@darbotlabs/darbot-browser-mcp 0.1.0 → 0.2.0

package/README.md

@@ -4,7 +4,7 @@
 
 **🤖 Your Autonomous Browser Companion - Powered by AI**
 
-A Model Context Protocol (MCP) server that provides intelligent browser automation capabilities. This server enables AI models to interact with web pages through structured accessibility snapshots, delivering autonomous browsing without requiring vision models. Optimized for Microsoft Edge with comprehensive work profile support.
+A Model Context Protocol (MCP) server that provides intelligent autonomous browser capabilities. This server enables AI models to interact with web pages through structured accessibility snapshots, delivering autonomous browsing without requiring vision models. Optimized for Microsoft Edge with comprehensive work profile support.
 
 [![NPM Version](https://img.shields.io/npm/v/@darbotlabs/darbot-browser-mcp?style=flat-square&color=0098FF)](https://www.npmjs.com/package/@darbotlabs/darbot-browser-mcp)
 [![Downloads](https://img.shields.io/npm/dm/@darbotlabs/darbot-browser-mcp?style=flat-square&color=0098FF)](https://www.npmjs.com/package/@darbotlabs/darbot-browser-mcp)
@@ -17,7 +17,7 @@ A Model Context Protocol (MCP) server that provides intelligent browser automati
 - **🧠 AI-friendly** - No vision models needed, operates purely on structured data  
 - **🎯 Deterministic** - Avoids ambiguity common with screenshot-based approaches
 - **🔄 Work Profiles** - Save and restore complete browser sessions
-- **🛠️ 29 Autonomous Tools** - Comprehensive browser automation capabilities
+- **🛠️ 29 Autonomous Tools** - Comprehensive autonomous browser capabilities
 - **⚡ Multi-Platform** - Available as NPM package, VS Code extension, NuGet package, and browser extension
 
 ## 📋 Requirements
@@ -41,8 +41,16 @@ npx @darbotlabs/darbot-browser-mcp@latest
 ### 🔌 VS Code Extension
 Install the **"Darbot Browser MCP"** extension from the VS Code marketplace or search for `darbotlabs.darbot-browser-mcp`.
 
+The extension **automatically configures the MCP server** when installed - just enable MCP in VS Code settings and start the server!
+
 [**📥 Install VS Code Extension**](https://marketplace.visualstudio.com/items?itemName=darbotlabs.darbot-browser-mcp)
 
