notebooklm-mcp
NotebookLM REST API + MCP server
Automate Google NotebookLM at scale. 33-endpoint HTTP REST API for n8n / Zapier / Make / curl, plus an MCP server for Claude Code / Cursor / Codex. Citation-backed Q&A, full Studio generation (audio · video · infographic · report · presentation · data table), multi-account rotation with auto-reauth.
v1.7.9 — production-grade, batch-tested on overnight runs of 1 000+ questions. New:
batch_to_vaultis now a first-class MCP tool (no HTTP server required) on top of the existingPOST /batch-to-vaultendpoint. See RTFM integration for the full pattern. Compare withPleasePrompto/notebooklm-mcpv2.0.0 to see when this project is the right pick (REST API, full Studio, auto-reauth) and when the MCP-only upstream is.
Features
Q&A with Citations
Ask questions to NotebookLM and get accurate, citation-backed answers
Source citation extraction with 5 formats: none, inline, footnotes, json, expanded (97% excerpt success rate)
Session management for multi-turn conversations with auto-reauth on session expiry
Content Generation
Generate multiple content types from your notebook sources:
Content Type | Formats | Options |
Audio Overview | Podcast-style discussion | Language (80+), custom instructions |
Video | Brief, Explainer | 6 visual styles, language, custom instructions |
Infographic | Horizontal, Vertical | Language, custom instructions |
Report | Summary, Detailed | Language, custom instructions |
Presentation | Overview, Detailed | Language, custom instructions |
Data Table | Simple, Detailed | Language, custom instructions |
Video Visual Styles: classroom, documentary, animated, corporate, cinematic, minimalist
Content Download
Download Audio — WAV audio files
Download Video — MP4 video files
Download Infographic — PNG image files
Text-based content (report, presentation, data_table) is returned in the API response
Source Management
Add sources: Files (PDF, TXT, DOCX), URLs, Text, YouTube videos, Google Drive
List sources: View all sources in a notebook
Notebook Library
Multi-notebook management with validation and smart selection
Auto-discovery: Automatically generate metadata via NotebookLM queries
Search notebooks by keyword in name, description, or topics
Scrape notebooks: List all notebooks from NotebookLM with IDs and names
Bulk delete: Delete multiple notebooks at once
Integration Options
MCP Protocol — Claude Code, Cursor, Codex, any MCP client
HTTP REST API — n8n, Zapier, Make.com, custom integrations
Docker — Isolated deployment with Docker or Docker Compose
RTFM retrieval layer —
/batch-to-vaultwrites citation-backed answers as markdown + JSON sidecars (nblm-answer-v1schema), indexable by RTFM (FTS5 + semantic) for unlimited offline queries. Ideal for academic / SOTA workflows. Guide.
Related MCP server: notebooklm-mcp
Quick Start
Option 0 — Claude Code marketplace (one-liner, recommended for Claude Code users)
The fastest way to get NotebookLM into Claude Code. Distributed via the roomi-fields/claude-plugins marketplace alongside RTFM (the retrieval companion — see RTFM integration guide):
/plugin marketplace add roomi-fields/claude-plugins
/plugin install notebooklm@roomi-fieldsThat registers the MCP server, runs npx -y @roomi-fields/notebooklm-mcp@<pinned-version> automatically (Node ≥ 18 required), and lets you upgrade with two commands when a new release ships: /plugin marketplace update roomi-fields then /reload-plugins. Then run npm run setup-auth once to log into Google. To install RTFM at the same time: /plugin install rtfm@roomi-fields.
Option 1 — HTTP REST API (n8n, Zapier, Make, curl, any HTTP client)
git clone https://github.com/roomi-fields/notebooklm-mcp.git
cd notebooklm-mcp
npm install && npm run build
npm run setup-auth # One-time Google login
npm run start:http # Start REST API on port 3000# Citation-backed Q&A, single curl, JSON response
curl -X POST http://localhost:3000/ask \
-H 'Content-Type: application/json' \
-d '{"question": "Summarize chapter 3", "notebook_id": "your-id", "source_format": "json"}'The full surface is 33 documented endpoints — see the REST API reference. For overnight batches of 1 000+ questions, see the batch pattern.
Option 2 — MCP Mode (Claude Code, Cursor, Codex)
# Build (same package, MCP transport)
git clone https://github.com/roomi-fields/notebooklm-mcp.git
cd notebooklm-mcp
npm install && npm run build
# Claude Code
claude mcp add notebooklm node /path/to/notebooklm-mcp/dist/index.js
# Cursor — add to ~/.cursor/mcp.json
{
"mcpServers": {
"notebooklm": {
"command": "node",
"args": ["/path/to/notebooklm-mcp/dist/index.js"]
}
}
}Then say: "Log me in to NotebookLM" → Chrome opens → log in with Google.
