mcpbrowser 0.3.17 → 0.3.19

package/README.md

@@ -7,7 +7,7 @@
 
 > ⚠️ **Security Notice:** MCPBrowser extracts webpage content and provides it to your AI agent (e.g., GitHub Copilot, Claude), which then sends it to the LLM provider it uses (e.g., Anthropic, OpenAI, GitHub) for processing. Make sure you trust both your agent and the LLM provider — especially when accessing pages with sensitive or private data.
 
-**MCPBrowser is an MCP browser server that gives AI assistants the ability to browse web pages using a real Chrome or Edge browser.** This browser-based MCP server fetches any web page — especially those protected by authentication, CAPTCHAs, anti-bot protection, or requiring JavaScript rendering. Uses your real Chrome/Edge browser for web automation so you can log in normally, then automatically extracts content. Works with corporate SSO, login forms, Cloudflare, and JavaScript-heavy sites (SPAs, dashboards).
+**MCPBrowser is an MCP browser server that gives AI assistants the ability to browse web pages using a real Chrome, Edge, or Brave browser.** This browser-based MCP server fetches any web page — especially those protected by authentication, CAPTCHAs, anti-bot protection, or requiring JavaScript rendering. Uses your real browser for web automation so you can log in normally, then automatically extracts content. Works with corporate SSO, login forms, Cloudflare, and JavaScript-heavy sites (SPAs, dashboards).
 
 This is an [MCP (Model Context Protocol)](https://modelcontextprotocol.io/) server using [stdio transport](https://modelcontextprotocol.io/docs/concepts/transports#stdio). Your AI assistant uses this web browser MCP server when standard HTTP requests fail — pages requiring authentication, CAPTCHA protection, or heavy JavaScript (SPAs). Once connected, the browser MCP server can navigate through websites, interact with elements, and send HTML back to the AI assistant. This gives your AI the ability to browse the web just like you do.
 
@@ -15,10 +15,9 @@ Example workflow for AI assistant to use MCPBrowser
 
 ```
 1. fetch_webpage    → Load the login page
-2. type_text        → Enter username
-3. type_text        → Enter password
-4. click_element    → Click "Sign In"
-5. get_current_html → Extract the content after login
+2. type_text        → Enter username and password (multiple fields at once)
+3. click_element    → Click "Sign In"
+4. get_current_html → Extract the content after login
 ```
 
 
@@ -35,6 +34,8 @@ Example workflow for AI assistant to use MCPBrowser
   - [click_element](#click_element)
   - [type_text](#type_text)
   - [get_current_html](#get_current_html)
+  - [scroll_page](#scroll_page)
+  - [take_screenshot](#take_screenshot)
   - [close_tab](#close_tab)
 - [Configuration](#configuration-optional)
 - [Troubleshooting](#troubleshooting)
@@ -42,7 +43,7 @@ Example workflow for AI assistant to use MCPBrowser
 
 ## Requirements
 
-- Chrome or Edge browser
+- Chrome, Edge, or Brave browser
 - [Node.js 18+](https://nodejs.org/) (includes npm)
 
 > **Note:** Node.js must be installed on your system. The VS Code extension and npm package both require Node.js to run the MCP server. Download from [nodejs.org](https://nodejs.org/) if not already installed.
@@ -53,8 +54,9 @@ Example workflow for AI assistant to use MCPBrowser
 |---|----------|------------|
 | 1 | [VS Code Extension](#option-1-vs-code-extension) | One Click |
 | 2 | [Claude Code](#option-2-claude-code) | One Command |
-| 3 | [Claude Desktop](#option-3-claude-desktop) | Manual |
-| 4 | [npm Package](#option-4-npm-package) | Manual |
+| 3 | [OpenClaw](#option-3-openclaw) | One Command |
+| 4 | [Claude Desktop](#option-4-claude-desktop) | Manual |
+| 5 | [npm Package](#option-5-npm-package) | Manual |
 
 ### Option 1: VS Code Extension
 
@@ -84,7 +86,22 @@ mcpbrowser: npx -y mcpbrowser@latest - ✓ Connected
 That's it! Ask Claude to fetch any protected page:
 > "Fetch https://portal.azure.com using mcpbrowser"
 
-### Option 3: Claude Desktop
+### Option 3: OpenClaw
+
+[OpenClaw](https://openclaw.ai/) is a personal AI assistant that runs on your devices. Add MCPBrowser to give it browser automation capabilities:
+
+```bash
+openclaw mcp add mcpbrowser -- npx -y mcpbrowser@latest
+```
+
+Verify it's working:
+```bash
+openclaw mcp list
+```
+
+Now OpenClaw can browse authenticated pages, fill forms, and interact with web apps using your existing browser sessions.
+
+### Option 4: Claude Desktop
 
 Add to your config file:
 
@@ -104,7 +121,7 @@ Add to your config file:
 
 Restart Claude Desktop after saving.
 
