Skip to main content
Glama
NotebookLM MCP Server (Security Hardened)

NotebookLM MCP Server (Security Hardened)

NotebookLM MCP Server (Security Hardened)

🏆 The World's Most Advanced NotebookLM MCP Server

Zero-hallucination answers • Gemini Deep Research • 17 Security Layers • Enterprise Compliance

npm CalVer TypeScript MCP Platform Security Post-Quantum Gemini Documents Notebooks Compliance Tests

What's New 2026 • Deep Research • Document API • Create Notebooks • Security • Install

The only NotebookLM MCP with enterprise-grade security, post-quantum encryption, and full Gemini API integration.

Security-hardened fork of PleasePrompto/notebooklm-mcp • Maintained by Pantheon Security

⚡ TL;DR — What You Get

  • 🔍 Query your NotebookLM notebooks — source-grounded, zero-hallucination answers

  • 📚 Create & manage notebooks programmatically — no manual clicking

  • 🎙️ Generate audio overviews — podcast-style summaries of your docs

  • 🎬 Generate video overviews — AI video summaries with 10 visual styles NEW

  • 📊 Extract data tables — structured JSON from notebook sources NEW

  • 🔬 Gemini 3 + Deep Research — latest models with thinking control (optional API) NEW

  • 📄 Document API — upload & query PDFs without browser (optional API)

  • 🔐 17 security layers — post-quantum encryption, audit logs, secrets scanning

  • ✅ Compliance-ready architecture — built to GDPR, SOC2, and CSSF standards (controls implemented; formal certification requires third-party audit)

  • 💡 No API key required — core features work with just browser auth


🚀 What's New in 2026

Latest: v2026.3.1 — All 334 audit issues resolved. 631 tests. Full MCP protocol compliance.

Version

Highlights

v2026.3.1

Security Audit Complete — All 334 issues from the independent audit resolved. Tests: 609 → 631. Code quality: URL resolution deduplicated, handler extraction, non-null assertions eliminated. Test gaps closed: validateNotebookId, error body shape, delete_document confirm guard, sanitized throws, log rotation, rate-limiter memory bound, range clamping.

v2026.3.0

The Security Audit Release — Four parallel AI code reviews (security, protocol, architecture, testing) against 334 issues. All highs and mediums resolved. Tests: 139 → 609 across 50 files (4.4×). Full MCP protocol compliance: structuredContent, isError, transport tags. Schema bounds on all 48 tools. Annotation correctness. Webhook SSRF fix. Audit log integrity (hash chain, concurrent write lock, rotation continuity). Per-page mutex. HandlerContext DI. Cert pinning retracted (claims aligned with implementation).

v2026.2.10

The Hardening Release — 3 new security layers (14→17): secure-by-default auth, exponential backoff lockout, credential isolation. Architecture overhaul: 3,611-line handler split into 9 domain modules, tool registry pattern. Gemini API retry with backoff. Multi-stage Docker build. Token CLI (token show/rotate). 168 tests.

v2026.2.9

performSetup no longer wipes credentials before Chrome opens — prevents auth destruction on failed launch

v2026.2.8

cleanup_data never deletes auth dirs (browser_state/, chrome_profile/) — auth survives all cleanup paths

v2026.2.7

Block headless setup_auth calls; robust auth-now.mjs standalone script with Chrome profile lock handling

v2026.2.6

New add_folder tool for bulk PDF/file uploads; improved tier detection for NotebookLM Plus

v2026.2.5

Fix show_browser silently ignored in setup_auth — browser now reliably opens for auth

v2026.2.4

Auth stability: 7-day state expiry, touchStateFile on validation, block headless re_auth

v2026.2.3

Studio Panel tools restored: Video Overview, Data Table generation re-enabled

v2026.2.1

Standard profile expanded: 14 → 33 tools — notebook creation, audio, source management now visible by default

v2026.2.0

Gemini 3 models (2.5 retiring March 31), Video Overviews, Data Tables, thinking level, structured JSON, SDK 1.41

v2026.1.12

Security hardening: constant-time auth, command injection fix, memory leak fixes, MCP SDK 1.26.0

v2026.1.11

Notebook sync extraction for new Angular UI, NOTEBOOKLM_NO_GEMINI env var

v2026.1.10

Tool description clarity for multi-LLM compatibility

v2026.1.9

Documentation & UX improvements, npm audit fix

v2026.1.8

Major dependency updates (zod 4.x, dotenv 17.x, post-quantum 0.5.4)

v2026.1.7

MCP Protocol UX: tool icons, human-friendly titles, behavior annotations

v2026.1.4

Defense-in-depth path validation, security hardening

v2026.1.1

Deep health checks, chat history extraction, context management

# Quick install
claude mcp add notebooklm -- npx @pan-sec/notebooklm-mcp@latest

Why Choose This MCP?

Capability

Other MCPs

This MCP

Query NotebookLM

✅ Basic

✅ + session management, quotas

Create notebooks programmatically

❌

✅ UNIQUE

Gemini Deep Research

❌

✅ EXCLUSIVE

Document API (no browser)

❌

✅ EXCLUSIVE

Post-quantum encryption

❌

✅ Hybrid PQ at-rest

Enterprise compliance

❌

✅ GDPR/SOC2/CSSF-ready

Video Overview generation

❌

✅ NEW

Data Table extraction

❌

✅ NEW

Chat history extraction

❌

✅

Deep health verification

❌

✅


Related MCP server: Sumulige NotebookLM MCP Server

🔬 Security Audit 2026 — What We Found and Fixed

In April 2026, we commissioned a parallel deep-audit of v2026.2.11 (main @ 2973097) using four specialised AI code reviewers, each focused on a different attack surface: security vulnerabilities, protocol correctness, architecture quality, and testing gaps and edge cases. The four reviewers operated independently so their findings wouldn't influence each other. Together they produced a 334-item master issue list covering protocol correctness, security vulnerabilities, architecture flaws, test gaps, and documentation accuracy. All 334 issues are resolved across v2026.3.0 and v2026.3.1.

Audit by the Numbers

Metric

Before (v2026.2.11)

After (v2026.3.1)

Tests

139

631 across 50 files

Test suites

~6

50

TypeScript errors (tsc --noEmit)

0

0 (maintained)

npm audit vulnerabilities

0

0 (maintained)

MCP protocol compliance

Partial

Full (structuredContent, isError, transport tags)

Audit log integrity

Basic

Hash-chain verified on read

Concurrent write safety

❌

✅ Write-locked

Webhook SSRF

❌

✅ Blocked

What the Four Reviewers Found

Security reviewer: Identified the forceAuth bypass in validateToken() allowing unauthenticated access to filesystem tools; webhook SSRF via unvalidated delivery targets; audit log hash chain not verified on read; concurrent audit writes interleaving entries; auth token salt not persisted (tokens invalidated on restart).

Protocol reviewer: Found 38 tools returning incorrect response shapes (missing structuredContent, wrong isError semantics, transport tags leaking into content); all 48 tools had incorrect or missing readOnlyHint/idempotentHint/destructiveHint annotations; 9 tool schemas lacked numeric bounds, enabling out-of-range inputs.

Architecture reviewer: Flagged the 3,611-line handlers.ts as a maintenance liability; singleton imports throughout domain functions preventing unit testing; the 500-line switch/case dispatch adding O(n) overhead and making tool registration error-prone.

Testing & edge-case reviewer: Found test suite at 139 tests with minimal coverage of security-critical modules; mcp-auth.ts at near-zero coverage; no tests for prompt injection patterns, audit log tampering, or concurrent browser session state; the DSAR handler had an undetected race condition.