Option 3 — Docker (NAS, server, headless)
# Build and run
docker build -t notebooklm-mcp .
docker run -d --name notebooklm-mcp -p 3000:3000 -p 6080:6080 -v notebooklm-data:/data notebooklm-mcp
# Authenticate via noVNC
# 1. Open http://localhost:6080/vnc.html
# 2. Run: curl -X POST http://localhost:3000/setup-auth -d '{"show_browser":true}'
# 3. Login to Google in the VNC windowSee Docker Guide for NAS deployment (Synology, QNAP).
Documentation
Full docs site: https://roomi-fields.github.io/notebooklm-mcp/ · OpenAPI 3.1 spec
Guide | Description |
Step-by-step setup for HTTP and MCP modes | |
Environment variables and security | |
Complete HTTP endpoint documentation (33 endpoints) | |
Production batch pattern with auto-reauth and rotation | |
Pipeline pattern: NotebookLM as one-shot ingestion, RTFM as retrieval layer. | |
Workflow automation setup | |
Common issues and solutions | |
Multi-notebook management | |
Autonomous metadata generation | |
Audio, video, infographic, report, presentation | |
Multiple accounts with TOTP auto-reauth | |
Docker and Docker Compose deployment | |
Run Claude Desktop + HTTP simultaneously | |
Feature matrix vs the upstream MCP-only server | |
Profile locking (solved in v1.3.6+) | |
i18n system for multilingual UI support |
Roadmap
See ROADMAP.md for planned features and version history.
Latest releases:
v1.7.9 — Security: resolve moderate XSS advisory GHSA-v2v4-37r5-5v8g in transitive
ip-address ≤10.1.0(pulled in via@modelcontextprotocol/sdk→express-rate-limit) by pinningip-address ^10.2.0inoverrides.npm auditclean. Unblocks the CI security gate that 1.7.8 had been failing.v1.7.8 —
add_sourcefalse-negative fix (verified at runtime against a live MCP session this time): the count-based success detection now runs on every poll cycle instead of only after the upload dialog closes, since NotebookLM 2026 keeps the dialog open to allow chained uploads. Also fixes a long-standing packaging bug wheredist/index.jswas published in mode 644 (no+x), causing silentPermission deniedfailures in sandbox shellsv1.7.7 —
add_sourcedefensive patch: broaden selectors to cover the empty/fresh-notebook "Upload sources" CTA (EN+FR), and replace the bareCould not find "Add source" buttonerror with a structured DOM dump (URL, title, top 25 buttons + their aria-label/text/class) so the next iteration can be precise. Not validated runtime — the enriched diagnostic is the deliverablev1.7.6 — Fixes two tools shipped in 1.7.4 without live-runtime validation: (1)
create_notebooknow waits for the final UUID-based URL (no morenotebook/creating/c) and verifies the rename actually applied (returnsname_applied/actual_name); (2)delete_notebooks_from_nblmnow uses the same id-based DOM strategy aslist_notebooks_from_nblm(the oldbutton[aria-labelledby*="project-"]selector was broken on the current NotebookLM DOM)v1.7.5 — Three end-user bugs fixed: (1)
/plugin marketplace update roomi-fields+/reload-pluginsnow actually upgrades the running MCP (npx pin inplugin.json); (2)list_notebooks_from_nblmno longer hardcodes"Notebook"as title — id-based scrape returns real names; (3)get_health.current_accountno longer returns a stale email afterre_authv1.7.4 — Expose
create_notebookanddelete_notebooks_from_nblmas MCP tools (handlers existed but lacked a tool definition + dispatch case); 30/30 alignment audit passesv1.7.3 — Fix:
list_notebooks_from_nblmMCP tool was declared but unreachable (missing dispatch case) — now resolves correctlyv1.7.2 — Claude Code plugin manifest (
.claude-plugin/plugin.json) + cross-file version sync script enforced in CI; README "Install via Claude Code marketplace" one-linerv1.7.0 —
batch_to_vaultexposed as a first-class MCP tool (parity with the HTTP endpoint, no localhost server required); sharedrunBatchToVaulthelper deduplicates the loop across both transportsv1.6.0 —
/batch-to-vaultendpoint + RTFM integration (nblm-answer-v1JSON Schema published at schemas.roomi-fields.com/nblm-answer-v1.json) for caching NotebookLM answers as a searchable markdown vaultv1.5.9 — Restore
mcpNamefield for MCP Registry npm-package ownership verificationv1.5.8 — NotebookLM 2026 UI adaptations (icon-label sanitization, Discussion-panel recovery, count-based source detection) — PR #5 by @KhizarJamshaidIqbal
v1.5.7 — Citation extraction selector fix (
.highlighted) and Docker multi-stage build — PR #1 by @JulienCANTONIv1.5.6 — Citation extraction major rewrite (97% success rate), browser-verified auth at startup, profile auto-sync
