@hypothesi/tauri-mcp-server 0.12.0 → 0.13.1

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": "0.12.0",
+  "version": "0.13.1",
   "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]);
-})

package/dist/driver/scripts/keyboard.js

@@ -1,76 +0,0 @@
-/**
- * Keyboard interaction scripts
- */
-
-/**
- * Type text into an element
- * @param {Object} params
- * @param {string} params.selector - CSS selector for the element
- * @param {string} params.text - Text to type
- */
-function typeText(params) {
-   const { selector, text } = params;
-
-   const element = document.querySelector(selector);
-   if (!element) {
-      throw new Error(`Element not found: ${selector}`);
-   }
-
-   // Focus the element
-   element.focus();
-
-   // Set the value
-   element.value = text;
-
-   // Trigger input event for frameworks that listen to it
-   element.dispatchEvent(new Event('input', { bubbles: true }));
-   element.dispatchEvent(new Event('change', { bubbles: true }));
-
-   return `Typed "${text}" into ${selector}`;
-}
-
-/**
- * Send keyboard events (press, down, up)
- * @param {Object} params
- * @param {string} params.action - 'press', 'down', or 'up'
- * @param {string} params.key - Key to press
- * @param {string[]} params.modifiers - Modifier keys
- */
-function keyEvent(params) {
-   const { action, key, modifiers } = params;
-
-   const eventOptions = {
-      key: key,
-      code: key,
-      bubbles: true,
-      cancelable: true,
-      ctrlKey: modifiers.includes('Control'),
-      altKey: modifiers.includes('Alt'),
-      shiftKey: modifiers.includes('Shift'),
-      metaKey: modifiers.includes('Meta'),
-   };
-
-   const activeElement = document.activeElement || document.body;
-
-   if (action === 'press') {
-      activeElement.dispatchEvent(new KeyboardEvent('keydown', eventOptions));
-      activeElement.dispatchEvent(new KeyboardEvent('keypress', eventOptions));
-      activeElement.dispatchEvent(new KeyboardEvent('keyup', eventOptions));
-      return `Pressed key: ${key}${modifiers.length ? ' with ' + modifiers.join('+') : ''}`;
-   }
-
-   if (action === 'down') {
-      activeElement.dispatchEvent(new KeyboardEvent('keydown', eventOptions));
-      return `Key down: ${key}${modifiers.length ? ' with ' + modifiers.join('+') : ''}`;
-   }
-
-   if (action === 'up') {
-      activeElement.dispatchEvent(new KeyboardEvent('keyup', eventOptions));
-      return `Key up: ${key}${modifiers.length ? ' with ' + modifiers.join('+') : ''}`;
-   }
-
-   throw new Error(`Unknown action: ${action}`);
-}
-
-// Export for use
-({ typeText, keyEvent })