+**Quick Setup:**
+1. Install the extension from VS Code marketplace
+2. The extension will automatically prompt you to enable MCP and configure the server
+3. Use Command Palette: "Darbot Browser MCP: Start Server" 
+4. Start chatting with GitHub Copilot using browser automation tools!
+
 ### 📚 NuGet Package (.NET)
 ```bash
 # Install for .NET projects
@@ -62,56 +70,56 @@ Install the **Browser MCP Bridge** extension from the Chrome Web Store to share
 | ❌ Requires vision models | ✅ Pure structured data approach |
 | ❌ Complex setup and maintenance | ✅ Simple NPM install, ready in seconds |
 | ❌ Browser-specific code | ✅ Universal MCP protocol |
-| ❌ No session management | ✅ Advanced work profiles |
+| ❌ No session management | ✅ Advanced autonomous work profiles |
 
 ### 🛠️ Complete Autonomous Toolkit (29 Tools)
 
 <details>
-<summary><b>🔧 Core Automation</b></summary>
+<summary><b>🔧 Core Autonomous Operations</b></summary>
 
-- `browser_navigate` - Navigate to any URL
-- `browser_click` - Intelligent element clicking  
-- `browser_type` - Smart text input with submit options
-- `browser_snapshot` - AI-optimized accessibility snapshots
-- `browser_wait_for` - Intelligent waiting conditions
+- `browser_navigate` - Autonomously navigate to any URL
+- `browser_click` - Autonomous intelligent element clicking  
+- `browser_type` - Autonomous smart text input with submit options
+- `browser_snapshot` - AI-optimized autonomous accessibility snapshots
+- `browser_wait_for` - Autonomous intelligent waiting conditions
 
 </details>
 
 <details>
-<summary><b>📁 Work Profile Management</b></summary>
+<summary><b>📁 Autonomous Work Profile Management</b></summary>
 
-- `browser_save_profile` - Save complete browser sessions
-- `browser_switch_profile` - Instantly load saved profiles  
-- `browser_list_profiles` - Manage all your profiles
-- `browser_delete_profile` - Clean profile management
+- `browser_save_profile` - Autonomously save complete browser sessions
+- `browser_switch_profile` - Autonomously load saved profiles  
+- `browser_list_profiles` - Autonomously manage all your profiles
+- `browser_delete_profile` - Autonomous clean profile management
 
 </details>
 
 <details>
-<summary><b>🖼️ Media & Resources</b></summary>
+<summary><b>🖼️ Autonomous Media & Resources</b></summary>
 
-- `browser_take_screenshot` - High-quality screenshots
-- `browser_pdf_save` - Generate PDFs from pages
-- `browser_file_upload` - Handle file uploads seamlessly
+- `browser_take_screenshot` - Autonomous high-quality screenshots
+- `browser_pdf_save` - Autonomous PDF generation from pages
+- `browser_file_upload` - Autonomous file upload handling
 
 </details>
 
 <details>
-<summary><b>🗂️ Tab Management</b></summary>
+<summary><b>🗂️ Autonomous Tab Management</b></summary>
 
-- `browser_tab_new` - Open new tabs programmatically
-- `browser_tab_list` - Get all open tabs
-- `browser_tab_select` - Switch between tabs
-- `browser_tab_close` - Clean tab management
+- `browser_tab_new` - Autonomously open new tabs
+- `browser_tab_list` - Autonomously get all open tabs
+- `browser_tab_select` - Autonomously switch between tabs
+- `browser_tab_close` - Autonomous clean tab management
 
 </details>
 
 <details>
-<summary><b>🧪 Testing & Development</b></summary>
+<summary><b>🧪 Autonomous Testing & Development</b></summary>
 
-- `browser_generate_playwright_test` - Auto-generate test code
-- `browser_console_messages` - Debug with console access
-- `browser_network_requests` - Monitor network activity
+- `browser_generate_playwright_test` - Autonomously auto-generate test code
+- `browser_console_messages` - Autonomous debug with console access
+- `browser_network_requests` - Autonomous network activity monitoring
 
 </details>
 
@@ -124,7 +132,16 @@ node utils/generate-links.js
 
 ## 🚀 Getting Started
 
-First, install the Browser MCP server with your client. A typical configuration looks like this:
+The fastest way to get started is with the VS Code extension, which automatically configures everything for you. For other clients, you'll need to manually configure the MCP server.
+
+### **🔌 VS Code (Automatic Setup)**
+1. Install the [VS Code Extension](https://marketplace.visualstudio.com/items?itemName=darbotlabs.darbot-browser-mcp)
+2. Extension auto-configures MCP settings
+3. Start the server via Command Palette
+4. Use with GitHub Copilot Chat!
+
+### **⚙️ Manual Configuration (Other Clients)**
+For Claude Desktop, Cursor, Windsurf, etc., add this configuration:
 
 ```js
 {
@@ -141,13 +158,25 @@ First, install the Browser MCP server with your client. A typical configuration
 
