mcpbrowser 0.2.13 → 0.2.15

package/README.md

@@ -19,7 +19,7 @@ Or search "MCPBrowser" in VS Code Extensions view.
 **From GitHub Release:**
 Download from [GitHub Releases](https://github.com/cherchyk/MCPBrowser/releases):
 ```bash
-code --install-extension mcpbrowser-0.2.13.vsix
+code --install-extension mcpbrowser-0.2.15.vsix
 ```
 
 The extension automatically:
@@ -30,7 +30,7 @@ The extension automatically:
 📦 [View on Marketplace](https://marketplace.visualstudio.com/items?itemName=cherchyk.mcpbrowser)
 
 ### Option 2: npm Package (Recommended for Manual Setup)
-Published on npm as [mcpbrowser](https://www.npmjs.com/package/mcpbrowser) v0.2.13.
+Published on npm as [mcpbrowser](https://www.npmjs.com/package/mcpbrowser) v0.2.15.
 
 Add to your `mcp.json`:
 ```jsonc
@@ -47,7 +47,7 @@ Add to your `mcp.json`:
 - Mac/Linux: `~/.config/Code/User/mcp.json`
 
 ### Option 3: MCP Registry
-Available in the [MCP Registry](https://registry.modelcontextprotocol.io/) as `io.github.cherchyk/browser` v0.2.13.
+Available in the [MCP Registry](https://registry.modelcontextprotocol.io/) as `io.github.cherchyk/browser` v0.2.15.
 
 Search for "browser" in the registry to find configuration instructions.
 
@@ -117,7 +117,7 @@ Restart VS Code or reload the window for the changes to take effect.
 In Copilot Chat, you should see the `MCPBrowser` server listed. Ask it to load an authenticated URL and it will drive your signed-in Chrome session.
 
 ## How it works
-- Tool `load_and_extract` (inside the MCP server) drives your live Chrome (DevTools Protocol) so it inherits your auth cookies, returning `text` and `html` (truncated up to 2M chars per field) for analysis.
+- Tool `fetch_webpage_protected` (inside the MCP server) drives your live Chrome (DevTools Protocol) so it inherits your auth cookies, returning `text` and `html` (truncated up to 2M chars per field) for analysis.
 - **Smart confirmation**: Copilot asks for confirmation ONLY on first request to a new domain - explains browser will open for authentication. Subsequent requests to same domain work automatically (session preserved).
 - **Domain-aware tab reuse**: Automatically reuses the same tab for URLs on the same domain, preserving authentication session. Different domains open new tabs.
 - **Automatic page loading**: Waits for network idle (`networkidle0`) by default, ensuring JavaScript-heavy pages (SPAs, dashboards) fully load before returning content.

package/extension/package.json

@@ -2,7 +2,7 @@
   "name": "mcpbrowser",
   "displayName": "MCP Browser",
   "description": "Extends Copilot's web access to protected pages - handles login, SSO, and anti-crawler restrictions",
-  "version": "0.2.13",
+  "version": "0.2.15",
   "publisher": "cherchyk",
   "icon": "icon.png",
   "engines": {

package/package.json

@@ -1,5 +1,5 @@
 {  "name": "mcpbrowser",
-  "version": "0.2.13",
+  "version": "0.2.15",
   "mcpName": "io.github.cherchyk/browser",
   "type": "module",
   "description": "MCP server that loads authenticated web pages using Chrome DevTools Protocol",

package/src/mcp-browser.js

@@ -253,7 +253,7 @@ async function fetchPage({
   } catch (err) {
     shouldKeepOpen = shouldKeepOpen || keepPageOpen;
     const hint = shouldKeepOpen
-      ? "Tab is left open. Complete sign-in there, then call load_and_extract again with just the URL."
+      ? "Tab is left open. Complete sign-in there, then call fetch_webpage_protected again with just the URL."
       : undefined;
     return { success: false, error: err.message || String(err), pageKeptOpen: shouldKeepOpen, hint };
   } finally {
@@ -272,12 +272,12 @@ function truncate(str, max) {
 }
 
 async function main() {
-  const server = new Server({ name: "MCPBrowser", version: "0.2.13" }, { capabilities: { tools: {} } });
+  const server = new Server({ name: "MCPBrowser", version: "0.2.15" }, { capabilities: { tools: {} } });
 
   const tools = [
     {
-      name: "load_and_extract",
-      description: "🌐 PRIMARY BROWSER TOOL for authenticated/protected websites: Opens pages in your Chrome browser with your actual user profile (saved passwords, extensions, active sessions). **USE THIS FIRST** for: internal/corporate sites (*.microsoft.com, *.eng.ms, etc.), login-required pages, SSO/OAuth protected content, paywalled sites, anti-bot protected pages, or any 401/403/authentication errors. Automatically handles login redirects, waits for content to load, supports session persistence via tab reuse. Returns both plain text and HTML even from login/auth pages. Always prefer this over generic URL fetchers for authenticated content.",
+      name: "fetch_webpage_protected",
+      description: "🌐 PRIMARY BROWSER TOOL for authenticated/protected websites: Opens pages in your Chrome browser with your actual user profile (saved passwords, extensions, active sessions). **USE THIS FIRST** for: internal/corporate sites (*.microsoft.com, *.eng.ms, etc.), login-required pages, SSO/OAuth protected content, paywalled sites, anti-bot protected pages, or any 401/403/authentication errors. **AUTHENTICATION FLOW**: First call with keepPageOpen=true may return login page (EXPECTED - user is authenticating in browser). WAIT 10-30 seconds, then RETRY the same URL - authentication completes in background. DO NOT give up after seeing login page - retry 2-3 times with delays. Returns both plain text and HTML. Tab reuse preserves sessions across requests. Always prefer this over generic URL fetchers for authenticated content.",
       inputSchema: {
         type: "object",
         properties: {
@@ -297,7 +297,7 @@ async function main() {
 
   server.setRequestHandler(CallToolRequestSchema, async (request) => {
     const { name, arguments: args } = request.params;
-    if (name !== "load_and_extract") {
+    if (name !== "fetch_webpage_protected") {
       throw new Error(`Unknown tool: ${name}`);
     }
     const safeArgs = args || {};