchema, EmitTestEventSchema, GetBackendStateSchema, ManageWindowSchema, } from './driver/plugin-commands.js';
-import { interact, screenshot, keyboard, waitFor, getStyles, executeJavaScript, findElement, domSnapshot, InteractSchema, ScreenshotSchema, KeyboardSchema, WaitForSchema, GetStylesSchema, ExecuteJavaScriptSchema, FindElementSchema, DomSnapshotSchema, } from './driver/webview-interactions.js';
+import { interact, screenshot, keyboard, waitFor, executeJavaScript, findElement, domSnapshot, InteractSchema, ScreenshotSchema, KeyboardSchema, WaitForSchema, ExecuteJavaScriptSchema, FindElementSchema, DomSnapshotSchema, } from './driver/webview-interactions.js';
 import { selectElement, getPointedElement, SelectElementSchema, GetPointedElementSchema, } from './driver/element-picker.js';
 import { SETUP_INSTRUCTIONS } from './constants.js';
 /**
@@ -99,10 +99,16 @@ export const TOOLS = [
     },
     {
         name: 'webview_find_element',
-        description: '[Tauri Apps Only] Find DOM elements in a running Tauri app\'s webview. ' +
+        description: '[Tauri Apps Only] Find elements in a running Tauri app\'s webview and return their geometry, text, ' +
+            'accessible name, attributes, visibility, and optionally their computed styles. ' +
             'Supports CSS selectors (default), XPath expressions, and text content matching via the strategy parameter. ' +
-            'The "text" strategy first searches element text content, then falls back to placeholder, aria-label, and title attributes. ' +
-            'Returns the element\'s HTML. ' +
+            'The "text" strategy searches element text content (not just direct text nodes), prefers exact matches over ' +
+            'substring matches, prefers innermost elements, and prefers interactive ancestors. ' +
+            'Returns structured JSON with totalMatches, returned count, and array of matches each containing: ' +
+            'nth index, ref ID, tag, trimmed text, accessible name, attributes, bounding rect, visibility, interactability, ' +
+            'optional computed styles, and optional truncated outerHTML. ' +
+            'Use this instead of webview_execute_js for querySelector, getBoundingClientRect, textContent, ' +
+            'and getComputedStyle reads. ' +
             'Requires active driver_session. ' +
             MULTI_APP_DESC + ' ' +
             'For browser pages or documentation sites, use Chrome DevTools MCP instead.',
@@ -118,6 +124,11 @@ export const TOOLS = [
             return await findElement({
                 selector: parsed.selector,
                 strategy: parsed.strategy,
+                nth: parsed.nth,
+                limit: parsed.limit,
+                properties: parsed.properties,
+                visibleOnly: parsed.visibleOnly,
+                includeHtml: parsed.includeHtml,
                 windowId: parsed.windowId,
                 appIdentifier: parsed.appIdentifier,
             });
@@ -144,9 +155,11 @@ export const TOOLS = [
     // WebView Interaction Tools
     {
         name: 'webview_interact',
-        description: '[Tauri Apps Only] Click, scroll, swipe, focus, or perform gestures in a Tauri app webview. ' +
-            'Supported actions: click, double-click, long-press, scroll, swipe, focus. ' +
+        description: '[Tauri Apps Only] Click, hover, right-click, scroll, swipe, focus, or perform gestures in a Tauri app webview. ' +
+            'Supported actions: click, double-click, long-press, scroll, swipe, focus, hover, right-click. ' +
             'Supports CSS selectors (default), XPath, and text content matching via the strategy parameter. ' +
+            'When using a text selector that matches multiple visible elements, you must provide the nth parameter ' +
+            'to disambiguate, or the tool will throw an error listing the candidates. ' +
             'Requires active driver_session. ' +
             'For browser interaction, use Chrome DevTools MCP instead.',
         category: TOOL_CATEGORIES.UI_AUTOMATION,
@@ -185,6 +198,7 @@ export const TOOLS = [
                 filePath: parsed.filePath,
                 appIdentifier: parsed.appIdentifier,
                 maxWidth: parsed.maxWidth,
+                allowScreenCapture: parsed.allowScreenCapture,
             });
             // If saved to file, return text confirmation
             if ('filePath' in result) {
@@ -217,6 +231,7 @@ export const TOOLS = [
                     action: parsed.action,
                     selectorOrKey: parsed.selector,
                     strategy: parsed.strategy,
+                    nth: parsed.nth,
                     textOrModifiers: parsed.text,
                     windowId: parsed.windowId,
                     appIdentifier: parsed.appIdentifier,