v1.5.5 — Multi-account state-path bug fix, Windows startup scripts, hidden-window MCP proxy
v1.5.4 — Mid-session auto-reauth with stored credentials, TOTP support
v1.5.3 — Docker deployment with noVNC for visual authentication + NAS support (Synology, QNAP)
v1.5.2 — Notebook scraping from NotebookLM + Bulk delete + Bug fixes
v1.5.1 — Multilingual UI support (FR/EN) with i18n selector system + E2E tests (76 tests)
v1.5.0 — Complete Studio content generation (video, infographic, presentation, data_table) + Notes management + Delete sources
v1.4.0 — Content management (sources, audio, generation) + Multi-account
Not yet implemented:
Discover sources (Web/Drive search with Fast/Deep modes)
Edit notes (create, delete, and convert are implemented)
Disclaimer
This tool automates browser interactions with NotebookLM. Use a dedicated Google account for automation. CLI tools like Claude Code can make mistakes — always review changes before deploying.
See full Disclaimer below.
Contributing
Found a bug? Have an idea? Open an issue or submit a PR!
See CONTRIBUTING.md for guidelines.
License
MIT — Use freely in your projects. See LICENSE.
Author
Romain Peyrichou — @roomi-fields
About browser automation: While I've built in humanization features (realistic typing speeds, natural delays, mouse movements), I can't guarantee Google won't detect or flag automated usage. Use a dedicated Google account for automation.
About CLI tools and AI agents: CLI tools like Claude Code, Codex, and similar AI-powered assistants are powerful but can make mistakes:
Always review changes before committing or deploying
Test in safe environments first
Keep backups of important work
AI agents are assistants, not infallible oracles
I built this tool for myself and share it hoping it helps others, but I can't take responsibility for any issues that might occur. Use at your own discretion.
Built with frustration about hallucinated APIs, powered by Google's NotebookLM
⭐ Star on GitHub if this saves you debugging time!
Available Tools
56 toolsauth_logoutADestructiveIdempotent
De-authenticate (logout) - Clears all authentication data for security. Use this when:
User wants to log out for security reasons
Removing credentials before shutting down
Clearing auth without immediately re-authenticating
This will:
Close all active browser sessions
Delete all saved authentication data (cookies, Chrome profile)
Preserve notebook library and other data
IMPORTANT: After de_auth, the server will need re-authentication via setup_auth or re_auth before making queries.
Use 'get_health' to verify de-authentication was successful (authenticated: false).
Inputs: no named parameters. Returns: data, error, success
auth_setupA
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. IMPORTANT: If already authenticated, this tool will skip re-authentication. 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:
Ask user to close ALL Chrome/Chromium instances
Run cleanup_data(confirm=true, preserve_library=true) to clean old data
Run setup_auth again for fresh start This helps resolve conflicts from old browser sessions and installation data.
Inputs: headless, show_browser, browser_options. Returns: data, error, success
auth_switchA
Switch to a different Google account or re-authenticate. Use this when:
NotebookLM usage limit is reached (compute-based, refreshes every 5 hours)
You want to switch to a different Google account
Authentication is broken and needs a fresh start
This will:
Close all active browser sessions
Delete all saved authentication data (cookies, Chrome profile)
Open browser for fresh Google login
After completion, use 'get_health' to verify authentication.
TROUBLESHOOTING for persistent auth issues: If re_auth fails repeatedly:
Ask user to close ALL Chrome/Chromium instances
Run cleanup_data(confirm=false, preserve_library=true) to preview old files
Run cleanup_data(confirm=true, preserve_library=true) to clean everything except library
Run re_auth again for completely fresh start This removes old installation data and browser sessions that can cause conflicts.
Inputs: headless, show_browser, browser_options. Returns: data, error, success
cancel_answerA
Stop a notebook’s in-flight answer — the UI’s “Stop” on a streaming reply. RPC-backed. Fire-and-forget: the server does not confirm, so cancelled: true means the stop was sent, not that a turn was running. Defaults to the most recent conversation.