-### Option 4: npm Package
+### Option 5: npm Package
 
 For VS Code (GitHub Copilot) manual setup, add to your `mcp.json`:
 
@@ -182,36 +199,55 @@ Clicks on any clickable element (buttons, links, divs with onclick handlers, etc
 
 ### `type_text`
 
-Types text into an input field, textarea, or other editable element. Simulates human-like typing with configurable delay between keystrokes. Automatically clears existing text by default.
+Types text into one or more input fields in a single call. Supports filling entire forms at once for efficient automation. Automatically clears existing text by default.
 
 **⚠️ Note:** Page must be already loaded via `fetch_webpage` first.
 
 **Parameters:**
 - `url` (string, required) - The URL of the page (must match a previously fetched page)
-- `selector` (string, required) - CSS selector for the input element (e.g., `#username`, `input[name="email"]`)
-- `text` (string, required) - Text to type into the field
-- `clear` (boolean, optional, default: `true`) - Whether to clear existing text first
-- `typeDelay` (number, optional, default: `50`) - Delay between keystrokes in milliseconds (simulates human typing)
+- `fields` (array, required) - Array of fields to fill. Each field object contains:
+  - `selector` (string, required) - CSS selector for the input element (e.g., `#username`, `input[name="email"]`)
+  - `text` (string, required) - Text to type into the field
+  - `clear` (boolean, optional, default: `true`) - Whether to clear existing text first
+  - `waitForElementTimeout` (number, optional, default: `5000`) - Maximum time to wait for element in milliseconds
 - `returnHtml` (boolean, optional, default: `true`) - Whether to wait for stability and return HTML after typing
 - `removeUnnecessaryHTML` (boolean, optional, default: `true`) - Remove unnecessary HTML for size reduction. Only used when `returnHtml` is `true`
 - `postTypeWait` (number, optional, default: `1000`) - Milliseconds to wait after typing for SPAs to render dynamic content
-- `waitForElementTimeout` (number, optional, default: `5000`) - Maximum time to wait for element in milliseconds
 
 **Examples:**
 ```javascript
-// Basic text input
-{ url: "https://example.com", selector: "#email", text: "user@example.com" }
-
-// Append text without clearing
-{ url: "https://example.com", selector: "#search", text: " advanced", clear: false }
+// Fill multiple fields at once (login form)
+{ 
+  url: "https://example.com/login", 
+  fields: [
+    { selector: "#username", text: "john@example.com" },
+    { selector: "#password", text: "secretpass123" }
+  ]
+}
 
-// Fast typing without human simulation
-{ url: "https://example.com", selector: "#username", text: "john", typeDelay: 0 }
+// Single field input
+{ url: "https://example.com", fields: [{ selector: "#search", text: "query" }] }
 
-// Type without waiting for HTML return (faster)
-{ url: "https://example.com", selector: "#field", text: "value", returnHtml: false }
+// Append text without clearing
+{ url: "https://example.com", fields: [{ selector: "#notes", text: " additional text", clear: false }] }
+
+// Fast form fill without HTML return
+{ 
+  url: "https://example.com/signup", 
+  fields: [
+    { selector: "#firstName", text: "John" },
+    { selector: "#lastName", text: "Doe" },
+    { selector: "#email", text: "john@example.com" }
+  ],
+  returnHtml: false 
+}
 ```
 
+**Error handling:** If a field fails, the response indicates:
+- Which field number failed (e.g., "Failed on field 2 of 3")
+- Which fields were successfully filled
+- Clear guidance to NOT re-type already filled fields
+
 ---
 
 ### `get_current_html`
@@ -239,6 +275,74 @@ Gets the current HTML from an already-loaded page **WITHOUT** navigating or relo
 