Key Fixes

  • 17 security vulnerabilities addressed (auth bypass, SSRF, audit integrity, race conditions, selector injection vectors)

  • MCP protocol fully compliant — all 48 tools return correct structuredContent/isError shapes; annotations accurate; schema bounds enforced

  • Architecture decomposed — handlers.ts split into 9 domain modules with HandlerContext dependency injection; 100% unit-testable without process mocks

  • Test coverage — 15 new security-critical test suites including browser session, auth, prompt injection, audit log, webhook, DSAR, and compliance

  • Claims aligned — certificate pinning removed (implementation was retracted in Day 1 of the audit); PQ encryption scope documented accurately; compliance language uses "controls implemented" not "certified"

Core NotebookLM (No API Key Required)

Tool

Description

ask_question

Query notebooks with source-grounded answers

add_notebook

Add a notebook to your library

list_notebooks

List all notebooks in library

select_notebook

Set active notebook

update_notebook

Update notebook metadata

remove_notebook

Remove from library

create_notebook

Programmatically create new notebooks

batch_create_notebooks

Create multiple notebooks at once

sync_library

Sync library with NotebookLM

list_sources

List sources in a notebook

add_source

Add source to notebook

add_folder

Bulk upload PDFs/files from a local folder to a notebook

remove_source

Remove source from notebook

generate_audio_overview

Create podcast-style audio

get_audio_status

Check audio generation status

download_audio

Download generated audio

generate_video_overview

Create AI video overview (10 styles)

get_video_status

Check video generation status

generate_data_table

Generate structured data table

get_data_table

Extract data table as JSON

list_sessions

List active sessions

close_session

Close a session

reset_session

Reset session history

get_health

Check server & auth status

setup_auth

Initial authentication

re_auth

Re-authenticate

cleanup_data

Clean up local data

get_quota

Check usage quotas

set_quota_tier

Set quota tier

get_query_history

View past queries

get_notebook_chat_history

Extract browser chat history

get_project_info

Get project context

export_library

Export library backup

Gemini API (Optional - Requires GEMINI_API_KEY)

Tool

Description

deep_research

Comprehensive research agent

gemini_query

Fast grounded queries

get_research_status

Check research progress

upload_document

Upload docs to Gemini

query_document

Query uploaded documents

query_chunked_document

Query large documents

list_documents

List uploaded documents

delete_document

Delete uploaded document

Webhooks & Integrations

Tool

Description

configure_webhook

Set up webhook notifications

list_webhooks

List configured webhooks

test_webhook

Test webhook delivery

remove_webhook

Remove a webhook

Enterprise Compliance (16 additional tools)

See Compliance Documentation for full list.


Gemini Deep Research (v1.8.0)

The most powerful research capability for AI agents — now in your MCP toolkit.

v1.8.0 introduces the Gemini Interactions API as a stable, API-based research backend alongside browser automation. This gives your agents access to Google's state-of-the-art Deep Research agent.

Why This Matters

Challenge

Solution

Browser UI changes break automation

Gemini API is stable and versioned

Need comprehensive research but no research agent

Deep Research agent does it for you

Want current information with citations

Google Search grounding built-in

Need reliable, fast queries

API-based = no UI dependencies

New Tools

deep_research — Comprehensive Research Agent

"Research the security implications of post-quantum cryptography adoption in financial services"
  • Runs Google's Deep Research agent (same as Gemini Advanced)

  • Takes 1-5 minutes for comprehensive, web-grounded analysis

  • Returns structured answers with citations and sources

  • Perfect for complex topics requiring multi-source synthesis

gemini_query — Fast Grounded Queries

"What are the latest CVEs for Log4j in 2025?" (with Google Search)
"Calculate the compound interest on $10,000 at 5% over 10 years" (with code execution)
"Summarize this security advisory: [URL]" (with URL context)
  • Google Search grounding — Current information, not just training data

  • Code execution — Run calculations, data analysis

  • URL context — Analyze web pages on demand

  • Models: gemini-3-flash-preview (default), gemini-3-pro-preview (powerful), gemini-2.5-flash (legacy)

get_research_status — Background Task Monitoring

Run deep research in the background and check progress:

"Start researching [topic] in the background"
... continue other work ...
"Check research status for interaction_abc123"

Hybrid Architecture

┌──────────────────────────────────────────────────────────────────────────────┐
│                      NotebookLM MCP Server v2026.3.x                         │
├──────────────────────────────────────────────────────────────────────────────┤
│                                                                              │
│  ┌────────────────────────────────┐    ┌──────────────────────────────────┐  │
│  │      BROWSER AUTOMATION        │    │          GEMINI API              │  │
│  │    ✅ NO API KEY NEEDED        │    │    ⚡ OPTIONAL - needs API key   │  │
│  ├────────────────────────────────┤    ├──────────────────────────────────┤  │
│  │                                │    │                                  │  │
│  │  QUERY                         │    │  RESEARCH                        │  │
│  │  • ask_question                │    │  • deep_research                 │  │
│  │  • get_notebook_chat_history   │    │  • gemini_query                  │  │
│  │                                │    │  • get_research_status           │  │
│  │  CREATE & MANAGE               │    │                                  │  │
│  │  • create_notebook             │    │  DOCUMENTS                       │  │
│  │  • batch_create_notebooks      │    │  • upload_document               │  │
│  │  • manage_sources              │    │  • query_document                │  │
│  │  • generate_audio              │    │  • query_chunked_document        │  │
│  │  • generate_video_overview     │    │  • list/delete_document          │  │
│  │  • generate_data_table         │    │                                  │  │
│  │  • sync_notebook               │    │                                  │  │
│  │                                │    │                                  │  │
│  │  HEALTH & SESSIONS     v2026   │    │                                  │  │
│  │  • get_health (deep_check)     │    │  Fast API • 48h retention        │  │
│  │  • get_query_history           │    │  Auto-chunking for large PDFs    │  │
│  └────────────────────────────────┘    └──────────────────────────────────┘  │
│                                                                              │
│                      ┌─────────────────────────────────┐                     │
│                      │       17 SECURITY LAYERS        │                     │
│                      │   Post-Quantum • Audit Logs     │                     │
│                      │   Secrets Scan • Memory Wipe    │                     │
│                      │  GDPR • SOC2 • CSSF Ready*      │                     │
│                      └─────────────────────────────────┘                     │
└──────────────────────────────────────────────────────────────────────────────┘

💡 Gemini API is completely optional! All core NotebookLM features (ask_question, notebooks, sessions, audio) work via browser automation with no API key required. The Gemini tools below are bonus features for users who want direct API access.

Gemini Configuration (Optional)

# Only required if you want Gemini API features (deep_research, gemini_query, upload_document)
GEMINI_API_KEY=your-api-key          # Get from https://aistudio.google.com/apikey

# Optional settings
GEMINI_DEFAULT_MODEL=gemini-3-flash-preview  # Default model (was gemini-2.5-flash)
GEMINI_DEEP_RESEARCH_ENABLED=true            # Enable Deep Research
GEMINI_TIMEOUT_MS=30000                      # API timeout

When to Use Which

Task

Best Tool

Why

Questions about YOUR documents

ask_question

Grounded on your uploaded sources

Comprehensive topic research

deep_research

Multi-source synthesis with citations

Current events / recent info

gemini_query + google_search

Live web data

Code calculations

gemini_query + code_execution

Reliable computation

Analyze a webpage

gemini_query + url_context

Direct page analysis

Quick PDF/document analysis

upload_document + query_document

Fast API, no browser (NEW!)


📄 Document API (v1.9.0)

Upload and query documents directly via Gemini API — no browser automation needed.

v1.9.0 introduces the Gemini Files API for fast, reliable document analysis. Upload PDFs, analyze them instantly, and delete when done.

Why This Matters

Feature

Browser Mode

Document API

Speed

Seconds

Milliseconds

Reliability

UI-dependent

API-stable

File Support

Via NotebookLM

50MB PDFs, 1000 pages

Retention

Permanent

48 hours

Setup

Auth + cookies

Just API key

New Tools

upload_document — Fast Document Upload

Upload any document to Gemini for instant querying:

Upload /path/to/research-paper.pdf
  • Supported: PDF (50MB, 1000 pages), TXT, MD, HTML, CSV, JSON, DOCX, images, audio, video

  • 48-hour retention — files auto-expire, or delete manually

  • Returns a file ID for querying

query_document — Ask Questions About Documents

"What are the main findings in this research paper?"
"Summarize section 3 of the document"
"Extract all statistics mentioned in the PDF"
  • Full document understanding (text, tables, charts, diagrams)

  • Multi-document queries (compare multiple files)

  • Fast API response (no browser wait)

list_documents — See All Uploaded Files

List all my uploaded documents

Shows file names, sizes, MIME types, and expiration times.

delete_document — Clean Up Sensitive Files

Delete file xyz123

Immediately remove files (don't wait for 48h expiration).