Inputs: notebook_id, notebook_url, conversation_id. Returns: data, error, success
cancel_researchA
Cancel an in-flight Fast Research run for a notebook. RPC-backed. Fire-and-forget: the server does not validate the run id, so cancelled: true means the cancel was sent; confirm with research_sources. run_id defaults to the notebook’s current research task.
Inputs: run_id, notebook_id, notebook_url. Returns: data, error, success
check_source_freshnessA
Say whether URL / Drive sources have drifted from what they point at. Name no source to check the whole notebook. RPC-backed (no browser). stale: null means the server did not say — not that the source is current.
Inputs: source_id, notebook_id, source_name, notebook_url. Returns: data, error, success
content_copyA
Copy Studio artifacts (audio, video, reports, quizzes, slide decks…) into another existing notebook. RPC-backed. Returns, for each artifact, its original id and the id of the copy. Only from a notebook you own (not one shared with you or public). Not idempotent: a failure is never retried automatically.
Inputs: content_ids (required), notebook_id, notebook_url, target_notebook_id, +1 more. Returns: data, error, success
content_deleteADestructiveIdempotent
Delete a generated Studio artifact (audio overview, video, report, infographic, presentation, data table, flashcards, quiz) from a notebook.
Use list_content first to get the artifact id. RPC-backed (no browser).
WARNING: irreversible. Note-backed mind maps are not covered — they live in the notes system, not the Studio library.
Inputs: content_id (required), notebook_id, notebook_url. Returns: data, error, success
content_downloadAIdempotent
Download or export generated content from NotebookLM.
Supported content types:
audio_overview: Downloads as audio file (MP3)
video: Downloads as video file
infographic: Downloads as image file
presentation: Exports to Google Slides (returns URL)
data_table: Exports to Google Sheets (returns URL)
Note: Report content is text-based and returned in the generation response.
Inputs: content_type (required), session_id, output_path, notebook_url. Returns: data, error, success
content_generateA
Generate content from your NotebookLM sources.
Supported content types:
audio_overview: Audio podcast/overview (Deep Dive conversation with two AI hosts)
video: Video summary that visually explains main topics (brief or explainer format)
presentation: Slides/presentation with AI-generated content and images
report: Briefing document (2,000-3,000 words) summarizing key findings, exportable as PDF/DOCX
infographic: Visual infographic in horizontal (16:9) or vertical (9:16) format
data_table: Structured table organizing key information (exportable as CSV/Excel)
Language support: All content types support 80+ languages via the language parameter.
Video styles: Video content supports 6 visual styles via the video_style parameter: classroom, documentary, animated, corporate, cinematic, minimalist.
These content types use real NotebookLM Studio UI buttons or the generic ContentGenerator architecture that navigates the Studio panel and falls back to chat-based generation.
NOTE: Other content types (faq, study_guide, timeline, table_of_contents) are NOT currently implemented. For document-style content, use the ask_question tool.
Inputs: content_type (required), language, session_id, video_style, +2 more. Returns: data, error, success
content_listARead-onlyIdempotent
List all sources and generated content in the current notebook.
Returns:
Sources: Documents, URLs, and other uploaded materials
Generated content: Audio overviews
Inputs: session_id, notebook_url. Returns: data, error, success
delete_chat_historyA
Clear a notebook’s chat history. RPC-backed (no browser). NotebookLM has no per-turn delete: the whole conversation goes. The next question then starts a fresh conversation.
Inputs: notebook_id, notebook_url, conversation_id. Returns: data, error, success
export_artifactA
Export a finished Studio artifact to Google Docs or Google Sheets. RPC-backed. Returns the created document link when the server sends one.
Inputs: artifact_id (required), title, target, notebook_id, +1 more. Returns: data, error, success
generate_mind_mapA
Generate and save a mind map from a notebook’s sources. RPC-backed (no browser). Returns the saved mind-map id and its JSON structure.
Inputs: focus, title, language, notebook_id, +1 more. Returns: data, error, success
generate_study_aidA
Generate a study aid from a notebook’s sources: flashcards or a quiz. RPC-backed (no browser). Returns when generation completes.
Inputs: kind (required), focus, language, notebook_id, +1 more. Returns: data, error, success
get_chat_historyA
Read back the questions and answers already recorded in a notebook, newest first. RPC-backed (no browser). NotebookLM exposes only the most recent conversation, which is what you get unless you pass conversation_id.
