Skip to content

This release adds 1 notable feature for engineering teams evaluating rollout.

Published 5mo MCP Security & Auth
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai automation browser-automation claude google llm
+5 more
mcp model-context-protocol notebooklm research typescript

Affected surfaces

auth

Summary

AI summary

The get_health tool adds a deep_check parameter to verify chat UI accessibility and detect stale sessions.

Full changelog

🔍 Deep Health Check for Chat UI Verification

Catches stale sessions where cookies exist but the NotebookLM chat UI won't actually load.

New Feature

The get_health tool now supports a deep_check parameter:

{ "deep_check": true }

What it does:

  • Actually navigates to a NotebookLM notebook
  • Verifies the chat input UI element loads
  • Returns chat_ui_accessible: true/false
  • Provides actionable troubleshooting if UI is not accessible

Response with deep check:

{
  "authenticated": true,
  "chat_ui_accessible": true,
  "deep_check_notebook": "Fine-tuning Security",
  "troubleshooting_tip": null
}

When UI is stale:

{
  "authenticated": true,
  "chat_ui_accessible": false,
  "troubleshooting_tip": "Chat UI not accessible. Session may be stale. Run re_auth to refresh authentication."
}

Why This Matters

Previously, get_health only checked if auth cookies existed. This missed cases where cookies were valid but the actual NotebookLM session had expired. Now you can verify the UI actually loads before starting important query sessions.


Full Changelog: https://github.com/Pantheon-Security/notebooklm-mcp-secure/compare/v2026.1.0...v2026.1.1

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track Pantheon-Security/notebooklm-mcp-secure

Get notified when new releases ship.

Sign up free

About Pantheon-Security/notebooklm-mcp-secure

Security-hardened NotebookLM MCP with post-quantum encryption (ML-KEM-768), GDPR/SOC2/CSSF compliance, and 14 security layers. Query Google's Gemini-grounded research from Claude and AI agents.

All releases →

Beta — feedback welcome: [email protected]