 ---
 
+### `scroll_page`
+
+Scrolls within an already-loaded page. Use before `take_screenshot` to capture different parts of the page, or to bring elements into view before interaction. Supports multiple scroll modes:
+
+- **By direction**: Scroll up/down/left/right by pixel amount
+- **To element**: Scroll until a specific element is visible
+- **To position**: Scroll to absolute coordinates
+
+**⚠️ Note:** Page must be already loaded via `fetch_webpage` first.
+
+**Parameters:**
+- `url` (string, required) - The URL of the page (must match a previously fetched page)
+- `direction` (string, optional) - Direction to scroll: `up`, `down`, `left`, `right`. Use with `amount`.
+- `amount` (number, optional, default: `500`) - Pixels to scroll in the specified direction (~half a viewport)
+- `selector` (string, optional) - CSS selector of element to scroll into view. Ignores direction/amount.
+- `x` (number, optional) - Absolute horizontal scroll position. Use with `y`.
+- `y` (number, optional) - Absolute vertical scroll position. Use with `x`.
+
+**Examples:**
+```javascript
+// Scroll down by 500px (default)
+{ url: "https://example.com", direction: "down" }
+
+// Scroll down by 1000px
+{ url: "https://example.com", direction: "down", amount: 1000 }
+
+// Scroll an element into view
+{ url: "https://example.com", selector: "#footer" }
+
+// Scroll to specific position
+{ url: "https://example.com", x: 0, y: 2000 }
+
+// Scroll to top of page
+{ url: "https://example.com", x: 0, y: 0 }
+```
+
+**Returns:** Current scroll position, page dimensions, and viewport size — useful for understanding where you are on the page.
+
+---
+
+### `take_screenshot`
+
+Takes a screenshot of an already-loaded page for visual analysis. **Useful when HTML parsing is insufficient** — for example, pages with charts, images, complex layouts, popups, or visual content that's hard to understand from HTML alone. Returns a PNG image.
+
+**⚠️ Note:** Page must be already loaded via `fetch_webpage` first.
+
+**Parameters:**
+- `url` (string, required) - The URL of the page (must match a previously fetched page)
+- `fullPage` (boolean, optional, default: `false`) - Capture the full scrollable page instead of just the viewport
+
+**Examples:**
+```javascript
+// Capture viewport screenshot (default)
+{ url: "https://example.com" }
+
+// Capture full scrollable page
+{ url: "https://dashboard.example.com", fullPage: true }
+```
+
+**Use cases:**
+- Visualize page layout when HTML is hard to parse
+- Capture charts, graphs, or data visualizations
+- Debug popups, modals, or overlays
+- Understand visual feedback (highlights, animations)
+- See what's blocking an element click
+
+---
+
 ### `close_tab`
 
 Closes the browser tab for the given URL's hostname. Removes the page from the tab pool and forces a fresh session on the next visit to that hostname. Useful for clearing authentication state, managing memory, or starting fresh with a domain.
@@ -299,7 +403,7 @@ Logs go to `stderr` so they don't interfere with MCP protocol on `stdout`.
 ## Troubleshooting
 
 **Browser doesn't open?**
-- Make sure Chrome or Edge is installed
+- Make sure Chrome, Edge, or Brave is installed
 - Try setting `CHROME_PATH` explicitly
 
 **Can't connect to browser?**

package/package.json

@@ -1,9 +1,9 @@
 {
   "name": "mcpbrowser",
-  "version": "0.3.17",
+  "version": "0.3.19",
   "mcpName": "io.github.cherchyk/mcpbrowser",
   "type": "module",
-  "description": "MCP browser server - fetch web pages using real Chrome/Edge browser. Handles authentication, SSO, CAPTCHAs, and anti-bot protection. Browser automation for AI assistants.",
+  "description": "MCP browser server - fetch web pages using real Chrome/Edge/Brave browser. Handles authentication, SSO, CAPTCHAs, and anti-bot protection. Browser automation for AI assistants.",
   "main": "src/mcp-browser.js",
   "bin": {
     "mcpbrowser": "src/mcp-browser.js"

package/src/actions/click-element.js

@@ -24,9 +24,9 @@
  * - Flexible: Can disable waiting for fast form interactions
  */
 
-import { getBrowser, domainPages } from '../core/browser.js';
+import { getBrowser, getValidatedPage } from '../core/browser.js';
 import { extractAndProcessHtml, waitForPageStability } from '../core/page.js';
-import { MCPResponse, ErrorResponse } from '../core/responses.js';
+import { MCPResponse, InformationalResponse } from '../core/responses.js';
 import logger from '../core/logger.js';
 
