roomi-fields/notebooklm-mcp

๐Ÿง  Knowledge & Memory
0 Views
0 Installs

๐Ÿ“‡ ๐Ÿ  ๐ŸŽ ๐ŸชŸ ๐Ÿง - Full automation of Google NotebookLM โ€” Q&A with citations, audio podcasts, video, content generation, source management, and notebook library. MCP + HTTP REST API.

Quick Install

One-Click IDE Configuration
claude_desktop_config.json
{
  "mcpServers": {
    "roomi-fields-notebooklm-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "roomi-fields-notebooklm-mcp"
      ]
    }
  }
}
Or

Using an AI coding agent (Claude Code, Cursor, etc.)? Copy a ready-made prompt that tells it to fetch the setup instructions and install this server for you.

Documentation Overview

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 ยท video ยท infographic ยท report ยท presentation ยท data table), multi-account rotation with auto-reauth across personal and Google Workspace accounts.

v2.2.1 โ€” production-grade, batch-tested on overnight runs of 1 000+ questions. Tools are now a namespaced tree (notebook_ask, source_add, session_listโ€ฆ) with MCP annotations + outputSchema on every tool โ€” the old flat names still work as aliases, nothing breaks. See the changelog for the full mapping. Compare with PleasePrompto/notebooklm-mcp v2.0.0 to see when this project is the right pick (REST API, full Studio, auto-reauth) and when the MCP-only upstream is.

CI npm version npm downloads codecov License: MIT TypeScript Node.js

MCP Claude Code n8n GitHub


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 TypeFormatsOptions
Audio OverviewPodcast-style discussionLanguage (80+), custom instructions
VideoBrief, Explainer6 visual styles, language, custom instructions
InfographicHorizontal, VerticalLanguage, custom instructions
ReportSummary, DetailedLanguage, custom instructions
PresentationOverview, DetailedLanguage, custom instructions
Data TableSimple, DetailedLanguage, custom instructions

Video Visual Styles: classroom, documentary, animated, corporate, cinematic, minimalist

Content Download

  • Download Audio โ€” WAV audio files
  • Download Video โ€” MP4 video files
  • Download Infographic โ€” 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

Accounts & Localization

  • Personal and Google Workspace accounts โ€” recognizes both NotebookLM hosts (notebooklm.google.com and the notebook.google.com Workspace alias), so Workspace sessions authenticate cleanly instead of looping on "session expired"
  • UI-language-aware โ€” drives NotebookLM whether its interface is in English, French, German, or Japanese (en ยท fr ยท de ยท ja); add a language in a single JSON file

Integration Options

  • MCP Protocol โ€” Claude Code, Cursor, Codex, any MCP client
  • HTTP REST API โ€” n8n, Zapier, Make.com, custom integrations
  • Docker โ€” Isolated deployment with Docker or Docker Compose
  • RTFM retrieval layer โ€” /batch-to-vault writes citation-backed answers as markdown + JSON sidecars (nblm-answer-v1 schema), indexable by RTFM (FTS5 + semantic) for unlimited offline queries. Ideal for academic / SOTA workflows. Guide.

Quick Start

Option 0 โ€” 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 โ€” see RTFM integration guide):

/plugin marketplace add roomi-fields/claude-plugins
/plugin install notebooklm@roomi-fields

That registers the MCP server, runs npx -y @roomi-fields/notebooklm-mcp@<pinned-version> automatically (Node โ‰ฅ 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 โ€” 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 โ€” see the REST API reference. For overnight batches of 1 000+ questions, see the batch pattern.

Option 2 โ€” 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 โ€” add to ~/.cursor/mcp.json
{
  "mcpServers": {
    "notebooklm": {
      "command": "node",
      "args": ["/path/to/notebooklm-mcp/dist/index.js"]
    }
  }
}

Then say: "Log me in to NotebookLM" โ†’ Chrome opens โ†’ log in with Google.

Option 3 โ€” 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 window

See Docker Guide for NAS deployment (Synology, QNAP).


Documentation

Full docs site: https://roomi-fields.github.io/notebooklm-mcp/ ยท OpenAPI 3.1 spec

GuideDescription
InstallationStep-by-step setup for HTTP and MCP modes
ConfigurationEnvironment variables and security
REST API referenceComplete HTTP endpoint documentation (33 endpoints)
Run 1 000 questions overnightProduction batch pattern with auto-reauth and rotation
RTFM integration โ€” cache as searchable vaultPipeline pattern: NotebookLM as one-shot ingestion, RTFM as retrieval layer. /batch-to-vault endpoint, nblm-answer-v1 schema.
n8n integrationWorkflow automation setup
TroubleshootingCommon issues and solutions
Notebook libraryMulti-notebook management
Auto-discoveryAutonomous metadata generation
Content managementAudio, video, infographic, report, presentation
Multi-account rotationMultiple accounts with TOTP auto-reauth
DockerDocker and Docker Compose deployment
Multi-interfaceRun Claude Desktop + HTTP simultaneously
Compare with PleasePrompto v2.0.0Feature matrix vs the upstream MCP-only server
Chrome profile limitationProfile locking (solved in v1.3.6+)
Adding a languagei18n system for multilingual UI support

Roadmap

See ROADMAP.md for planned features and version history.