Workflow Example

1. upload_document("/research/paper.pdf")
   → Returns: files/abc123

2. query_document("files/abc123", "What methodology was used?")
   → Returns: "The paper uses a mixed-methods approach combining..."

3. query_document("files/abc123", "List all cited authors")
   → Returns: "Smith et al. (2024), Johnson (2023)..."

4. delete_document("files/abc123")
   → File removed

Auto-Chunking for Large PDFs (v1.10.0)

No file size limits — PDFs of any size are automatically handled.

When you upload a PDF that exceeds Gemini's limits (50MB or 1000 pages), the system automatically:

  1. Detects the oversized PDF

  2. Splits it into optimal chunks (500 pages each)

  3. Uploads all chunks in parallel

  4. Returns chunk metadata for querying

upload_document("/research/massive-2000-page-report.pdf")

→ Returns:
{
  "wasChunked": true,
  "totalPages": 2000,
  "chunks": [
    { "fileName": "files/abc1", "pageStart": 1, "pageEnd": 500 },
    { "fileName": "files/abc2", "pageStart": 501, "pageEnd": 1000 },
    { "fileName": "files/abc3", "pageStart": 1001, "pageEnd": 1500 },
    { "fileName": "files/abc4", "pageStart": 1501, "pageEnd": 2000 }
  ],
  "allFileNames": ["files/abc1", "files/abc2", "files/abc3", "files/abc4"]
}

query_chunked_document — Query All Chunks at Once

For chunked documents, use this tool to query all parts and get an aggregated answer:

query_chunked_document(
  file_names: ["files/abc1", "files/abc2", "files/abc3", "files/abc4"],
  query: "What are the key recommendations in this report?"
)

→ Queries each chunk, then synthesizes a unified answer

When to Use Document API vs NotebookLM

Scenario

Use

Quick one-off document analysis

Document API — fast, no setup

Building a permanent knowledge base

NotebookLM — permanent storage

Analyzing sensitive documents

Document API — 48h auto-delete

Multi-source research over time

NotebookLM — organized notebooks

CI/CD pipeline document processing

Document API — API-native

Large PDFs (1000+ pages)

Document API — auto-chunking


Programmatic Notebook Creation (v1.7.0+)

Create NotebookLM notebooks entirely from code — no manual clicks required.

Most MCP servers can only read from NotebookLM. This one can create notebooks, add sources, and generate audio — all programmatically.

create_notebook — Build Notebooks Instantly

Create a complete notebook with multiple sources in one command:

{
  "name": "Security Research 2025",
  "sources": [
    { "type": "url", "value": "https://owasp.org/Top10" },
    { "type": "file", "value": "/path/to/security-report.pdf" },
    { "type": "text", "value": "Custom analysis notes...", "title": "My Notes" }
  ],
  "description": "OWASP security best practices",
  "topics": ["security", "owasp", "vulnerabilities"]
}

Supported source types:

  • URL — Web pages, documentation, articles

  • File — PDF, DOCX, TXT, and more

  • Text — Raw text, code snippets, notes

batch_create_notebooks — Scale Up

Create up to 10 notebooks in a single operation:

{
  "notebooks": [
    { "name": "React Docs", "sources": [{ "type": "url", "value": "https://react.dev/reference" }] },
    { "name": "Node.js API", "sources": [{ "type": "url", "value": "https://nodejs.org/api/" }] },
    { "name": "TypeScript Handbook", "sources": [{ "type": "url", "value": "https://www.typescriptlang.org/docs/" }] }
  ]
}

Perfect for:

  • Setting up project documentation libraries

  • Onboarding new team members with curated knowledge bases

  • Creating topic-specific research notebooks in bulk

manage_sources — Dynamic Source Management

Add or remove sources from existing notebooks:

{
  "notebook_id": "abc123",
  "action": "add",
  "sources": [{ "type": "url", "value": "https://new-documentation.com" }]
}

generate_audio — Audio Overview Creation

Generate NotebookLM's famous "Audio Overview" podcasts programmatically:

"Generate an audio overview for my Security Research notebook"

sync_notebook — Keep Sources Updated

Sync notebook sources from a local directory:

{
  "notebook_id": "abc123",
  "directory": "/path/to/docs",
  "patterns": ["*.md", "*.pdf"]
}

Why This Matters

Traditional Workflow

With This MCP

Manually create notebook in browser

create_notebook → done

Click "Add source" for each document

Batch add in single command

Navigate UI to generate audio

generate_audio → podcast ready

Update sources by hand

sync_notebook from local files

Your agent can now build entire knowledge bases autonomously.


🎬 Video Overviews & Data Tables (v2026.2.0)

Generate AI-powered visual summaries and extract structured data from any notebook — all programmatically.

NotebookLM's Studio panel now offers Video Overviews and Data Tables alongside Audio Overviews. This release brings full automation for both.

generate_video_overview — AI Video Summaries

Generate visual video overviews of your notebook content with 10 visual styles:

Style

Description

auto-select

Let NotebookLM choose the best style (default)

classic

Clean presentation style

whiteboard

Hand-drawn whiteboard aesthetic

kawaii

Cute illustrated style

anime

Anime-inspired visuals

watercolour

Watercolour painting style

retro-print

Retro print aesthetic

heritage

Traditional heritage style

paper-craft

Paper-craft visual style

custom

Custom visual style

Two formats:

  • Explainer — Full explanation (5-15 min)

  • Brief — Quick summary (1-3 min)

"Generate a kawaii-style brief video overview for my Security Research notebook"

get_video_status — Check Generation Progress

Video generation takes 3-10 minutes. Check progress:

"Check video status for my Security Research notebook"
→ { "status": "generating", "progress": 0 }
→ { "status": "ready" }

generate_data_table — Structured Data Extraction

Generate a structured table from your notebook sources. NotebookLM extracts key information into rows and columns:

"Generate a data table for my research notebook"

get_data_table — Extract Table as JSON

Extract the generated table as structured JSON for processing:

"Get the data table from my research notebook"
→ {
    "headers": ["Title", "Year", "Key Finding", "Methodology", ...],
    "rows": [["Paper A", "2025", "Finding X", "Survey", ...], ...],
    "totalRows": 27,
    "totalColumns": 7
  }

When to Use Which Studio Feature

Task

Best Tool

Why

Podcast-style audio summary

generate_audio_overview

Shareable audio content

Visual presentation of research

generate_video_overview

Engaging video summary

Structured data for analysis

generate_data_table + get_data_table

Machine-readable JSON

Quick status check

get_audio_status / get_video_status

Non-blocking progress


📊 Query History & Chat Extraction (v2026.1.0)

Track your research and recover conversations from NotebookLM notebooks.

get_query_history — Review Past Research (v1.10.8)

All queries made through the MCP are automatically logged for review:

"Show me my recent NotebookLM queries"
"Find queries about security from last week"
"What did I ask the fine-tuning notebook?"
  • Automatic logging — every Q&A pair saved with metadata

  • Search — find specific topics across all queries

  • Filter — by notebook, session, or date

  • Quota tracking — see query counts and timing

get_notebook_chat_history — Extract Browser Conversations (v2026.1.0)

Extract conversation history directly from a NotebookLM notebook's chat UI with context management to avoid overwhelming your AI context window:

Quick audit (preview mode):

{ "notebook_id": "my-research", "preview_only": true }

Returns message counts without content — test the water before extracting.

Export to file (avoids context overflow):

{ "notebook_id": "my-research", "output_file": "/tmp/chat-history.json" }

Dumps full history to disk instead of returning to context.

Paginate through history:

{ "notebook_id": "my-research", "limit": 20, "offset": 0 }
{ "notebook_id": "my-research", "limit": 20, "offset": 20 }

Page through large histories without loading everything at once.

