mcpbrowser 0.2.4 → 0.2.6

package/README.md

@@ -1,10 +1,10 @@
-# MCPBrowser (MCP fetch tool with authenticated Chrome)
+# MCP Browser (MCP fetch for protected web resources)
 
 [![VS Code Marketplace](https://img.shields.io/visual-studio-marketplace/v/cherchyk.mcpbrowser.svg)](https://marketplace.visualstudio.com/items?itemName=cherchyk.mcpbrowser)
 [![npm version](https://img.shields.io/npm/v/mcpbrowser.svg)](https://www.npmjs.com/package/mcpbrowser)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
-Alternative web fetcher for GitHub Copilot when normal URL access fails due to authentication or anti-crawler restrictions. Uses your Chrome/Edge browser session via DevTools Protocol to bypass login requirements and bot detection.
+**Extends GitHub Copilot's web access to protected pages** - handles login-protected pages, corporate SSO, and anti-crawler restrictions that normal fetching can't handle. Uses your Chrome/Edge browser session via DevTools Protocol.
 
 ## 🚀 Installation Options
 

package/extension/README.md

@@ -1,13 +1,12 @@
-# MCPBrowser
+# MCP Browser
 
-Alternative web fetcher for GitHub Copilot when normal URL access fails due to authentication or anti-crawler restrictions.
+**Extends GitHub Copilot's web access to protected pages** - handles login-protected pages, corporate SSO, and anti-crawler restrictions that normal fetching can't handle.
 
 ## Features
 
-- 🚀 **One-Click Setup**: Installs npm package and configures mcp.json automatically
-- 🔐 **Bypass Authentication**: Opens pages in your Chrome/Edge browser - you authenticate if needed, MCPBrowser waits and fetches the final page content
-- 🤖 **Beat Anti-Crawler**: Works when sites block Copilot's normal fetching
-- ⚙️ **Auto-Configuration**: Complete setup with a single click
+- 🚀 **One-Click Setup**: Installs npm package and configures mcp.json automatically - complete setup with a single click
+- 🔐 **Authentication Support**: Opens pages in your Chrome/Edge browser - authenticate once, reuse sessions automatically
+- 🤖 **Bypass Anti-Crawler**: Access sites that block automated tools
 
 ## How It Works
 

package/extension/package.json

@@ -1,8 +1,8 @@
 {
   "name": "mcpbrowser",
-  "displayName": "MCPBrowser",
-  "description": "Alternative web fetcher for Copilot when auth/crawler blocks prevent normal access. Installs and configures MCPBrowser",
-  "version": "0.1.4",
+  "displayName": "MCP Browser",
+  "description": "Extends Copilot's web access to protected pages - handles login, SSO, and anti-crawler restrictions",
+  "version": "0.1.6",
   "publisher": "cherchyk",
   "icon": "icon.png",
   "engines": {

package/package.json

@@ -1,5 +1,5 @@
 {  "name": "mcpbrowser",
-  "version": "0.2.4",
+  "version": "0.2.6",
   "mcpName": "io.github.cherchyk/browser",
   "type": "module",
   "description": "MCP server that loads authenticated web pages using Chrome DevTools Protocol",

package/server.json

@@ -6,7 +6,7 @@
     "url": "https://github.com/cherchyk/MCPBrowser",
     "source": "github"
   },
-  "version": "0.2.4",
+  "version": "0.2.6",
   "packages": [
     {
       "registryType": "npm",

package/src/mcp-browser.js

@@ -227,7 +227,7 @@ async function main() {
   const tools = [
     {
       name: "load_and_extract",
-      description: "**FALLBACK MECHANISM**: Use this when normal URL fetching fails due to authentication requirements, login redirects, 401/403 errors, anti-crawler/bot detection, or session requirements. **FIRST ACCESS ONLY**: Ask user for confirmation ONLY if this is the first request to this domain/site - explain a browser window will open where they may need to authenticate. **SUBSEQUENT REQUESTS**: Use automatically without asking - browser session is already authenticated. Loads web pages using your authenticated Chrome/Edge browser session via DevTools Protocol, bypassing auth and crawler restrictions. Automatically handles auth redirects, waits for network idle, and supports tab reuse to preserve sessions. Returns both plain text and HTML content.",
+      description: "⚠️ BROWSER ACCESS: Opens pages in your Chrome browser with your default profile (saved passwords, extensions, authenticated sessions). Use when normal URL fetching fails due to authentication requirements, login redirects, 401/403 errors, anti-crawler/bot detection, or session requirements. Automatically handles auth redirects, waits for network idle, and supports tab reuse to preserve sessions. Returns both plain text and HTML content.",
       inputSchema: {
         type: "object",
         properties: {
@@ -237,6 +237,9 @@ async function main() {
         required: ["url"],
         additionalProperties: false,
       },
+      annotations: {
+        title: "Access Authenticated Web Page"
+      }
     },
   ];