This release includes breaking changes for platform teams planning a safe upgrade.
✓ No known CVEs patched in this version
Topics
+5 more
Affected surfaces
Summary
AI summaryQuery interactions are now logged to JSONL files with 90‑day retention and quota visibility is added to responses.
Full changelog
What's New
Query Logging 📝
- All Q&A interactions now logged to
~/.local/share/notebooklm-mcp/query_logs/ - JSONL format with 90-day retention
- New
get_query_historytool to search past sessions by session_id, notebook_id, date, or search pattern
Enhanced Quota Visibility 📊
- Every
ask_questionresponse now includesquota_info:queries_remaining,queries_used_today,should_stop,warnings
get_quotatool enhanced with:- Remaining counts for queries and notebooks
should_stopflag (true when ≤5 queries remaining)reset_time(next midnight)- New
sync=trueoption to fetch actual quota from Google's NotebookLM UI
Multi-Session Auth Stability 🔒
- Cross-platform advisory file locking for concurrent sessions
- Atomic quota increment with reload-before-write pattern
- Locked auth state save/load and browser context creation
- Prevents race conditions when running 4-5 concurrent research chats
Rate Limit Detection ⚠️
- Scrapes NotebookLM UI for query usage patterns
- Detects rate limit error messages ("quota exceeded", "try again tomorrow", etc.)
- Automatically marks quota as exhausted when rate limit detected
Environment Variables
NLMCP_QUERY_LOG_ENABLED=true # Enable query logging (default: true)
NLMCP_QUERY_LOG_RETENTION_DAYS=90 # Log retention (default: 90)
NLMCP_LOCK_TIMEOUT_MS=10000 # Lock timeout (default: 10s)
NLMCP_LOCK_STALE_MS=30000 # Stale lock threshold (default: 30s)
Full Changelog: https://github.com/Pantheon-Security/notebooklm-mcp-secure/compare/v1.10.7...v1.10.8
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
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.
Related context
Beta — feedback welcome: [email protected]