Returns:

{
  "notebook_url": "https://notebooklm.google.com/notebook/xxx",
  "notebook_name": "My Research",
  "total_messages": 150,
  "returned_messages": 40,
  "user_messages": 75,
  "assistant_messages": 75,
  "offset": 0,
  "has_more": true,
  "messages": [...]
}

Use cases:

  • Recover conversations made directly in the NotebookLM browser (not tracked by MCP)

  • Audit research — see what queries were made in a notebook

  • Resume context — pick up where a previous session left off

  • Quota reconciliation — understand why quota seems off


Why This Fork?

The original NotebookLM MCP is excellent for productivity — but MCP servers handle sensitive data:

  • Browser sessions with Google authentication

  • Cookies and tokens stored on disk

  • Query history that may contain proprietary information

This fork adds 17 security hardening layers to protect that data.


Security Features

Layer

Feature

Protection

🔐

Post-Quantum Encryption

ML-KEM-768 + ChaCha20-Poly1305 hybrid (local at-rest)

🔍

Secrets Scanning

Detects 30+ credential patterns (AWS, GitHub, Slack...)

🧹

Memory Scrubbing

Zeros sensitive data after use

📝

Audit Logging

Tamper-evident logs with hash chains

⏱️

Session Timeout

8h hard limit + 30m inactivity auto-logout

🎫

MCP Authentication

Token-based auth with brute-force lockout

🛡️

Response Validation

Detects prompt injection attempts

✅

Input Validation

URL whitelisting, sanitization

🚦

Rate Limiting

Per-session request throttling

🙈

Log Sanitization

Credentials masked in all output

🐍

MEDUSA Integration

Automated security scanning

🖥️

Cross-Platform

Native support for Linux, macOS, Windows

🔒

Secure-by-Default Auth

Auth ON without configuration, explicit opt-out required

📈

Exponential Backoff

Lockout escalation: 5min → 15min → 45min → 4hr cap

🗝️

Credential Isolation

SecureCredential TTL + env var scrubbing from process.env

Post-Quantum Primitives (Local At-Rest)

Encryption of secrets on disk uses hybrid post-quantum primitives:

ML-KEM-768 (Kyber) + ChaCha20-Poly1305
  • ML-KEM-768: NIST-standardized post-quantum key encapsulation

  • ChaCha20-Poly1305: Modern stream cipher (immune to timing attacks)

Scope, honestly: this is local at-rest encryption. Both keys live on the same machine — the PQ secret key is wrapped with a classical key derived from a machine-bound secret, not held by a remote recipient. This protects against offline theft of individual encrypted files, not against Harvest-Now-Decrypt-Later attacks (those require a remote PQ recipient holding the unwrap key).

Cross-Platform Support

Full native support for all major operating systems:

Platform

File Permissions

Data Directory

Linux

Unix chmod (0o600/0o700)

~/.local/share/notebooklm-mcp/

macOS

Unix chmod (0o600/0o700)

~/Library/Application Support/notebooklm-mcp/

Windows

ACLs via icacls (current user only)

%LOCALAPPDATA%\notebooklm-mcp\

All sensitive files (encryption keys, auth tokens, audit logs) are automatically protected with owner-only permissions on every platform.

Enterprise Compliance-Ready Architecture (v1.6.0+)

Built to the standards required for regulated industries. All code-level technical controls are implemented — full compliance also requires organizational process controls (policies, training, vendor management). Formal certification (SOC2 Type II report, GDPR registration, CSSF submission) requires a third-party audit engagement.

Regulation

Controls Implemented

GDPR

Consent management, DSAR handling, right to erasure, data portability

SOC2 Type II

Hash-chained audit logs, incident response, availability monitoring

CSSF

7-year retention, SIEM integration, policy documentation

Compliance Tools (16 MCP tools)

compliance_dashboard    - Real-time compliance status
compliance_report       - Generate audit reports (JSON/CSV/HTML)
compliance_evidence     - Collect evidence packages
grant_consent          - Record user consent
submit_dsar            - Handle data subject requests
request_erasure        - Right to be forgotten
export_user_data       - Data portability export
create_incident        - Security incident management
...and 8 more

See COMPLIANCE-SPEC.md for full documentation.


Installation

What Works Out of the Box (No API Key)

All core NotebookLM features work immediately with just browser authentication:

Feature

Tool

Description

🔍 Query notebooks

ask_question

Get source-grounded answers from your documents

📚 Manage library

add_notebook, list_notebooks, etc.

Organize your notebook collection

🎙️ Audio overviews

generate_audio_overview

Create podcast-style summaries

🎬 Video overviews

generate_video_overview

AI video summaries with 10 visual styles NEW

📊 Data tables

generate_data_table, get_data_table

Structured data extraction as JSON NEW

📝 Create notebooks

create_notebook

Programmatically create new notebooks

🔄 Session management

list_sessions, reset_session

Manage conversation context

📊 Chat history

get_notebook_chat_history

Extract past conversations

❤️ Health checks

get_health

Verify authentication status

Optional: Add GEMINI_API_KEY for bonus features like deep_research, gemini_query, and upload_document.

For repeatable authenticated validation, see the Authenticated Testing Runbook.


Claude Code

claude mcp add notebooklm -- npx @pan-sec/notebooklm-mcp@latest
claude mcp add notebooklm \
  --env NLMCP_AUTH_ENABLED=true \
  --env NLMCP_AUTH_TOKEN=$(openssl rand -base64 32) \
  --env GEMINI_API_KEY=your-gemini-api-key \
  -- npx @pan-sec/notebooklm-mcp@latest

Codex

codex mcp add notebooklm -- npx @pan-sec/notebooklm-mcp@latest

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "notebooklm": {
      "command": "npx",
      "args": ["-y", "@pan-sec/notebooklm-mcp@latest"],
      "env": {
        "NLMCP_AUTH_ENABLED": "true",
        "NLMCP_AUTH_TOKEN": "your-secure-token",
        "GEMINI_API_KEY": "your-gemini-api-key"
      }
    }
  }
}

Add to ~/.gemini/antigravity/mcp_config.json (macOS/Linux) or %USERPROFILE%\.gemini\antigravity\mcp_config.json (Windows):

{
  "mcpServers": {
    "notebooklm": {
      "command": "npx",
      "args": ["-y", "@pan-sec/notebooklm-mcp@latest"]
    }
  }
}

With optional env vars:

{
  "mcpServers": {
    "notebooklm": {
      "command": "npx",
      "args": ["-y", "@pan-sec/notebooklm-mcp@latest"],
      "env": {
        "GEMINI_API_KEY": "your-gemini-api-key"
      }
    }
  }
}

Note: Antigravity does NOT support ${workspaceFolder} variables. Use absolute paths.

Add to ~/.config/opencode/opencode.json (global) or opencode.json in project root:

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "notebooklm": {
      "type": "local",
      "command": ["npx", "-y", "@pan-sec/notebooklm-mcp@latest"],
      "enabled": true,
      "environment": {
        "GEMINI_API_KEY": "your-gemini-api-key"
      }
    }
  }
}

Note: OpenCode uses "mcp" (not "mcpServers") and "command" is an array.