Inputs: limit, notebook_id, notebook_url, conversation_id. Returns: data, error, success
get_notebook_summaryA
Read a notebook’s own summary of its sources and the questions it suggests asking. RPC-backed (no browser). Cheaper than asking a question to find out what is in there.
Inputs: notebook_id, notebook_url. Returns: data, error, success
get_source_guideB
Read NotebookLM’s own summary and key topics for a single source. RPC-backed. A source NotebookLM has not summarised yet returns an empty summary.
Inputs: source_id, notebook_id, source_name, notebook_url. Returns: data, error, success
get_usageA
Read the account’s live compute-meter usage (RPC-backed, account-scoped — no notebook). Returns the five-hour and weekly quota windows as percentages, their reset times, and a per-action table of what still has quota. status=disabled when the account has no meter. Use it to check headroom before a long batch of questions or generations.
Inputs: no named parameters. Returns: data, error, success
library_addA
📝 MANUAL ENTRY — Add notebook with manually specified metadata (use auto_discover_notebook instead)
When to Use
Auto-discovery failed or unavailable
User has specific metadata requirements
User prefers manual control
Conversation Workflow (Mandatory)
When the user says: "I have a NotebookLM with X"
FIRST: Try auto_discover_notebook for faster setup ONLY IF user refuses auto-discovery or it fails:
Ask URL: "What is the NotebookLM URL?"
Ask content: "What knowledge is inside?" (1–2 sentences)
Ask topics: "Which topics does it cover?" (3–5)
Ask use cases: "When should we consult it?"
Propose metadata and confirm:
Name: [suggested]
Description: [from user]
Topics: [list]
Use cases: [list] "Add it to your library now?"
Only after explicit "Yes" → call this tool
Rules
Do not add without user permission
Prefer auto_discover_notebook when possible
Do not guess metadata — ask concisely
Confirm summary before calling the tool
Example
User: "I have a notebook with n8n docs" You: "Want me to auto-generate the metadata?" (offer auto_discover_notebook first) User: "No, I'll specify it myself" You: Ask URL → content → topics → use cases; propose summary User: "Yes" You: Call add_notebook
How to Get a NotebookLM Share Link
Visit https://notebooklm.google/ → Login (free: 100 notebooks, 50 sources each, 500k words, 50 daily queries)
Click "+ New" (top right) → Upload sources (docs, knowledge)
Click "Share" (top right) → Select "Anyone with the link"
Click "Copy link" (bottom left) → Give this link to Claude
(Upgraded: Google AI Pro/Ultra gives 5x higher limits)
Inputs: url (required), name (required), topics (required), description (required), +3 more. Returns: data, error, success
library_discoverA
🚀 AUTO-DISCOVERY — Automatically generate notebook metadata via NotebookLM (RECOMMENDED)
When to Use
User provides NotebookLM URL and wants quick/automatic setup
User prefers not to manually specify metadata
Default choice for adding notebooks
Workflow
User provides NotebookLM URL
Ask confirmation: "Add '[URL]' with auto-generated metadata?"
Call this tool → NotebookLM generates name, description, tags
Show generated metadata to user for review
Benefits
✅ 30 seconds vs 5 minutes manual entry
✅ Zero-friction notebook addition
✅ Consistent metadata quality
✅ Discovers topics user might not think of
Example
User: "Add this NotebookLM: https://notebooklm.google.com/notebook/abc123" You: "Add this notebook with auto-generated metadata?" User: "Yes" You: Call auto_discover_notebook(url="https://...") → Returns: {name: "n8n-workflow-guide", description: "...", tags: [...]}
Fallback
If auto-discovery fails (rare), use add_notebook tool for manual entry.
How to Get a NotebookLM Share Link
Visit https://notebooklm.google/ → Login (free: 100 notebooks, 50 sources each, 500k words, 50 daily queries)
Click "+ New" (top right) → Upload sources (docs, knowledge)
Click "Share" (top right) → Select "Anyone with the link"
Click "Copy link" (bottom left) → Give this link to Claude
(Upgraded: Google AI Pro/Ultra gives 5x higher limits)
Inputs: url (required). Returns: data, error, success
library_getARead-onlyIdempotent
Get detailed information about a specific notebook by ID
Inputs: id (required). Returns: data, error, success
library_listARead-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. Returns: data, error, success
library_removeADestructiveIdempotent
Dangerous — requires explicit user confirmation.
Confirmation Workflow
User requests removal ("Remove the React notebook")
Look up full name to confirm
Ask: "Remove '[notebook_name]' from your library? (Does not delete the actual NotebookLM notebook)"
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). Returns: data, error, success
library_searchARead-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). Returns: data, error, success
library_selectAIdempotent
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). Returns: data, error, success
library_statsARead-onlyIdempotent
Get statistics about your notebook library (total notebooks, usage, etc.)