 ### 📱 Quick Install Buttons
 
-[<img src="https://img.shields.io/badge/VS_Code-Install_Server-0098FF?style=for-the-badge&logo=visual-studio-code" alt="Install in VS Code">](https://insiders.vscode.dev/redirect?url=vscode%3Amcp%2Finstall%3F%257B%2522name%2522%253A%2522browser%2522%252C%2522command%2522%253A%2522npx%2522%252C%2522args%2522%253A%255B%2522%2540darbotlabs%252Fdarbot-browser-mcp%2540latest%2522%255D%257D) [<img src="https://img.shields.io/badge/VS_Code_Insiders-Install_Server-24bfa5?style=for-the-badge&logo=visual-studio-code" alt="Install in VS Code Insiders">](https://insiders.vscode.dev/redirect?url=vscode-insiders%3Amcp%2Finstall%3F%257B%2522name%2522%253A%2522browser%2522%252C%2522command%2522%253A%2522npx%2522%252C%2522args%2522%253A%255B%2522%2540darbotlabs%252Fdarbot-browser-mcp%2540latest%2522%255D%257D)
+**🔌 VS Code (Automatic):**
+[<img src="https://img.shields.io/badge/VS_Code-Auto_Install_Extension-0098FF?style=for-the-badge&logo=visual-studio-code" alt="Install VS Code Extension">](https://marketplace.visualstudio.com/items?itemName=darbotlabs.darbot-browser-mcp)
+
+**⚙️ Manual Configuration:**
+[<img src="https://img.shields.io/badge/VS_Code-Manual_Server_Config-0098FF?style=for-the-badge&logo=visual-studio-code" alt="Install in VS Code">](https://insiders.vscode.dev/redirect?url=vscode%3Amcp%2Finstall%3F%257B%2522name%2522%253A%2522browser%2522%252C%2522command%2522%253A%2522npx%2522%252C%2522args%2522%253A%255B%2522%2540darbotlabs%252Fdarbot-browser-mcp%2540latest%2522%255D%257D) [<img src="https://img.shields.io/badge/VS_Code_Insiders-Manual_Server_Config-24bfa5?style=for-the-badge&logo=visual-studio-code" alt="Install in VS Code Insiders">](https://insiders.vscode.dev/redirect?url=vscode-insiders%3Amcp%2Finstall%3F%257B%2522name%2522%253A%2522browser%2522%252C%2522command%2522%253A%2522npx%2522%252C%2522args%2522%253A%255B%2522%2540darbotlabs%252Fdarbot-browser-mcp%2540latest%2522%255D%257D)
+
+
+<details><summary><b>Install in VS Code (Automatic Setup)</b></summary>
 
+**🚀 Recommended: Use the VS Code Extension for automatic setup!**
 
-<details><summary><b>Install in VS Code</b></summary>
+The [Darbot Browser MCP Extension](https://marketplace.visualstudio.com/items?itemName=darbotlabs.darbot-browser-mcp) automatically handles all configuration:
 
-You can also install the Browser MCP server using the VS Code CLI:
+1. **Install from marketplace**: Search "Darbot Browser MCP" in VS Code extensions
+2. **Auto-configuration**: Extension prompts to enable MCP and configures the server
+3. **Start & Use**: Use Command Palette → "Darbot Browser MCP: Start Server"
+4. **Chat with Copilot**: Ask GitHub Copilot to "browse to example.com"
 