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "notebooklm": {
      "command": "npx",
      "args": ["-y", "@pan-sec/notebooklm-mcp@latest"],
      "env": {
        "GEMINI_API_KEY": "your-gemini-api-key"
      }
    }
  }
}

Add to your VS Code settings.json:

{
  "mcp": {
    "servers": {
      "notebooklm": {
        "command": "npx",
        "args": ["-y", "@pan-sec/notebooklm-mcp@latest"],
        "env": {
          "GEMINI_API_KEY": "your-gemini-api-key"
        }
      }
    }
  }
}

Most MCP clients use this standard format:

{
  "mcpServers": {
    "notebooklm": {
      "command": "npx",
      "args": ["-y", "@pan-sec/notebooklm-mcp@latest"],
      "env": {
        "GEMINI_API_KEY": "your-gemini-api-key"
      }
    }
  }
}

Common config locations:

Client

Config File

Claude Desktop

~/.config/claude/claude_desktop_config.json

Cursor

~/.cursor/mcp.json

Antigravity

~/.gemini/antigravity/mcp_config.json

OpenCode

~/.config/opencode/opencode.json

Windsurf

~/.codeium/windsurf/mcp_config.json


Quick Start

1. Install (see above)

2. Authenticate

"Log me in to NotebookLM"

Chrome opens → sign in with Google

3. Add your notebook

Go to notebooklm.google.com → Create notebook → Upload docs → Share link

4. Use it

"Research [topic] using this NotebookLM: [link]"

5. Try Deep Research (NEW!)

"Use deep research to investigate [complex topic]"

Complete Tool Reference

Research Tools

Tool

Description

Backend

ask_question

Query your NotebookLM notebooks

Browser

deep_research

Comprehensive research with citations

Gemini API

gemini_query

Fast queries with grounding tools

Gemini API

get_research_status

Check background research progress

Gemini API

Notebook Management

Tool

Description

add_notebook

Add notebook to library

list_notebooks

List all notebooks

get_notebook

Get notebook details

update_notebook

Update notebook metadata

remove_notebook

Remove from library

select_notebook

Set active notebook

search_notebooks

Search by query

Source Management (v1.7.0+)

Tool

Description

manage_sources

Add/remove/list sources

generate_audio

Create Audio Overview

sync_notebook

Sync sources from local files

Studio Features (v2026.2.0)

Tool

Description

generate_video_overview

Create AI video overview (10 visual styles, 2 formats)

get_video_status

Check video generation progress

generate_data_table

Generate structured data table from sources

get_data_table

Extract data table as JSON (headers + rows)

Session & System

Tool

Description

list_sessions

View active sessions

close_session

Close a session

reset_session

Reset session chat

get_health

Server health check (with deep_check for UI verification)

get_query_history

Review past queries with search/filter

get_notebook_chat_history

Extract browser conversations (pagination, file export)

setup_auth

Initial authentication

re_auth

Re-authenticate

cleanup_data

Deep cleanup utility

get_library_stats

Library statistics

get_quota

Check usage limits and remaining quota

Compliance (v1.6.0+)

16 compliance tools for GDPR, SOC2, and CSSF requirements.


What Gets Protected

Data

Protection

Browser cookies

Post-quantum encrypted at rest

Session tokens

Auto-expire + memory scrubbing

Query history

Audit logged with tamper detection

Google connection

TLS with response validation

Log output

Credentials auto-redacted

API responses

Scanned for leaked secrets

Gemini API key

Secure memory handling


Configuration

All security features are enabled by default. Override via environment variables:

# Authentication
NLMCP_AUTH_ENABLED=true
NLMCP_AUTH_TOKEN=your-secret-token

# Gemini API (v1.8.0+)
GEMINI_API_KEY=your-api-key
GEMINI_DEFAULT_MODEL=gemini-3-flash-preview  # Default (was gemini-2.5-flash)
GEMINI_DEEP_RESEARCH_ENABLED=true
GEMINI_TIMEOUT_MS=30000
NOTEBOOKLM_NO_GEMINI=false       # Set to true to disable all Gemini tools

# Tool Profiles
NOTEBOOKLM_PROFILE=standard      # minimal (5 tools) | standard (33 tools) | full (all 47)
NOTEBOOKLM_DISABLED_TOOLS=       # Comma-separated list of tools to hide

# Encryption
NLMCP_USE_POST_QUANTUM=true
NLMCP_ENCRYPTION_KEY=base64-32-bytes  # Optional custom key

# Session Limits
NLMCP_SESSION_MAX_LIFETIME=28800  # 8 hours
NLMCP_SESSION_INACTIVITY=1800     # 30 minutes

# Secrets Scanning
NLMCP_SECRETS_SCANNING=true
NLMCP_SECRETS_BLOCK=false         # Block on detection
NLMCP_SECRETS_REDACT=true         # Auto-redact

# Audit Logging
NLMCP_AUDIT_ENABLED=true

# Multi-Session Support (v2026.1.2+)
NOTEBOOK_PROFILE_STRATEGY=isolated  # isolated|single|auto
NOTEBOOK_CLONE_PROFILE=true         # Clone auth from base profile

Multi-Session Mode

Run multiple Claude Code sessions simultaneously with isolated browser profiles:

# Add to ~/.bashrc or ~/.zshrc
export NOTEBOOK_PROFILE_STRATEGY=isolated
export NOTEBOOK_CLONE_PROFILE=true

Variable

Values

Description

NOTEBOOK_PROFILE_STRATEGY

single, auto, isolated

isolated = separate profile per session

NOTEBOOK_CLONE_PROFILE

true, false

Clone authenticated base profile into isolated instances

How it works:

  • Each session gets its own Chrome profile (no lock conflicts)

  • Isolated profiles clone from the authenticated base profile

  • Auth coordination ensures cloning waits for any in-progress authentication

See SECURITY.md for complete configuration reference.


Security Scanning

Run MEDUSA security scanner:

npm run security-scan

Or integrate in CI/CD:

- name: Security Scan
  run: npx @pan-sec/notebooklm-mcp && npm run security-scan

Comparison

vs Other NotebookLM MCPs

Feature

Others

@pan-sec/notebooklm-mcp

Zero-hallucination Q&A

✅

✅

Library management

✅

✅

Create Notebooks Programmatically

❌

✅ EXCLUSIVE

Batch Create (10 notebooks)

❌

✅ EXCLUSIVE

Gemini Deep Research

❌

✅ EXCLUSIVE

Document API (no browser)

❌

✅ EXCLUSIVE

Auto-chunking (1000+ page PDFs)

❌

✅ EXCLUSIVE

Chat History Extraction

❌

✅ NEW

Deep Health Verification

❌

✅ NEW

Query History & Search

❌

✅

Quota Management

❌

✅

Source Management (add/remove)

❌

✅

Audio Overview Generation

❌

✅

Video Overview Generation (10 styles)

❌

✅ NEW

Data Table Extraction (JSON)

❌

✅ NEW

Gemini 3 + Thinking Control

❌

✅ NEW

Structured JSON Output

❌

✅ NEW

Sync from Local Directories

❌

✅

Security & Compliance (Unique to This Fork)

Feature

Others

@pan-sec/notebooklm-mcp

Cross-platform (Linux/macOS/Windows)

⚠️ Partial

✅ Full

Post-quantum encryption

❌

✅ ML-KEM-768 + ChaCha20 (local at-rest)

Secrets scanning

❌

✅ 30+ patterns

Memory scrubbing

❌

✅ Zero-on-free

Audit logging

❌

✅ Hash-chained

MCP authentication

❌

✅ Token + lockout

Prompt injection detection

❌

✅ Response validation

GDPR Compliance

❌

✅ Controls implemented*

SOC2 Type II

❌

✅ Controls implemented*

CSSF (Luxembourg)

❌

✅ Controls implemented*

* Compliance-ready: code-level technical controls are implemented. Full compliance also requires organizational process controls and formal certification via third-party audit.

Bottom line: If you need more than basic queries, or care about security, there's only one choice.