Inputs: no named parameters. Returns: data, error, success
library_updateAIdempotent
Update notebook metadata based on user intent.
Pattern
Identify target notebook and fields (topics, description, use_cases, tags, url)
Propose the exact change back to the user
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), url, name, tags, +4 more. Returns: data, error, success
manage_labelsA
Manage a notebook’s source labels (RPC-backed): list them, create one, or delete some. action=list (default) / create (needs name) / delete (needs label_ids).
Inputs: name, emoji, action, label_ids, +2 more. Returns: data, error, success
notebook_askA
Conversational Research Partner (NotebookLM • Gemini 2.5 • Session RAG)
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. If authentication later fails (e.g., expired cookies), use the prompt 'notebooklm.auth-repair'.
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, +3 more. Returns: data, error, success
notebook_copyA
Copy a whole notebook — its sources and Studio artifacts — into a new notebook. RPC-backed. Returns the new notebook id and URL. The sources are copied in the background and may not be listed in the reply yet — call list_sources a few seconds later. Only a notebook you own can be copied (not one shared with you or public). Not idempotent: a failure is never retried automatically, so check the notebook list before retrying.
Inputs: title, notebook_id, notebook_url. Returns: data, error, success
notebook_createA
Create a brand-new empty notebook directly in NotebookLM (no pre-existing URL required, unlike add_notebook which only registers an already-created notebook into the library).
Returns { notebook_url, notebook_id, name_applied, actual_name, message }.
notebook_url/notebook_id: always the FINAL UUID-based URL (the tool waits past the/notebook/creating/ctransitional URL).name_applied(boolean): whether thenameparameter actually took effect.falsemeans the notebook is still "Untitled notebook" — rename via UI if needed.actual_name(string): the title observed on the notebook after creation.
Typical workflow:
create_notebook({ name?: "my-research" })→{ notebook_url, notebook_id, name_applied, actual_name }add_source({ notebook_url, source_type: "url", source: "https://..." })ask_question({ notebook_url, question: "..." })
Note: Requires authentication. Run setup_auth first if not authenticated.
Inputs: name, show_browser. Returns: data, error, success
notebook_deleteADestructive
Delete one or more notebooks directly from NotebookLM (UI-level deletion, not just from the local library). Pass an array of notebook IDs (UUIDs from list_notebooks_from_nblm).
Returns { deleted: [...], failed: [...] } so the caller can retry or report on partial failures.
Use this to:
Bulk-clean up a NotebookLM account (e.g. test notebooks from automation runs)
Free up the 100-notebook free-tier quota
Remove notebooks no longer covered by your sources
Warning: This is irreversible at the NotebookLM side. Confirm with the user before calling.
Note: Requires authentication. Run setup_auth first if not authenticated.
Inputs: notebook_ids (required), show_browser. Returns: data, error, success
notebook_listARead-onlyIdempotent
Scrape the NotebookLM homepage to get a real list of all notebooks with their IDs and names.
This tool navigates to notebooklm.google.com and extracts:
Notebook ID (UUID from URL)
Notebook name (displayed title)
Notebook URL
Use this to:
Discover notebooks not yet in your library
Get accurate notebook IDs for automation
Verify which notebooks exist in your account
Find notebooks to delete when cleanup is needed
Note: Requires authentication. Run setup_auth first if not authenticated.
Inputs: show_browser. Returns: data, error, success
note_createA
Create a note in the NotebookLM Studio panel.
Notes are user-created annotations that appear in your notebook. Use them to save research findings, summaries, key insights, or any custom content you want to keep alongside your sources.
Notes support markdown formatting for rich text content.
Inputs: title (required), content (required), session_id, notebook_url. Returns: data, error, success
note_getB
Retrieve the full title and text content of a specific note in the NotebookLM Studio panel.
Inputs: note_title (required), note_id, session_id, notebook_url. Returns: data, error, success
note_listB
List all user notes in the NotebookLM Studio panel. Returns note titles, IDs, and timestamps (e.g. details).
Inputs: session_id, notebook_url. Returns: data, error, success
note_save_chatA
Save the current NotebookLM chat/discussion to a note.
This tool extracts all messages from the current conversation (both user questions and NotebookLM AI responses) and saves them as a formatted note in the Studio panel.
Use this to:
Preserve important research conversations
Create a summary of your discussion with NotebookLM
Save chat history before starting a new topic
The note will include timestamps and message attribution (User/NotebookLM).
