@page2ai/mcp 0.8.0 → 0.8.1

package/CHANGELOG.md

@@ -5,6 +5,15 @@ The format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/) and
 project uses [Semantic Versioning](https://semver.org/spec/v2.0.0.html); while the
 major version is `0`, a minor bump may carry breaking changes.
 
+## 0.8.1 - 2026-11-02
+
+### Changed
+
+- **`@page2ai/core` 0.4.0:** `HTTPS_PROXY`, `HTTP_PROXY` and `NO_PROXY` environment variables are now
+  honoured by the page fetch. Corporate networks and self-hosted CI runners behind a proxy can set
+  these variables and `page_to_markdown` will route through the proxy while keeping SSRF checks.
+  undici upgraded to 7.30.1 (fixes CVE-2026-87018). Node.js >=20.18.1 required.
+
 ## 0.8.0 - 2026-11-02
 
 Multiple MCP clients (Claude Desktop, Cursor, `claude -p`) can now share the user's browser through Agent Bridge simultaneously.

package/manifest.json

@@ -2,7 +2,7 @@
   "manifest_version": "0.3",
   "name": "page2ai-mcp",
   "display_name": "Page2AI — Web to Markdown",
-  "version": "0.8.0",
+  "version": "0.8.1",
   "description": "Convert any web page to clean Markdown for LLM context",
   "long_description": "Page2AI MCP converts a web page URL to Markdown for AI context windows. It keeps the page's main content (its <main> or dominant <article>), preserves code blocks with language hints, converts tables and lists, and drops navigation, headers, footers and sidebars. The only network requests go to the URL you pass it and the addresses it redirects to, asked for as a browser opens a page, so docs platforms return the page itself rather than a Markdown copy of it: pure Node + linkedom, no external services, no telemetry.\n\nAgent Bridge (Page2AI browser extension 1.6.0 or later: the Chrome Web Store serves it since 2026-10-26, while Firefox Add-ons still serves 1.5.1, which has no Agent Bridge switch): when the extension is connected, the tool routes through the user's real browser — cookies, JavaScript rendering, extension-quality extraction — so pages behind a sign-in and JS-rendered content are within reach. Without the bridge, a page behind a sign-in or rendered only by JavaScript is out of the tool's reach; pass its HTML directly via the `html` parameter.\n\nA long page comes back in parts of up to 30,000 characters (about 8,000 tokens), the first one listing the page's sections, so an agent reads only what it needs; a page the server cannot read comes back with the next step to take.\n\nCompanion to the Page2AI browser extension (https://github.com/igorsaevets/page2ai-extension), which converts the live page in your own browser, including pages behind a sign-in. Built on the open-source @page2ai/core library.",
   "author": {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@page2ai/mcp",
-  "version": "0.8.0",
+  "version": "0.8.1",
   "mcpName": "io.github.igorsaevets/page2ai-mcp",
   "description": "MCP server that converts any web page URL to clean Markdown for LLM context. Processing is local and SSRF-guarded; no external APIs, no telemetry.",
   "type": "module",
@@ -19,7 +19,7 @@
     "server.json"
   ],
   "engines": {
-    "node": ">=20.0.0"
+    "node": ">=20.18.1"
   },
   "scripts": {
     "build": "tsc -p tsconfig.build.json && node -e \"import('node:fs').then(({chmodSync})=>chmodSync('dist/index.js',0o755))\"",
@@ -35,7 +35,7 @@
   },
   "dependencies": {
     "@modelcontextprotocol/server": "^2.0.0",
-    "@page2ai/core": "^0.3.2",
+    "@page2ai/core": "^0.4.0",
     "ws": "^8.22.0",
     "zod": "^4.2.0"
   },

package/server.json

@@ -8,12 +8,12 @@
     "source": "github"
   },
   "websiteUrl": "https://igorsaevets.github.io/page2ai-docs/mcp/",
-  "version": "0.8.0",
+  "version": "0.8.1",
   "packages": [
     {
       "registryType": "npm",
       "identifier": "@page2ai/mcp",
-      "version": "0.8.0",
+      "version": "0.8.1",
       "transport": {
         "type": "stdio"
       },