+**Manual CLI installation (if you prefer):**
 ```bash
 # For VS Code
 code --add-mcp '{"name":"browser","command":"npx","args":["@darbotlabs/darbot-browser-mcp@latest"]}'
@@ -553,6 +582,7 @@ X Y coordinate space, based on the provided screenshot.
   - Parameters:
     - `element` (string): Human-readable element description used to obtain permission to interact with the element
     - `ref` (string): Exact target element reference from the page snapshot
+    - `doubleClick` (boolean, optional): Whether to perform a double click instead of a single click
   - Read-only: **false**
 
 <!-- NOTE: This has been generated via update-readme.js -->

package/lib/config.js

@@ -28,8 +28,7 @@ const defaultConfig = {
             args: [
                 '--disable-popup-blocking',
                 '--allow-popups',
-                `--disable-extensions-except=${process.env.EXTENSION_PATH || '/default/path/to/extension'}`, // Use EXTENSION_PATH environment variable or fallback to default
-                `--load-extension=${process.env.EXTENSION_PATH || '/default/path/to/extension'}`, // Use EXTENSION_PATH environment variable or fallback to default
+                '--disable-extensions', // Disable all extensions to prevent manifest errors
             ],
         },
         contextOptions: {

package/lib/tools/common.js

@@ -19,8 +19,8 @@ const close = defineTool({
     capability: 'core',
     schema: {
         name: 'browser_close',
-        title: 'Close browser',
-        description: 'Close the page',
+        title: 'Autonomous browser closure',
+        description: 'Autonomously close the browser session and terminate all operations',
         inputSchema: z.object({}),
         type: 'readOnly',
     },
@@ -37,8 +37,8 @@ const resize = captureSnapshot => defineTool({
     capability: 'core',
     schema: {
         name: 'browser_resize',
-        title: 'Resize browser window',
-        description: 'Resize the browser window',
+        title: 'Autonomous window resizing',
+        description: 'Autonomously resize the browser window to specific dimensions for optimal viewing',
         inputSchema: z.object({
             width: z.number().describe('Width of the browser window'),
             height: z.number().describe('Height of the browser window'),

package/lib/tools/console.js

@@ -19,8 +19,8 @@ const console = defineTool({
     capability: 'core',
     schema: {
         name: 'browser_console_messages',
-        title: 'Get console messages',
-        description: 'Returns all console messages',
+        title: 'Autonomous console monitoring',
+        description: 'Autonomously retrieve all browser console messages for debugging and analysis',
         inputSchema: z.object({}),
         type: 'readOnly',
     },

package/lib/tools/dialogs.js

@@ -19,8 +19,8 @@ const handleDialog = captureSnapshot => defineTool({
     capability: 'core',
     schema: {
         name: 'browser_handle_dialog',
-        title: 'Handle a dialog',
-        description: 'Handle a dialog',
+        title: 'Autonomous dialog handling',
+        description: 'Autonomously handle browser dialog boxes (alerts, confirmations, prompts)',
         inputSchema: z.object({
             accept: z.boolean().describe('Whether to accept the dialog.'),
             promptText: z.string().optional().describe('The text of the prompt in case of a prompt dialog.'),

package/lib/tools/files.js

@@ -19,8 +19,8 @@ const uploadFile = captureSnapshot => defineTool({
     capability: 'files',
     schema: {
         name: 'browser_file_upload',
-        title: 'Upload files',
-        description: 'Upload one or multiple files',
+        title: 'Autonomous file upload',
+        description: 'Autonomously upload one or multiple files when a file chooser dialog appears',
         inputSchema: z.object({
             paths: z.array(z.string()).describe('The absolute paths to the files to upload. Can be a single file or multiple files.'),
         }),

package/lib/tools/install.js

@@ -22,8 +22,8 @@ const install = defineTool({
     capability: 'install',
     schema: {
         name: 'browser_install',
-        title: 'Install the browser specified in the config',
-        description: 'Install the browser specified in the config. Call this if you get an error about the browser not being installed.',
+        title: 'Autonomous browser installation',