Inputs: title, session_id, notebook_url. Returns: data, error, success
note_to_sourceA
Convert a note to a source document in NotebookLM.
This feature allows you to convert an existing note into a source, making the note content available for RAG queries and research.
The method:
Finds the note by title in the Studio panel
Attempts to use NotebookLM's native "Convert to source" feature if available
Falls back to extracting note content and creating a text source if not
Use this when you want your note content to be included in NotebookLM's knowledge base for answering questions.
Inputs: note_title (required), session_id, notebook_url. Returns: data, error, success
rename_sourceA
Rename one source inside a notebook. RPC-backed (no browser). Identify the source by source_id (see list_sources) or by source_name — an ambiguous name is refused rather than guessed.
Inputs: title (required), source_id, notebook_id, source_name, +1 more. Returns: data, error, success
research_sourcesA
Discover web sources for a notebook via NotebookLM Fast Research. RPC-backed. Returns the found sources; set import: true to also add them to the notebook.
Inputs: query (required), import, notebook_id, notebook_url. Returns: data, error, success
retry_contentA
Retry a Studio generation that failed, keeping the same content id. RPC-backed. Prefer this over deleting and regenerating: that mints a new id and invalidates every reference you were holding. The artifact goes back to generating; poll list_content for the outcome. A retry can fail again on Google’s side.
Inputs: content_id (required), notebook_id, notebook_url. Returns: data, error, success
revise_slideA
Revise one slide of an existing slide deck from a prompt, instead of regenerating the whole deck. RPC-backed. slide_index is zero-based. The call returns as soon as the revision is accepted; poll list_content for the result.
Inputs: prompt (required), artifact_id (required), slide_index (required), notebook_id, +1 more. Returns: data, error, success
search_passagesA
Find the passages in a notebook’s sources that match a query, ranked best first. RPC-backed (no browser). This is retrieval, not an answer: nothing is generated, no generation quota is spent, and you get the indexed text with its offsets. Prefer this over ask_question when you want the evidence rather than the prose, and when you intend to reason over the passages yourself.
Inputs: query (required), limit, source_ids, notebook_id, +2 more. Returns: data, error, success
server_cleanupADestructive
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:
Legacy Installation (notebooklm-mcp-nodejs) - Old paths with -nodejs suffix
Current Installation (notebooklm-mcp) - Active data, browser profiles, library
NPM/NPX Cache - Cached installations from npx
Claude CLI MCP Logs - MCP server logs from Claude CLI
Temporary Backups - Backup directories in system temp
Claude Projects Cache - Project-specific cache (optional)
Editor Logs (Cursor/VSCode) - MCP logs from code editors (optional)
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:
Ask user to close ALL Chrome/Chromium instances
Run cleanup_data(confirm=false, preserve_library=true) to preview
Run cleanup_data(confirm=true, preserve_library=true) to execute
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. Returns: data, error, success
server_healthARead-onlyIdempotent
Get server health status including authentication state, active sessions, and configuration. Use this to verify the server is ready before starting research workflows.
If authenticated=false and having persistent issues: Consider running cleanup_data(preserve_library=true) + setup_auth for fresh start with clean browser session.
Inputs: no named parameters. Returns: data, error, success
session_closeADestructiveIdempotent
Close a specific session by session ID. Ask before closing if the user might still need it.
Inputs: session_id (required). Returns: data, error, success
session_listARead-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. Returns: data, error, success
session_resetADestructiveIdempotent
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). Returns: data, error, success
source_addA
Add a source (document, URL, text, YouTube video) to the current NotebookLM notebook.
Supported source types:
file: Upload a local file (PDF, DOCX, TXT, etc.). Audio (MP3, M4A…) is transcribed and images (JPG, PNG…) are read, so a voice memo or a photo of a whiteboard becomes a queryable source.
url: Add a web page URL
text: Paste text content directly
youtube: Add a YouTube video URL
google_drive: Add a Google Drive document link
The source will be processed and indexed for use in conversations.
Inputs: source_type (required), url, text, title, +3 more. Returns: data, error, success
source_copyA
Copy some of a notebook’s sources into another existing notebook. RPC-backed. Returns, for each source, its original id and the id of the copy. The target must be named explicitly. Only from a notebook you own (not one shared with you or public). Not idempotent: a failure is never retried automatically.
Inputs: source_ids (required), notebook_id, notebook_url, target_notebook_id, +1 more. Returns: data, error, success
source_deleteADestructive
Delete a source from the current NotebookLM notebook.