Version History

Version

Highlights

v2026.3.1

✅ Security Audit Complete — All 334 issues resolved. Tests 609→631. Code quality + test gap phase.

v2026.3.0

🔬 Security Audit Release — 334-issue independent audit. Tests 139→609 (50 files). Full MCP protocol compliance. Webhook SSRF fix. Audit log hash-chain verified on read. Per-page mutex. HandlerContext DI. Cert pinning retracted.

v2026.2.9

🔐 performSetup no longer destroys credentials before Chrome opens — last root cause of auth loop fixed

v2026.2.8

🛡️ cleanup_data excludes browser_state/ and chrome_profile/ from all deletion paths — auth survives cleanup

v2026.2.7

🚫 Block headless setup_auth; auth-now.mjs standalone script handles Chrome profile locks and silent save failures

v2026.2.6

📁 New add_folder tool — bulk upload PDFs/files to a notebook with progress, dry_run, and auto-split support

v2026.2.5

🔧 Fix: show_browser now correctly passed to performSetup — browser reliably opens for auth

v2026.2.4

🔑 Auth stability: 7-day state expiry (was 24h), touchStateFile resets clock on each validation, headless re_auth blocked

v2026.2.3

🎬 Studio Panel tools restored — Video Overview generation and Data Table tools re-enabled after UI update

v2026.2.1

🔧 Standard profile expanded: 14 → 33 tools — all key features now visible by default

v2026.2.0

🚀 Gemini 3 models (2.5 retiring March 31), Video Overviews (10 styles), Data Table extraction (JSON), thinking level control, structured JSON output, SDK 1.41

v2026.1.12

🔒 Security hardening — timing attack fix, command injection fix, 6 memory leak fixes, MCP SDK 1.26.0

v2026.1.11

🔄 Notebook sync extraction for Angular UI, NOTEBOOKLM_NO_GEMINI env var

v2026.1.10

📝 Tool descriptions clarified for multi-LLM compatibility (OpenCode fix)

v2026.1.9

📄 Documentation & UX improvements, npm audit fix

v2026.1.8

📦 Major dependency updates (zod 4.x, dotenv 17.x, post-quantum 0.5.4)

v2026.1.7

🎨 MCP Protocol UX — tool icons, titles, behavior annotations

v2026.1.4

🛡️ Defense-in-depth path validation, security hardening

v2026.1.2

🔗 Multi-session auth coordination — lock system for concurrent sessions

v2026.1.1

🔍 Deep health check — verifies NotebookLM chat UI actually loads

v2026.1.0

📊 Chat history extraction with context management, CalVer versioning

v1.10.8

Query history logging, quota tracking

v1.10.0

Auto-chunking for large PDFs (1000+ pages)

v1.9.0

Document API: upload, query, delete via Gemini Files API

v1.8.0

Gemini Deep Research, Query with Grounding, Background Tasks

v1.7.0

Programmatic notebook creation, batch operations, audio generation

v1.6.0

Enterprise compliance: GDPR, SOC2 Type II, CSSF

v1.5.0

Cross-platform support (Windows ACLs, macOS, Linux)

v1.4.0

Post-quantum encryption, secrets scanning


Reporting Vulnerabilities

Found a security issue? Do not open a public GitHub issue.

Email: support@pantheonsecurity.io


Credits

License

MIT — Same as original.


Security hardened with 🔒 by Pantheon Security

Powered by Google Gemini 3 🚀

Full Security Documentation • Compliance Guide • Report Vulnerability

Available Tools

31 tools
add_notebookAdd NotebookA
Idempotent

PERMISSION REQUIRED — Only when user explicitly asks to add a notebook.

Conversation Workflow (Mandatory)

When the user says: "I have a NotebookLM with X"

  1. Ask URL: "What is the NotebookLM URL?"

  2. Ask content: "What knowledge is inside?" (1–2 sentences)

  3. Ask topics: "Which topics does it cover?" (3–5)

  4. Ask use cases: "When should we consult it?"

  5. Propose metadata and confirm:

    • Name: [suggested]

    • Description: [from user]

    • Topics: [list]

    • Use cases: [list] "Add it to your library now?"

  6. Only after explicit "Yes" → call this tool

Rules

  • Do not add without user permission

  • Do not guess metadata — ask concisely

  • Confirm summary before calling the tool

Example

User: "I have a notebook with n8n docs" You: Ask URL → content → topics → use cases; propose summary User: "Yes" You: Call add_notebook

Visit https://notebooklm.google/ → Login (free: 100 notebooks, 50 sources each, 500k words, 50 daily queries)

  1. Click "+ New" (top right) → Upload sources (docs, knowledge)

  2. Click "Share" (top right) → Select "Anyone with the link"

  3. Click "Copy link" (bottom left) → Give this link to Claude

(Upgraded: Google AI Pro/Ultra gives 5x higher limits)

Inputs: url (required), name (required), description (required), topics (required), +3 more.

add_sourceAdd SourceA
Idempotent

Add a source to an existing NotebookLM notebook.

Source Types

  • url: Web page URL

  • text: Text content (paste)

  • file: Local file path (PDF, DOCX, TXT)

Example

{
  "notebook_id": "my-notebook",
  "source": {
    "type": "url",
    "value": "https://docs.example.com/api"
  }
}

Inputs: source (required), notebook_id, notebook_url.

ask_questionAsk NotebookLMA
Read-only

NotebookLM Research (Browser-Based • NO API KEY REQUIRED)

IMPORTANT: This tool uses browser automation - NO GEMINI_API_KEY needed!

No Active Notebook

  • Visit https://notebooklm.google to create a notebook and get a share link

  • Use add_notebook to add it to your library (explains how to get the link)

  • Use list_notebooks to show available sources

  • Use select_notebook to set one active

Auth tip: If login is required, use the prompt 'notebooklm.auth-setup' and then verify with the 'get_health' tool.

Tip: Tell the user you can manage NotebookLM library and ask which notebook to use for the current task.

Inputs: question (required), session_id, notebook_id, notebook_url, +2 more.

batch_create_notebooksBatch CreateA

Create multiple NotebookLM notebooks in one operation.

What This Tool Does

  • Creates up to 10 notebooks in a single batch operation

  • Reports progress for each notebook

  • Optionally continues on error or stops on first failure

  • Auto-adds created notebooks to your library

Example Usage

{
  "notebooks": [
    {
      "name": "React Documentation",
      "sources": [
        { "type": "url", "value": "https://react.dev/reference" }
      ],
      "topics": ["react", "frontend"]
    },
    {
      "name": "Node.js API",
      "sources": [
        { "type": "url", "value": "https://nodejs.org/api/" }
      ],
      "topics": ["nodejs", "backend"]
    }
  ],
  "stop_on_error": false
}

Limits

  • Maximum 10 notebooks per batch

  • Each notebook follows individual source limits (50-600 based on tier)

  • Delays between notebooks to avoid rate limiting

Returns

Summary with:

  • total: Number of notebooks attempted

  • succeeded: Successfully created count

  • failed: Failed count

  • results: Array of individual results

Inputs: notebooks (required), stop_on_error, show_browser.

cleanup_dataCleanup DataA
DestructiveIdempotent

ULTRATHINK Deep Cleanup - Scans entire system for ALL NotebookLM MCP data files across 8 categories. Always runs in deep mode, shows categorized preview before deletion.

⚠️ CRITICAL: Close ALL Chrome/Chromium instances BEFORE running this tool! Open browsers can prevent cleanup and cause issues.

Categories scanned:

  1. Legacy Installation (notebooklm-mcp-nodejs) - Old paths with -nodejs suffix

  2. Current Installation (notebooklm-mcp) - Active data, browser profiles, library

  3. NPM/NPX Cache - Cached installations from npx

  4. Claude CLI MCP Logs - MCP server logs from Claude CLI

  5. Temporary Backups - Backup directories in system temp

  6. Claude Projects Cache - Project-specific cache (optional)

  7. Editor Logs (Cursor/VSCode) - MCP logs from code editors (optional)

  8. Trash Files - Deleted notebooklm files in system trash (optional)

Works cross-platform (Linux, Windows, macOS). Safe by design: shows detailed preview before deletion, requires explicit confirmation.

LIBRARY PRESERVATION: Set preserve_library=true to keep your notebook library.json file while cleaning everything else.

RECOMMENDED WORKFLOW for fresh start:

  1. Ask user to close ALL Chrome/Chromium instances

  2. Run cleanup_data(confirm=false, preserve_library=true) to preview

  3. Run cleanup_data(confirm=true, preserve_library=true) to execute

  4. Run setup_auth or re_auth for fresh browser session

Use cases: Clean reinstall, troubleshooting auth issues, removing all traces before uninstall, cleaning old browser sessions and installation data.

Inputs: confirm (required), preserve_library.

close_sessionClose SessionA
DestructiveIdempotent

Close a specific session by session ID. Ask before closing if the user might still need it.

Inputs: session_id (required).

create_notebookCreate NotebookA

Create a new NotebookLM notebook with sources programmatically.