+        description: 'Autonomously install the required browser engine specified in configuration. Use this to resolve browser installation errors.',
         inputSchema: z.object({}),
         type: 'destructive',
     },

package/lib/tools/keyboard.js

@@ -19,8 +19,8 @@ const pressKey = captureSnapshot => defineTool({
     capability: 'core',
     schema: {
         name: 'browser_press_key',
-        title: 'Press a key',
-        description: 'Press a key on the keyboard',
+        title: 'Autonomous keyboard input',
+        description: 'Autonomously press keys on the keyboard to interact with the web page',
         inputSchema: z.object({
             key: z.string().describe('Name of the key to press or a character to generate, such as `ArrowLeft` or `a`'),
         }),

package/lib/tools/navigate.js

@@ -20,7 +20,7 @@ const navigate = captureSnapshot => defineTool({
     schema: {
         name: 'browser_navigate',
         title: 'Navigate to a URL',
-        description: 'Navigate to a URL',
+        description: 'Autonomously navigate the browser to any URL. Use this command to launch and direct the browser to websites.',
         inputSchema: z.object({
             url: z.string().describe('The URL to navigate to'),
         }),
@@ -45,7 +45,7 @@ const goBack = captureSnapshot => defineTool({
     schema: {
         name: 'browser_navigate_back',
         title: 'Go back',
-        description: 'Go back to the previous page',
+        description: 'Autonomously navigate back to the previous page in browser history',
         inputSchema: z.object({}),
         type: 'readOnly',
     },
@@ -68,7 +68,7 @@ const goForward = captureSnapshot => defineTool({
     schema: {
         name: 'browser_navigate_forward',
         title: 'Go forward',
-        description: 'Go forward to the next page',
+        description: 'Autonomously navigate forward to the next page in browser history',
         inputSchema: z.object({}),
         type: 'readOnly',
     },

package/lib/tools/network.js

@@ -19,8 +19,8 @@ const requests = defineTool({
     capability: 'core',
     schema: {
         name: 'browser_network_requests',
-        title: 'List network requests',
-        description: 'Returns all network requests since loading the page',
+        title: 'Autonomous network monitoring',
+        description: 'Autonomously capture and analyze all network requests made since page load for debugging',
         inputSchema: z.object({}),
         type: 'readOnly',
     },

package/lib/tools/pdf.js

@@ -24,8 +24,8 @@ const pdf = defineTool({
     capability: 'pdf',
     schema: {
         name: 'browser_pdf_save',
-        title: 'Save as PDF',
-        description: 'Save page as PDF',
+        title: 'Autonomous PDF generation',
+        description: 'Autonomously save the current web page as a PDF document for archival or sharing',
         inputSchema: pdfSchema,
         type: 'readOnly',
     },

package/lib/tools/profiles.js

@@ -159,8 +159,8 @@ export const browserSaveProfile = defineTool({
     capability: 'core',
     schema: {
         name: 'browser_save_profile',
-        title: 'Save Work Profile',
-        description: 'Save the current browser state as a work profile',
+        title: 'Autonomous profile saving',
+        description: 'Autonomously save the current browser state as a reusable work profile for later restoration',
         inputSchema: saveProfileSchema,
         type: 'destructive',
     },
@@ -184,8 +184,8 @@ export const browserSwitchProfile = defineTool({
     capability: 'core',
     schema: {
         name: 'browser_switch_profile',
-        title: 'Switch Work Profile',
-        description: 'Switch to a saved work profile',
+        title: 'Autonomous profile switching',
+        description: 'Autonomously switch to a previously saved work profile, restoring browser state and session',
         inputSchema: switchProfileSchema,
         type: 'destructive',
     },
@@ -209,8 +209,8 @@ export const browserListProfiles = defineTool({
     capability: 'core',
     schema: {
         name: 'browser_list_profiles',
-        title: 'List Work Profiles',
-        description: 'List all saved work profiles',
+        title: 'Autonomous profile listing',
+        description: 'Autonomously list all saved work profiles with their details and creation information',
         inputSchema: listProfilesSchema,