@@ -257,38 +272,14 @@ export const TOOLS = [
             });
         },
     },
-    {
-        name: 'webview_get_styles',
-        description: '[Tauri Apps Only] Get computed CSS styles from elements in a Tauri app. ' +
-            'Supports CSS selectors (default), XPath, and text content matching via the strategy parameter. ' +
-            'Requires active driver_session. ' +
-            MULTI_APP_DESC + ' ' +
-            'For browser style inspection, use Chrome DevTools MCP instead.',
-        category: TOOL_CATEGORIES.UI_AUTOMATION,
-        schema: GetStylesSchema,
-        annotations: {
-            title: 'Get Styles in Tauri Webview',
-            readOnlyHint: true,
-            openWorldHint: false,
-        },
-        handler: async (args) => {
-            const parsed = GetStylesSchema.parse(args);
-            return await getStyles({
-                selector: parsed.selector,
-                strategy: parsed.strategy,
-                properties: parsed.properties,
-                multiple: parsed.multiple,
-                windowId: parsed.windowId,
-                appIdentifier: parsed.appIdentifier,
-            });
-        },
-    },
     {
         name: 'webview_execute_js',
         description: '[Tauri Apps Only] Execute JavaScript in a Tauri app\'s webview context. ' +
             'Requires active driver_session. Has access to window.__TAURI__. ' +
             'If you need a return value, it must be JSON-serializable. ' +
             'For functions that return values, use an IIFE: "(() => { return 5; })()" not "() => { return 5; }". ' +
+            'Accepts an optional timeout parameter (milliseconds) for long-running scripts. ' +
+            'Timeout errors will identify which layer timed out (transport, script self-race, or Rust eval). ' +
             MULTI_APP_DESC + ' ' +
             'For browser JS execution, use Chrome DevTools MCP instead.',
         category: TOOL_CATEGORIES.UI_AUTOMATION,
@@ -304,6 +295,7 @@ export const TOOLS = [
             return await executeJavaScript({
                 script: parsed.script,
                 args: parsed.args,
+                timeout: parsed.timeout,
                 windowId: parsed.windowId,
                 appIdentifier: parsed.appIdentifier,
             });
@@ -396,6 +388,9 @@ export const TOOLS = [
         name: 'ipc_execute_command',
         description: '[Tauri Apps Only] Execute Tauri IPC commands (invoke Rust backend functions). ' +
             'Requires active driver_session. This is Tauri-specific IPC, not browser APIs. ' +
+            'Plugin commands (plugin:mcp-bridge|*) are routed through the bridge; all other commands ' +
+            'are executed via the webview using window.__TAURI_INTERNALS__.invoke, which keeps ' +
+            'the application\'s Tauri capability rules in force. ' +
             'For Electron IPC or browser APIs, use appropriate tools for those frameworks.',
         category: TOOL_CATEGORIES.IPC_PLUGIN,
         schema: ExecuteIPCCommandSchema,
@@ -410,6 +405,7 @@ export const TOOLS = [
             return await executeIPCCommand({
                 command: parsed.command,
                 args: parsed.args,
+                windowId: parsed.windowId,
                 appIdentifier: parsed.appIdentifier,
             });
         },
@@ -417,7 +413,8 @@ export const TOOLS = [
     {
         name: 'ipc_monitor',
         description: '[Tauri Apps Only] Monitor Tauri IPC calls between frontend and Rust backend. ' +
-            'Requires active driver_session. Captures invoke() calls and responses. ' +
+            'Requires active driver_session. Captures invoke() calls made through window.__TAURI__.core. ' +
+            'Bridge-internal commands (plugin:mcp-bridge|*) are excluded from capture. ' +
             'This is Tauri-specific; for browser network monitoring, use Chrome DevTools MCP.',
         category: TOOL_CATEGORIES.IPC_PLUGIN,
         schema: ManageIPCMonitoringSchema,
@@ -492,6 +489,11 @@ export const TOOLS = [
             '"list" - List all windows with labels, titles, URLs, and state. ' +
             '"info" - Get detailed info for a window (size, position, title, focus, visibility). ' +
             '"resize" - Resize a window (requires width/height, uses logical pixels by default). ' +
+            '"focus" - Focus a window (bring to front). ' +
+            '"minimize" - Minimize a window. ' +
+            '"maximize" - Maximize a window. ' +
+            'Desktop-only actions (focus, minimize, maximize) require tauri-plugin-mcp-bridge 0.13.0+ ' +
+            'and return a version error on older plugins. ' +
             'Requires active driver_session. ' +
             'For browser windows, use Chrome DevTools MCP instead.',
         category: TOOL_CATEGORIES.UI_AUTOMATION,