What This Tool Does

  • Creates a NEW notebook in your NotebookLM account

  • Uploads sources (URLs, text, files) to the notebook

  • Returns the notebook URL for immediate use

  • Optionally adds to your local library

Supported Source Types

  • url: Web page URL (documentation, articles, etc.)

  • text: Raw text content (code, notes, etc.)

  • file: Local file path (PDF, DOCX, TXT)

Example Usage

Create a notebook from API documentation:

{
  "name": "React Docs",
  "sources": [
    { "type": "url", "value": "https://react.dev/reference/react" }
  ]
}

Create a notebook with multiple sources:

{
  "name": "Security Research",
  "sources": [
    { "type": "url", "value": "https://owasp.org/Top10" },
    { "type": "file", "value": "/path/to/security-report.pdf" },
    { "type": "text", "value": "Custom notes...", "title": "My Notes" }
  ],
  "description": "Security best practices and research",
  "topics": ["security", "owasp", "best-practices"]
}

NotebookLM Limits (Free Tier)

  • 100 notebooks maximum

  • 50 sources per notebook

  • 500k words per source

  • 50 queries per day

Notes

  • Requires authentication (run setup_auth first)

  • Creates notebook with sharing set to private by default

  • Large files may take longer to process

Inputs: name (required), sources (required), description, topics, +3 more.

download_audioDownload AudioA
Read-onlyIdempotent

Download the generated audio overview file.

Requirements

  • Audio must be in "ready" status

  • Use get_audio_status to check before downloading

Output

Downloads to specified path or ~/notebooklm-audio-{timestamp}.mp3

Example

{
  "notebook_id": "my-research",
  "output_path": "/path/to/save/podcast.mp3"
}

Inputs: notebook_id, notebook_url, output_path.

generate_audio_overviewGenerate AudioA

Generate an AI-powered audio overview (podcast-style) for a notebook.

What This Tool Does

  • Triggers NotebookLM's audio overview generation

  • Audio overviews are ~5-15 minute podcast-style summaries

  • Generation takes 2-5 minutes typically

  • Returns immediately with status (check with get_audio_status)

Requirements

  • Notebook must have at least one source

  • Audio generation may not be available on all notebooks

Example

{ "notebook_id": "my-research" }

Inputs: notebook_id, notebook_url.

generate_data_tableGenerate TableA

Generate a structured Data Table from notebook sources.

What This Tool Does

  • Opens the Studio panel in NotebookLM

  • Generates a structured tabular extraction from notebook content

  • Tables organize key information from sources into rows and columns

  • Generation typically takes 1-3 minutes

  • Returns immediately with status (check with get_data_table)

Requirements

  • Notebook must have at least one source

  • Authentication required (run setup_auth first)

Example

{ "notebook_id": "my-research" }

Inputs: notebook_id, notebook_url.

generate_video_overviewGenerate VideoA

Generate an AI-powered Video Overview for a notebook.

What This Tool Does

  • Opens the Studio panel in NotebookLM

  • Generates a visual video summary of notebook content

  • Supports multiple visual styles and formats

  • Generation takes 3-10 minutes typically

  • Returns immediately with status (check with get_video_status)

Visual Styles

  • auto-select — Let NotebookLM choose the best style (default)

  • custom — Custom visual style

  • classic — Classic presentation style

  • whiteboard — Hand-drawn whiteboard style

  • kawaii — Cute kawaii style

  • anime — Anime-inspired visuals

  • watercolour — Watercolour painting style

  • retro-print — Retro print aesthetic

  • heritage — Heritage/traditional style

  • paper-craft — Paper-craft visual style

Formats

  • explainer — Full explanation (5-15 min, default)

  • brief — Quick summary (1-3 min)

Requirements

  • Notebook must have at least one source

  • Authentication required (run setup_auth first)

Example

{ "notebook_id": "my-research", "style": "documentary", "format": "brief" }

Inputs: notebook_id, notebook_url, style, format.

get_audio_statusAudio StatusA
Read-onlyIdempotent

Check the audio overview generation status for a notebook.

Returns

  • status: "not_started" | "generating" | "ready" | "failed" | "unknown"

  • progress: Generation progress (0-100) if generating

  • duration: Audio duration in seconds if ready

Example

{ "notebook_id": "my-research" }

Inputs: notebook_id, notebook_url.

get_data_tableGet TableA
Read-onlyIdempotent

Extract the generated Data Table content from a notebook.

What This Tool Does

  • Navigates to the notebook's Studio panel

  • Extracts the table data (headers and rows) as structured JSON

  • Returns the full table content for analysis

Returns

  • table.headers: Column headers

  • table.rows: Array of row arrays

  • table.totalRows: Number of rows

  • table.totalColumns: Number of columns

Requirements

  • Data table must be generated first (use generate_data_table)

  • Returns error if table is not yet ready

Example

{ "notebook_id": "my-research" }

Inputs: notebook_id, notebook_url.

get_healthHealth CheckA
Read-onlyIdempotent

Get server health status including authentication state, active sessions, and configuration. Use this to verify the server is ready before starting research workflows.

Deep Check Mode (v2026.1.1) Set deep_check: true to actually verify the NotebookLM chat UI loads. This catches stale sessions where cookies exist but the UI won't load. Returns chat_ui_accessible: true/false.

If authenticated=false and having persistent issues: Consider running cleanup_data(preserve_library=true) + setup_auth for fresh start with clean browser session.

Inputs: deep_check, notebook_id.

get_notebookGet NotebookB
Read-onlyIdempotent

Get detailed information about a specific notebook by ID

Inputs: id (required).

get_notebook_chat_historyChat HistoryA
Read-onlyIdempotent

Extract conversation history from a NotebookLM notebook's chat interface.

This tool uses browser automation to navigate to a notebook and extract all Q&A pairs from the chat UI. This is useful for:

  • Recovering previous research conversations

  • Auditing what queries were made in a notebook

  • Understanding quota usage from direct NotebookLM browser usage

  • Resuming context from previous sessions

Context Management

Use preview_only: true to get a quick count before extracting full content. Use output_file to export to JSON instead of returning to context. Use offset with limit for pagination through large histories.

Examples

Quick audit (preview only):

{ "notebook_id": "my-research", "preview_only": true }

Export to file (avoids context overflow):

{ "notebook_id": "my-research", "output_file": "/tmp/chat-history.json" }

Paginate through history:

{ "notebook_id": "my-research", "limit": 20, "offset": 0 }
{ "notebook_id": "my-research", "limit": 20, "offset": 20 }

Inputs: notebook_id, notebook_url, preview_only, limit, +3 more.

get_query_historyQuery HistoryA
Read-onlyIdempotent

Retrieve past NotebookLM queries and answers for reviewing research sessions.

Use this tool to:

  • Review past research conversations

  • Find specific information from previous queries

  • Track which notebooks and sessions you've used

  • Search through question and answer content

Returns query entries with question, answer, notebook, session, and timing info.

Inputs: session_id, notebook_id, date, search, +1 more.

get_quotaGet QuotaA
Read-onlyIdempotent

Get current quota status including license tier, usage, and limits.

Returns:

  • tier: 'free', 'pro', 'ultra', or 'unknown'

  • notebooks: used/limit/remaining/percent

  • sources: limit per notebook

  • queries: used/limit/remaining/percent/should_stop/reset_time

  • warnings: array of warning messages

Quota Limits by Tier:

  • Free: 100 notebooks, 50 sources/notebook, 50 queries/day

  • Pro: 500 notebooks, 300 sources/notebook, 500 queries/day

  • Ultra: 500 notebooks, 600 sources/notebook, 5000 queries/day

Use sync=true to fetch actual quota from Google's NotebookLM UI (requires browser). Without sync, returns locally tracked counts which may differ if you used NotebookLM directly in browser. Query counts reset daily at midnight.

Inputs: sync.

get_video_statusVideo StatusA
Read-onlyIdempotent

Check the Video Overview generation status for a notebook.