         type: 'readOnly',
     },
@@ -248,8 +248,8 @@ export const browserDeleteProfile = defineTool({
     capability: 'core',
     schema: {
         name: 'browser_delete_profile',
-        title: 'Delete Work Profile',
-        description: 'Delete a saved work profile',
+        title: 'Autonomous profile deletion',
+        description: 'Autonomously delete a saved work profile permanently from storage',
         inputSchema: deleteProfileSchema,
         type: 'destructive',
     },

package/lib/tools/screenshot.js

@@ -33,8 +33,8 @@ const screenshot = defineTool({
     capability: 'core',
     schema: {
         name: 'browser_take_screenshot',
-        title: 'Take a screenshot',
-        description: `Take a screenshot of the current page. You can't perform actions based on the screenshot, use browser_snapshot for actions.`,
+        title: 'Autonomous screenshot capture',
+        description: `Autonomously take visual screenshots of the current page or specific elements. Use browser_snapshot for structured page data instead of visual screenshots.`,
         inputSchema: screenshotSchema,
         type: 'readOnly',
     },

package/lib/tools/snapshot.js

@@ -21,8 +21,8 @@ const snapshot = defineTool({
     capability: 'core',
     schema: {
         name: 'browser_snapshot',
-        title: 'Page snapshot',
-        description: 'Capture accessibility snapshot of the current page, this is better than screenshot',
+        title: 'Autonomous page snapshot',
+        description: 'Autonomously capture a detailed accessibility snapshot of the current page for analysis. This provides structured page content better than a screenshot.',
         inputSchema: z.object({}),
         type: 'readOnly',
     },
@@ -46,8 +46,8 @@ const click = defineTool({
     capability: 'core',
     schema: {
         name: 'browser_click',
-        title: 'Click',
-        description: 'Perform click on a web page',
+        title: 'Autonomous click',
+        description: 'Autonomously perform click interactions on web page elements',
         inputSchema: clickSchema,
         type: 'destructive',
     },
@@ -75,8 +75,8 @@ const drag = defineTool({
     capability: 'core',
     schema: {
         name: 'browser_drag',
-        title: 'Drag mouse',
-        description: 'Perform drag and drop between two elements',
+        title: 'Autonomous drag & drop',
+        description: 'Autonomously perform drag and drop operations between web page elements',
         inputSchema: z.object({
             startElement: z.string().describe('Human-readable source element description used to obtain the permission to interact with the element'),
             startRef: z.string().describe('Exact source element reference from the page snapshot'),
@@ -105,8 +105,8 @@ const hover = defineTool({
     capability: 'core',
     schema: {
         name: 'browser_hover',
-        title: 'Hover mouse',
-        description: 'Hover over element on page',
+        title: 'Autonomous hover',
+        description: 'Autonomously hover over specific elements on the web page',
         inputSchema: elementSchema,
         type: 'readOnly',
     },
@@ -134,8 +134,8 @@ const type = defineTool({
     capability: 'core',
     schema: {
         name: 'browser_type',
-        title: 'Type text',
-        description: 'Type text into editable element',
+        title: 'Autonomous text input',
+        description: 'Autonomously type text into editable elements on the web page',
         inputSchema: typeSchema,
         type: 'destructive',
     },
@@ -174,8 +174,8 @@ const selectOption = defineTool({
     capability: 'core',
     schema: {
         name: 'browser_select_option',
-        title: 'Select option',
-        description: 'Select an option in a dropdown',
+        title: 'Autonomous dropdown selection',
+        description: 'Autonomously select options in dropdown menus on the web page',
         inputSchema: selectOptionSchema,
         type: 'destructive',
     },

package/lib/tools/tabs.js

@@ -19,8 +19,8 @@ const listTabs = defineTool({
     capability: 'tabs',
     schema: {
         name: 'browser_tab_list',
-        title: 'List tabs',
-        description: 'List browser tabs',
+        title: 'Autonomous tab listing',
+        description: 'Autonomously list all open browser tabs and their current status',
         inputSchema: z.object({}),