You can identify the source to delete by either:
source_id: The unique identifier of the source
source_name: The name/title of the source (partial match supported)
Use list_content first to see available sources and their IDs/names.
WARNING: This action is irreversible. The source will be permanently removed from the notebook.
Inputs: source_id, session_id, source_name, notebook_url. Returns: data, error, success
source_listARead-onlyIdempotent
List the sources of a NotebookLM notebook, with their IDs and titles.
Use this to get the source_id that read_source and delete_source expect. RPC-backed (no browser).
Inputs: notebook_id, notebook_url. Returns: data, error, success
source_readARead-onlyIdempotent
Read a source’s full indexed content — the exact text NotebookLM reasons over, which the web UI only ever shows in fragments.
Use it to quote a source verbatim, to check what was actually ingested from a PDF or web page, or to feed the raw material to another tool. Identify the source by source_id (from list_sources) or by source_name (partial match).
Long sources are paginated by default: you get the first 20,000 characters plus totalChars, nextCursor and a continue instruction telling you exactly how to ask for the rest. Pass cursor to continue, or paginate: false to take the whole document in one call. RPC-backed (no browser).
Inputs: cursor, format, paginate, max_chars, +4 more. Returns: data, error, success
vault_batchA
Run a list of questions against a notebook and persist each answer to disk as two artifacts: {slug}.md (markdown with YAML frontmatter, answer body and cited source excerpts) and {slug}.json (structured payload conforming to the nblm-answer-v1 schema). Designed for one-shot ingestion of a notebook into a searchable markdown vault (e.g. for indexing with RTFM) — every answer keeps titles + highlighted excerpts, so repeat queries no longer need to round-trip through NotebookLM.
Reuses the same browser/session as ask_question — no HTTP server required. Pass sleep_between_ms (1500–3000ms) for batches above ~20 questions to avoid hammering NotebookLM.
Returns per-question file paths, success flags, citation counts and the resolved session id. See the RTFM integration guide for the recommended workflow.
Inputs: questions (required), vault_dir (required), session_id, notebook_id, +4 more. Returns: data, error, success
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 56 tools
Many clusters overlap heavily: library_list vs notebook_list; library_add vs notebook_create vs library_discover; source_list/content_list/note_list; source_delete/content_delete/notebook_delete; content_generate vs generate_study_aid vs generate_mind_map; notebook_ask vs search_passages vs vault_batch. Descriptions also reference tool names that do not exist in this set (get_health, ask_question, add_notebook, list_sources, cleanup_data, setup_auth), which will actively mislead an agent choosing tools.
All names are snake_case, but the ordering convention is mixed: noun_verb (source_delete, content_generate, notebook_copy) alongside verb_noun (delete_chat_history, get_source_guide, generate_mind_map). Some names are vague or omit the domain noun entirely (vault_batch, manage_labels, share_notebook), though most remain readable.
56 tools is an extreme overshoot for a single NotebookLM integration and spans library management, browser auth, cleanup, sessions, sources, Studio artifacts, notes, research, and usage. Many operations could be consolidated or moved behind a smaller set of parameterized tools.
The surface is unusually comprehensive: notebook lifecycle, source ingestion/reading/deletion/copying, Studio generation/export/download, notes, chat, research, labels, sharing, auth, cleanup, and usage are all represented. Minor gaps remain, such as no direct NotebookLM-side notebook rename and several Studio content types explicitly marked as not implemented.
Maintenance
Related MCP Connectors
n8n MCP — query your own n8n instance (BYO).
MCP-native notes and memory for ChatGPT, Claude, and other AI tools.
Private persistent memory for Claude, ChatGPT & Gemini via MCP - semantic search, zero-code setup.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Related MCP Servers
- AlicenseAqualityBmaintenanceProvides CLI and MCP server to programmatically access Google NotebookLM, enabling AI assistants to create notebooks, add sources, generate podcasts, and more, with support for both personal and enterprise accounts.41MIT
- AlicenseNot gradedqualityDmaintenanceMCP server that lets CLI agents (Claude, Codex, Cursor) chat directly with Google NotebookLM for zero-hallucination answers based on user's own notebooks.MIT
- AlicenseAqualityDmaintenanceA thin MCP wrapper around the unofficial Google NotebookLM Python client, enabling notebook management, source handling, chat, artifact generation, deep research, and sharing via MCP tools.39MIT
- AlicenseNot gradedqualityCmaintenanceEnables interaction with Google NotebookLM through a unified CLI and MCP server, featuring automatic multi-browser authentication and support for notebook queries, source management, notes, and audio generation.MIT