Skip to content

This release includes breaking changes for platform teams planning a safe upgrade.

Published 4mo 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

Summary

AI summary

Removed confusing 'Gemini' references from ask_question and added API‑key warnings to deep_research and gemini_query.

Full changelog

Multi-LLM Compatibility Fix

Fixes tool description clarity to help LLMs (especially in OpenCode) choose the correct tools.

Fixed

  • ask_question - Removed "Gemini" references that confused LLMs into thinking API key was needed
    • Now clearly states "Browser-Based • NO API KEY REQUIRED"
    • Added "PREFER THIS TOOL" guidance for notebook queries
  • deep_research - Added prominent warning "⚠️ REQUIRES GEMINI_API_KEY"
    • Added "When NOT to Use" section directing to ask_question
  • gemini_query - Added prominent warning "⚠️ REQUIRES GEMINI_API_KEY"
    • Added "When NOT to Use" section directing to ask_question
  • upload_document - Added note about alternatives that don't need API key

Why This Matters

Some LLMs were incorrectly choosing Gemini API tools over browser-based tools, causing failures when no API key was configured. The updated descriptions now clearly guide LLMs to prefer ask_question for notebook queries.

Installation

npm install @pan-sec/[email protected]

Full Changelog: https://github.com/Pantheon-Security/notebooklm-mcp-secure/compare/v2026.1.9...v2026.1.10

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]