         type: 'readOnly',
     },
@@ -43,8 +43,8 @@ const selectTab = captureSnapshot => defineTool({
     capability: 'tabs',
     schema: {
         name: 'browser_tab_select',
-        title: 'Select a tab',
-        description: 'Select a tab by index',
+        title: 'Autonomous tab selection',
+        description: 'Autonomously select and switch to a specific browser tab by index',
         inputSchema: z.object({
             index: z.number().describe('The index of the tab to select'),
         }),
@@ -66,8 +66,8 @@ const newTab = captureSnapshot => defineTool({
     capability: 'tabs',
     schema: {
         name: 'browser_tab_new',
-        title: 'Open a new tab',
-        description: 'Open a new tab',
+        title: 'Autonomous new tab creation',
+        description: 'Autonomously open a new browser tab, optionally navigating to a specified URL',
         inputSchema: z.object({
             url: z.string().optional().describe('The URL to navigate to in the new tab. If not provided, the new tab will be blank.'),
         }),
@@ -91,8 +91,8 @@ const closeTab = captureSnapshot => defineTool({
     capability: 'tabs',
     schema: {
         name: 'browser_tab_close',
-        title: 'Close a tab',
-        description: 'Close a tab',
+        title: 'Autonomous tab closure',
+        description: 'Autonomously close a browser tab by index, or close the current tab if no index specified',
         inputSchema: z.object({
             index: z.number().optional().describe('The index of the tab to close. Closes current tab if not provided.'),
         }),

package/lib/tools/testing.js

@@ -24,8 +24,8 @@ const generateTest = defineTool({
     capability: 'testing',
     schema: {
         name: 'browser_generate_playwright_test',
-        title: 'Generate a Playwright test',
-        description: 'Generate a Playwright test for given scenario',
+        title: 'Autonomous test generation',
+        description: 'Autonomously generate Playwright test code for browser automation scenarios and user workflows',
         inputSchema: generateTestSchema,
         type: 'readOnly',
     },

package/lib/tools/wait.js

@@ -19,8 +19,8 @@ const wait = captureSnapshot => defineTool({
     capability: 'wait',
     schema: {
         name: 'browser_wait_for',
-        title: 'Wait for',
-        description: 'Wait for text to appear or disappear or a specified time to pass',
+        title: 'Autonomous wait conditions',
+        description: 'Autonomously wait for specific conditions: text appearance, text disappearance, or time duration',
         inputSchema: z.object({
             time: z.number().optional().describe('The time to wait in seconds'),
             text: z.string().optional().describe('The text to wait for'),

package/package.json

@@ -1,13 +1,38 @@
 {
   "name": "@darbotlabs/darbot-browser-mcp",
-  "version": "0.1.0",
-  "description": "🤖 Your Autonomous Browser Companion - 29 AI-driven browser tools with work profile support",
+  "version": "0.2.0",
+  "description": "🤖 Your Autonomous Browser Companion - 29 AI-driven browser tools with work profile support and VS Code GitHub Copilot agent mode integration",
   "type": "module",
   "repository": {
     "type": "git",
     "url": "git+https://github.com/darbotlabs/darbot-browser-mcp.git"
   },
   "homepage": "https://github.com/darbotlabs/darbot-browser-mcp",
+  "keywords": [
+    "mcp",
+    "browser",
+    "autonomous",
+    "darbot",
+    "automation", 
+    "testing",
+    "screenshot",
+    "copilot",
+    "ai",
+    "edge",
+    "chrome",
+    "web-automation",
+    "playwright",
+    "selenium-alternative",
+    "browser-testing",
+    "accessibility",
+    "work-profiles",
+    "session-management",
+    "github-copilot",
+    "model-context-protocol",
+    "vscode-extension",
+    "agent-mode",
+    "copilot-integration"
+  ],
   "engines": {
     "node": ">=18"
   },
@@ -25,7 +50,9 @@
     "run-server": "node cli.js",
     "run-darbot": "node cli.js",
     "clean": "rmdir /s /q lib 2>nul || echo Clean completed",
-    "npm-publish": "npm run clean && npm run build && npm run test && npm publish"
+    "npm-publish": "npm run clean && npm run build && npm run test && npm publish",
+    "package": "npm run build && npm pack",
+    "prepublishOnly": "npm run clean && npm run build"
   },
   "exports": {
     "./package.json": "./package.json",