 /**
@@ -171,15 +171,36 @@ export async function clickElement({ url, selector, text, waitForElementTimeout
     throw new Error(`Invalid URL: ${url}`);
   }
 
-  const browser = await getBrowser();
-  let page = domainPages.get(hostname);
+  // Ensure browser connection (triggers domain map rebuild on reconnect)
+  try {
+    await getBrowser();
+  } catch (err) {
+    logger.error(`click_element: Failed to connect to browser: ${err.message}`);
+    return new InformationalResponse(
+      `Browser connection failed: ${err.message}`,
+      'The browser must be running with remote debugging enabled.',
+      [
+        'Ensure the browser is installed and running',
+        'Check that remote debugging is enabled (--remote-debugging-port)',
+        'Try restarting the MCP server'
+      ]
+    );
+  }
+
+  // Validate page exists and is usable
+  const { page, error: pageError } = await getValidatedPage(hostname);
   
-  if (!page || page.isClosed()) {
-    logger.error(`No open page found for ${hostname}`);
-    return new ErrorResponse(
-      `No open page found for ${hostname}. Please fetch the page first using fetch_webpage.`,
+  if (!page) {
+    const isConnectionLost = pageError && pageError.includes('connection');
+    logger.info(`click_element: ${pageError || 'No page found for ' + hostname}`);
+    return new InformationalResponse(
+      isConnectionLost ? `Page connection lost for ${hostname}` : `No open page found for ${hostname}`,
+      isConnectionLost 
+        ? 'The browser tab was closed or the connection was lost. The page needs to be reloaded.'
+        : 'The page must be loaded before you can interact with elements on it',
       [
-        "Use fetch_webpage to load the page first"
+        "Use MCPBrowser's fetch_webpage tool to load the page first",
+        "Then retry MCPBrowser's click_element with the same URL"
       ]
     );
   }
@@ -218,10 +239,12 @@ export async function clickElement({ url, selector, text, waitForElementTimeout
     }
 
     if (!elementHandle || !elementHandle.asElement()) {
-      return new ErrorResponse(
+      return new InformationalResponse(
         selector ? `Element not found: ${selector}` : `Element with text "${text}" not found`,
+        'The element could not be located on the page. It may be hidden, dynamically loaded, or the selector/text may be incorrect.',
         [
-          "Use get_current_html to verify page content",
+          "Use MCPBrowser's get_current_html to verify page content",
+          "Use MCPBrowser's take_screenshot to see the visual layout if HTML is unclear",
           "Try a different selector or text",
           "Check if the element is visible on the page"
         ]
@@ -260,10 +283,11 @@ export async function clickElement({ url, selector, text, waitForElementTimeout
         selector ? `Clicked element: ${selector}` : `Clicked element with text: "${text}"`,
         html,
         [
-          "Use click_element again to navigate further",
-          "Use type_text to fill forms if needed",
-          "Use get_current_html to refresh page state",
-          "Use close_tab when finished"
+          "Use MCPBrowser's click_element again to navigate further",
+          "Use MCPBrowser's type_text to fill forms if needed",
+          "Use MCPBrowser's get_current_html to refresh page state",
+          "Use MCPBrowser's take_screenshot if page has popups or visual content that's hard to parse from HTML",
+          "Use MCPBrowser's close_tab when finished"
         ]
       );
     } else {
@@ -285,20 +309,23 @@ export async function clickElement({ url, selector, text, waitForElementTimeout
         selector ? `Clicked element: ${selector}` : `Clicked element with text: "${text}"`,
         null,
         [
-          "Use get_current_html to see updated page state",
-          "Use click_element or type_text for more interactions",
-          "Use close_tab when finished"
+          "Use MCPBrowser's get_current_html to see updated page state",
+          "Use MCPBrowser's take_screenshot if the page has popups, modals, or visual content",
+          "Use MCPBrowser's click_element or MCPBrowser's type_text for more interactions",
+          "Use MCPBrowser's close_tab when finished"
         ]
       );
     }
   } catch (err) {
     logger.error(`click_element failed: ${err.message}`);
-    return new ErrorResponse(
+    return new InformationalResponse(
       `Failed to click element: ${err.message}`,
+      'The element was found but could not be clicked. It may be covered by another element, not interactable, or the page may have changed.',
       [
-        "Use get_current_html to check current page state",
+        "Use MCPBrowser's get_current_html to check current page state",
+        "Use MCPBrowser's take_screenshot to see what's visually blocking the element",
         "Verify the selector or text is correct",
-        "Try fetch_webpage to reload if page is stale"
+        "Try MCPBrowser's fetch_webpage to reload if page is stale"
       ]
     );
   }