Latest releases:

  • v2.2.1 โ€” Recognize both NotebookLM hosts so Google Workspace accounts authenticate (the notebook.google.com alias); notebook listing no longer wastes ~30s after the "Gemini Notebook" rebrand; HTTP banner reads the real version. Diagnosis + patch by @kpietkaa (#19)
  • v2.2.0 โ€” Fix new-answer detection timing out when an answer repeats an earlier one (position-based identity, not text-hash); graceful shutdown on stdio disconnect; Japanese UI locale
  • v2.1.1 โ€” Thai UI selectors for notebook_create (partial, #18)
  • v2.1.0 โ€” note_list and note_get MCP tools (#17)
  • v2.0.4 โ€” German UI selectors (closes #14)
  • v2.0.0 โ€” Tools renamed to a namespaced tree (notebook_ask, source_add, session_list, server_health, vault_batchโ€ฆ) across 9 namespaces; tools/list advertises only the canonical names. Backward compatible โ€” the legacy flat names still work as aliases, so existing scripts and configs keep running. Also adds MCP annotations (read-only / destructive / idempotent / open-world hints) and outputSchema + structuredContent on every tool. Published on the Smithery registry.
  • v1.7.0 โ€” batch_to_vault exposed as a first-class MCP tool (parity with the HTTP endpoint, no localhost server required); shared runBatchToVault helper deduplicates the loop across both transports
  • v1.6.0 โ€” /batch-to-vault endpoint + RTFM integration (nblm-answer-v1 JSON Schema published at schemas.roomi-fields.com/nblm-answer-v1.json) for caching NotebookLM answers as a searchable markdown vault
  • v1.5.8 โ€” NotebookLM 2026 UI adaptations (icon-label sanitization, Discussion-panel recovery, count-based source detection) โ€” PR #5 by @KhizarJamshaidIqbal
  • v1.5.7 โ€” Citation extraction selector fix (.highlighted) and Docker multi-stage build โ€” PR #1 by @JulienCANTONI
  • v1.5.6 โ€” Citation extraction major rewrite (97% success rate), browser-verified auth at startup, profile auto-sync
  • v1.5.0 โ€” Complete Studio content generation (video, infographic, presentation, data_table) + Notes management + Delete sources
  • v1.4.0 โ€” Content management (sources, audio, generation) + Multi-account

Intermediate patch and hardening releases (1.5.xโ€“1.7.x) are in the full CHANGELOG.

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 โ€” 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 โ€” Use freely in your projects. See LICENSE.

Author

Romain Peyrichou โ€” @roomi-fields


Full Disclaimer

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

โญ Star on GitHub if this saves you debugging time!

Related MCP Servers

modelcontextprotocol/server-memoryVerified

๐Ÿ“‡ ๐Ÿ  - Knowledge graph-based persistent memory system for maintaining context

๐Ÿง  Knowledge & Memory2 views
0xshellming/mcp-summarizer

๐Ÿ“• โ˜๏ธ - AI Summarization MCP Server, Support for multiple content types: Plain text, Web pages, PDF documents, EPUB books, HTML content

๐Ÿง  Knowledge & Memory0 views
20alexl/claude-engram

๐Ÿ ๐Ÿ  - Persistent memory and session intelligence for Claude Code. Auto-tracks mistakes, decisions, and context via hooks. Mines session history for patterns and cross-session search. Loop detection, pre-edit warnings, context compaction survival. Runs locally with Ollama.

๐Ÿง  Knowledge & Memory0 views
a2cr/a2cr

๐Ÿ โ˜๏ธ ๐Ÿ  ๐ŸŽ ๐ŸชŸ ๐Ÿง - MCP server for AI-agent handoffs. Saves client-encrypted WorkBaton checkpoints and WorkStash notes so Codex, Claude Code, Roo Code, and other MCP clients can resume work without passing full chat history.

๐Ÿง  Knowledge & Memory0 views

Engagement

Views
0
Installs
0
Upvotes
0

Views and upvotes are unique per visitor network (hashed IP). Installs count copy actions.

Status

Health: Not checked yet

We have not completed a health check for this listing yet.

No check timestamp yet.

Unclaimed listing (imported or pending owner verification). Claim it โ†’
โ˜… Spotlight Slot

Feature Your MCP Server

Get maximum visibility for your server across our directory, search results, and detail pages.

Spotlight Your Server

Own this project?

This directory is pre-filled from public sources. Claim via GitHub README, site badge, or DNS TXT to get the verified badge and attach your website.

Claim this listing

Promote this listing

Optional paid placement. Free listings stay free forever.

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.