Returns

  • status: "not_started" | "generating" | "ready" | "failed" | "unknown"

  • progress: Generation progress (0-100) if generating

  • duration: Video duration in seconds if ready

Example

{ "notebook_id": "my-research" }

Inputs: notebook_id, notebook_url.

list_notebooksList NotebooksA
Read-onlyIdempotent

List all library notebooks with metadata (name, topics, use cases, URL). Use this to present options, then ask which notebook to use for the task.

Inputs: no named parameters.

list_sessionsList SessionsA
Read-onlyIdempotent

List all active sessions with stats (age, message count, last activity). Use to continue the most relevant session instead of starting from scratch.

Inputs: no named parameters.

list_sourcesList SourcesA
Read-onlyIdempotent

List all sources in a NotebookLM notebook.

Returns

Array of sources with:

  • id: Source identifier (for use with remove_source)

  • title: Source name/title

  • type: url, text, file, drive, or unknown

  • status: ready, processing, or failed

Example

{ "notebook_id": "my-notebook" }

Or with direct URL:

{ "notebook_url": "https://notebooklm.google.com/notebook/xxx" }

Inputs: notebook_id, notebook_url.

re_authRe-authenticateA
Destructive

Switch to a different Google account or re-authenticate. Use this when:

  • NotebookLM rate limit is reached (50 queries/day for free accounts)

  • You want to switch to a different Google account

  • Authentication is broken and needs a fresh start

This will:

  1. Close all active browser sessions

  2. Delete all saved authentication data (cookies, Chrome profile)

  3. Open browser for fresh Google login

After completion, use 'get_health' to verify authentication.

TROUBLESHOOTING for persistent auth issues: If re_auth fails repeatedly:

  1. Ask user to close ALL Chrome/Chromium instances

  2. Run cleanup_data(confirm=false, preserve_library=true) to preview old files

  3. Run cleanup_data(confirm=true, preserve_library=true) to clean everything except library

  4. Run re_auth again for completely fresh start This removes old installation data and browser sessions that can cause conflicts.

Inputs: show_browser, browser_options.

remove_notebookRemove NotebookA
DestructiveIdempotent

Dangerous — requires explicit user confirmation.

Confirmation Workflow

  1. User requests removal ("Remove the React notebook")

  2. Look up full name to confirm

  3. Ask: "Remove '[notebook_name]' from your library? (Does not delete the actual NotebookLM notebook)"

  4. Only on explicit "Yes" → call remove_notebook

Never remove without permission or based on assumptions.

Example: User: "Delete the old React notebook" You: "Remove 'React Best Practices' from your library?" User: "Yes" → call remove_notebook

Inputs: id (required).

remove_sourceRemove SourceA
DestructiveIdempotent

Remove a source from a NotebookLM notebook.

Usage

  1. First call list_sources to get source IDs

  2. Then call remove_source with the source ID

Example

{
  "notebook_id": "my-notebook",
  "source_id": "source-0"
}

Inputs: source_id (required), notebook_id, notebook_url.

reset_sessionReset SessionA
DestructiveIdempotent

Reset a session's chat history (keep same session ID). Use for a clean slate when the task changes; ask the user before resetting.

Inputs: session_id (required).

search_notebooksSearch NotebooksB
Read-onlyIdempotent

Search library by query (name, description, topics, tags). Use to propose relevant notebooks for the task and then ask which to use.

Inputs: query (required).

select_notebookSelect NotebookA
Idempotent

Set a notebook as the active default (used when ask_question has no notebook_id).

When To Use

  • User switches context: "Let's work on React now"

  • User asks explicitly to activate a notebook

  • Obvious task change requires another notebook

Auto-Switching

  • Safe to auto-switch if the context is clear and you announce it: "Switching to React notebook for this task..."

  • If ambiguous, ask: "Switch to [notebook] for this task?"

Example

User: "Now let's build the React frontend" You: "Switching to React notebook..." (call select_notebook)

Inputs: id (required).

setup_authSetup AuthA

Google authentication for NotebookLM access - opens a browser window for manual login to your Google account. Returns immediately after opening the browser. You have up to 10 minutes to complete the login. Use 'get_health' tool afterwards to verify authentication was saved successfully. Use this for first-time authentication or when auto-login credentials are not available. For switching accounts or rate-limit workarounds, use 're_auth' tool instead.

TROUBLESHOOTING for persistent auth issues: If setup_auth fails or you encounter browser/session issues:

  1. Ask user to close ALL Chrome/Chromium instances

  2. Run cleanup_data(confirm=true, preserve_library=true) to clean old data

  3. Run setup_auth again for fresh start This helps resolve conflicts from old browser sessions and installation data.

Inputs: show_browser, browser_options.

sync_librarySync LibraryA
Idempotent

Sync your local library with actual NotebookLM notebooks.

What This Tool Does

  • Navigates to NotebookLM and extracts all your notebooks

  • Compares with local library entries

  • Detects stale entries (notebooks deleted or URLs changed)

  • Identifies notebooks not in your library

  • Optionally auto-removes stale entries

When To Use

  • Library seems out of sync with NotebookLM

  • After deleting notebooks in NotebookLM

  • To discover new notebooks to add

  • Before setting up automation workflows

Output

Returns a sync report with:

  • matched: Library entries that match actual notebooks

  • staleEntries: Library entries with no matching notebook (candidates for removal)

  • missingNotebooks: NotebookLM notebooks not in library (candidates for adding)

  • suggestions: Recommended actions

Example Usage

{ "auto_fix": false }

With auto-fix to remove stale entries:

{ "auto_fix": true }

Inputs: auto_fix, show_browser.

update_notebookUpdate NotebookA
Idempotent

Update notebook metadata based on user intent.

Pattern

  1. Identify target notebook and fields (topics, description, use_cases, tags, url)

  2. Propose the exact change back to the user

  3. After explicit confirmation, call this tool

Examples

  • User: "React notebook also covers Next.js 14" You: "Add 'Next.js 14' to topics for React?" User: "Yes" → call update_notebook

  • User: "Include error handling in n8n description" You: "Update the n8n description to mention error handling?" User: "Yes" → call update_notebook

Tip: You may update multiple fields at once if requested.

Inputs: id (required), name, description, topics, +4 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.8/5.0

    Scored across 31 tools

    Disambiguation3/5

    The tool set has clear distinct purposes for core operations like notebook management (add_notebook, create_notebook, list_notebooks) and media generation (generate_audio_overview, generate_video_overview), but there is significant overlap between tools like ask_question, get_notebook_chat_history, and get_query_history, which all involve querying or retrieving chat data, potentially causing confusion. Additionally, cleanup_data and re_auth both handle authentication/session cleanup with overlapping functions.

    Naming Consistency5/5

    Tool names follow a highly consistent verb_noun pattern throughout, such as add_notebook, create_notebook, list_notebooks, generate_audio_overview, get_health, and sync_library. All tools use snake_case without deviation, making them predictable and easy to parse for agents.

    Tool Count2/5

    With 31 tools, the count is excessive for the server's purpose of managing NotebookLM notebooks and media. Many tools could be consolidated (e.g., multiple chat history tools, overlapping cleanup/auth tools), leading to a bloated interface that may overwhelm agents and increase misselection risk.

    Completeness4/5

    The tool surface provides comprehensive coverage for NotebookLM operations, including CRUD for notebooks and sources, media generation (audio, video, data tables), session management, authentication, and library syncing. Minor gaps exist, such as no direct tool for editing source content or managing sharing settings, but agents can work around these with existing tools.

    Maintenance

    ActivityStale
    ResponsivenessLimited data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to drive Google NotebookLM notebooks as a deep-research workspace: ingesting local PDFs and YouTube videos, cross-checking sources for contradictions, identifying knowledge gaps, generating audio overviews, and exporting Markdown dossiers with BibTeX and APA bibliographies. It operates over the Model Context Protocol inside Google Antigravity IDE, with browser-session authentication handled automatically.
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables AI assistants and agents to connect directly to Google NotebookLM through its high-performance internal RPC calls. Provides grounded RAG chat with citations, notebook and source management (URLs, YouTube, Drive files, text), Audio Overview generation and download, persistent session handling, and automated Deep Research.
      38
      1
      MIT