package/src/actions/close-tab.js

@@ -145,7 +145,7 @@ export async function closeTab({ url }) {
           'No open tab found for this hostname',
           hostname,
           [
-            "Use fetch_webpage to open a new page if needed"
+            "Use MCPBrowser's fetch_webpage to open a new page if needed"
           ]
         );
       }
@@ -164,7 +164,7 @@ export async function closeTab({ url }) {
         'Tab was already closed',
         hostname,
         [
-          "Use fetch_webpage to open a new page if needed"
+          "Use MCPBrowser's fetch_webpage to open a new page if needed"
         ]
       );
     }
@@ -181,7 +181,7 @@ export async function closeTab({ url }) {
       `Successfully closed tab for ${hostname}`,
       hostname,
       [
-        "Use fetch_webpage to open a new page if needed"
+        "Use MCPBrowser's fetch_webpage to open a new page if needed"
       ]
     );
     

package/src/actions/fetch-page.js

@@ -6,7 +6,7 @@
 import { getBrowser, domainPages } from '../core/browser.js';
 import { getOrCreatePage, queueRequest, navigateToUrl, waitForPageReady, extractAndProcessHtml, waitForPageStability } from '../core/page.js';
 import { detectRedirectType, waitForAutoAuth, waitForManualAuth } from '../core/auth.js';
-import { MCPResponse, ErrorResponse } from '../core/responses.js';
+import { MCPResponse, ErrorResponse, HttpStatusResponse, InformationalResponse } from '../core/responses.js';
 import logger from '../core/logger.js';
 
 /**
@@ -156,14 +156,29 @@ async function doFetchPage({ url, hostname, browser, removeUnnecessaryHTML, post
   const authCompletionTimeout = 600000;
   const reuseLastKeptPage = true;
 
-  const browserInstance = await getBrowser(browser);
+  // Ensure browser connection
+  let browserInstance;
+  try {
+    browserInstance = await getBrowser(browser);
+  } catch (err) {
+    logger.error(`fetch_webpage: Failed to connect to browser: ${err.message}`);
+    return new InformationalResponse(
+      `Browser connection failed: ${err.message}`,
+      'The browser must be running with remote debugging enabled.',
+      [
+        'Ensure the browser is installed and running',
+        'Check that remote debugging is enabled (--remote-debugging-port)',
+        'Try restarting the MCP server'
+      ]
+    );
+  }
   
   try {
     // Get or create page for this domain (simple - no locks needed)
     let page = await getOrCreatePage(browserInstance, hostname, reuseLastKeptPage);
     
     // Navigate to URL (pure navigation)
-    await navigateToUrl(page, url, waitUntil, navigationTimeout);
+    const { statusCode, statusText } = await navigateToUrl(page, url, waitUntil, navigationTimeout);
     
     // Wait for page content to be ready (handles SPAs automatically)
     await waitForPageReady(page);
@@ -227,8 +242,8 @@ async function doFetchPage({ url, hostname, browser, removeUnnecessaryHTML, post
             manualAuthResult.error,
             [
               "Complete authentication in the browser window",
-              "Call fetch_webpage again with the same URL to retry",
-              "Use close_tab to reset the session if authentication fails"
+              "Call MCPBrowser's fetch_webpage again with the same URL to retry",
+              "Use MCPBrowser's close_tab to reset the session if authentication fails"
             ]
           );
         }
@@ -257,14 +272,26 @@ async function doFetchPage({ url, hostname, browser, removeUnnecessaryHTML, post
     
     logger.info(`fetch_webpage completed: ${page.url()}`);
     