package/dist/version.d.ts

@@ -13,3 +13,8 @@ export declare const PLUGIN_VERSION_FULL: string;
  * This is the major.minor version used in Cargo.toml dependency specifications.
  */
 export declare const PLUGIN_VERSION_CARGO: string;
+/**
+ * Describe version skew between plugin and server.
+ * Returns null if versions match (major.minor), otherwise returns an upgrade message.
+ */
+export declare function describeVersionSkew(pluginVersion: string | null): string | null;

package/dist/version.js

@@ -15,3 +15,19 @@ export const PLUGIN_VERSION_FULL = pkg.version;
  * This is the major.minor version used in Cargo.toml dependency specifications.
  */
 export const PLUGIN_VERSION_CARGO = `${major}.${minor}`;
+/**
+ * Describe version skew between plugin and server.
+ * Returns null if versions match (major.minor), otherwise returns an upgrade message.
+ */
+export function describeVersionSkew(pluginVersion) {
+    if (!pluginVersion) {
+        return 'The connected app cannot report its plugin version. ' +
+            `Update tauri-plugin-mcp-bridge to ${PLUGIN_VERSION_CARGO} and rebuild the app.`;
+    }
+    const [pMajor, pMinor] = pluginVersion.split('.'), [sMajor, sMinor] = PLUGIN_VERSION_FULL.split('.');
+    if (pMajor === sMajor && pMinor === sMinor) {
+        return null;
+    }
+    return `Plugin ${pluginVersion} does not match server ${PLUGIN_VERSION_FULL}. ` +
+        `Set tauri-plugin-mcp-bridge = "${PLUGIN_VERSION_CARGO}" in Cargo.toml and rebuild the app.`;
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@hypothesi/tauri-mcp-server",
-  "version": "0.11.2",
+  "version": "0.13.0",
   "mcpName": "io.github.hypothesi/mcp-server-tauri",
   "description": "A Model Context Protocol server for use with Tauri v2 applications",
   "type": "module",

package/dist/driver/scripts/get-styles.js

@@ -1,47 +0,0 @@
-/**
- * Get computed CSS styles for elements
- *
- * @param {Object} params
- * @param {string} params.selector - CSS selector, XPath, text, or ref ID (e.g., "ref=e3") for element(s)
- * @param {string} params.strategy - Selector strategy: 'css', 'xpath', or 'text'
- * @param {string[]} params.properties - Specific CSS properties to retrieve
- * @param {boolean} params.multiple - Whether to get styles for all matching elements
- */
-(function(params) {
-   const { selector, strategy, properties, multiple } = params;
-
-   var elements;
-
-   if (multiple) {
-      elements = window.__MCP__.resolveAll(selector, strategy);
-   } else {
-      var el = window.__MCP__.resolveRef(selector, strategy);
-      elements = el ? [el] : [];
-   }
-
-   if (!elements[0]) {
-      throw new Error('Element not found: ' + selector);
-   }
-
-   const results = elements.map(function(element) {
-      const styles = window.getComputedStyle(element);
-
-      if (properties.length > 0) {
-         const result = {};
-         properties.forEach(function(prop) {
-            result[prop] = styles.getPropertyValue(prop);
-         });
-         return result;
-      }
-
-      // Return all styles
-      const allStyles = {};
-      for (let i = 0; i < styles.length; i++) {
-         const prop = styles[i];
-         allStyles[prop] = styles.getPropertyValue(prop);
-      }
-      return allStyles;
-   });
-
-   return JSON.stringify(multiple ? results : results[0]);
-})