+    // Check for non-2xx HTTP status codes - return informational response (not red error)
+    if (statusCode && (statusCode >= 400 && statusCode < 600)) {
+      logger.info(`HTTP ${statusCode} ${statusText} - returning as informational response`);
+      return new HttpStatusResponse(
+        page.url(),
+        statusCode,
+        statusText,
+        processedHtml
+      );
+    }
+    
     return new FetchPageSuccessResponse(
       page.url(),
       processedHtml,
       [
-        "Use click_element to interact with buttons/links on the page",
-        "Use type_text to fill in form fields",
-        "Use get_current_html to re-check page state after interactions",
-        "Use close_tab when finished to free browser resources"
+        "Use MCPBrowser's click_element to interact with buttons/links on the page",
+        "Use MCPBrowser's type_text to fill in form fields",
+        "Use MCPBrowser's get_current_html to re-check page state after interactions",
+        "Use MCPBrowser's take_screenshot if page has charts, images, or complex visual layout that's hard to understand from HTML",
+        "Use MCPBrowser's close_tab when finished to free browser resources"
       ]
     );
   } catch (err) {
@@ -273,8 +300,8 @@ async function doFetchPage({ url, hostname, browser, removeUnnecessaryHTML, post
       err.message || String(err),
       [
         "Complete authentication in the browser if prompted",
-        "Call fetch_webpage again with the same URL to retry",
-        "Use close_tab to reset the session if needed"
+        "Call MCPBrowser's fetch_webpage again with the same URL to retry",
+        "Use MCPBrowser's close_tab to reset the session if needed"
       ]
     );
   }

package/src/actions/get-current-html.js

@@ -2,9 +2,9 @@
  * get-current-html.js - Get current HTML from an already-loaded page
  */
 
-import { getBrowser, domainPages } from '../core/browser.js';
+import { getBrowser, getValidatedPage } from '../core/browser.js';
 import { extractAndProcessHtml } from '../core/page.js';
-import { MCPResponse, ErrorResponse } from '../core/responses.js';
+import { MCPResponse, InformationalResponse } from '../core/responses.js';
 import logger from '../core/logger.js';
 
 /**
@@ -113,15 +113,36 @@ export async function getCurrentHtml({ url, removeUnnecessaryHTML = true }) {
     throw new Error(`Invalid URL: ${url}`);
   }
 
-  const browser = await getBrowser();
-  let page = domainPages.get(hostname);
+  // Ensure browser connection (triggers domain map rebuild on reconnect)
+  try {
+    await getBrowser();
+  } catch (err) {
+    logger.error(`get_current_html: Failed to connect to browser: ${err.message}`);
+    return new InformationalResponse(
+      `Browser connection failed: ${err.message}`,
+      'The browser must be running with remote debugging enabled.',
+      [
+        'Ensure the browser is installed and running',
+        'Check that remote debugging is enabled (--remote-debugging-port)',
+        'Try restarting the MCP server'
+      ]
+    );
+  }
+
+  // Validate page exists and is usable
+  const { page, error: pageError } = await getValidatedPage(hostname);
   
-  if (!page || page.isClosed()) {
-    logger.error(`get_current_html: No open page found for ${hostname}`);
-    return new ErrorResponse(
-      `No open page found for ${hostname}. Please fetch the page first using fetch_webpage.`,
+  if (!page) {
+    const isConnectionLost = pageError && pageError.includes('connection');
+    logger.info(`get_current_html: ${pageError || 'No page found for ' + hostname}`);
+    return new InformationalResponse(
+      isConnectionLost ? `Page connection lost for ${hostname}` : `No open page found for ${hostname}`,
+      isConnectionLost 
+        ? 'The browser tab was closed or the connection was lost. The page needs to be reloaded.'
+        : 'The page must be loaded before you can get its current HTML',
       [
-        "Use fetch_webpage to load the page first"
+        "Use MCPBrowser's fetch_webpage tool to load the page first",
+        "Then retry MCPBrowser's get_current_html with the same URL"
       ]
     );
   }
@@ -136,18 +157,20 @@ export async function getCurrentHtml({ url, removeUnnecessaryHTML = true }) {
       currentUrl,
       html,
       [
-        "Use click_element to interact with elements",
-        "Use type_text to fill forms",
-        "Use close_tab to free resources when done"
+        "Use MCPBrowser's click_element to interact with elements",
+        "Use MCPBrowser's type_text to fill forms",
+        "Use MCPBrowser's take_screenshot if page layout or visual content is hard to understand from HTML",
+        "Use MCPBrowser's close_tab to free resources when done"
       ]
     );
   } catch (err) {
     logger.error(`get_current_html failed: ${err.message}`);
-    return new ErrorResponse(
+    return new InformationalResponse(
       `Failed to get HTML: ${err.message}`,
+      'Could not extract HTML from the page. The page may have navigated away or the connection was lost.',
       [
-        "Try fetch_webpage to reload the page",
-        "Use close_tab and start fresh if needed"
+        "Try MCPBrowser's fetch_webpage to reload the page",
+        "Use MCPBrowser's close_tab and start fresh if needed"
       ]
     );
   }