notebooklm MCP
About
Chat with Google NotebookLM via MCP or HTTP REST API for zero-hallucination answers from your docs. Perfect for n8n workflows and automation.
Details
- Author
- roomi-fields
- Categories
- Productivity, Knowledge Base, Other
Jump to
Setup
Install notebooklm MCP in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/roomi-fields/notebooklm-mcp
Follow the installation instructions in the repository README, then restart your MCP client.
Import web pages and YouTube videos to NotebookLM with one click. Trusted by 200,000+ users.
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 across personal and Google Workspace accounts.
v3.1.0 —major refactor: dual transport.The data plane now drives NotebookLM'sinternalbatchexecuteRPC API(the same one the web app calls) instead of scraping the DOM —immune to UI rebrands, 10-100× faster(list notebooks ~1 s vs ~30 s, generate a report ~13 s vs minutes), and more correct. The Playwright browser is kept as anautomatic fallback(NOTEBOOKLM_TRANSPORT=domforces it) plus login / auto-reauth, so nothing breaks if an internal endpoint shifts —both paths ship permanently for robustness. Adds5 new tools: notebook sharing, study aids (flashcards / quiz), mind maps, source labels, and web research / source discovery. Still batch-tested on overnight runs of 1 000+ questions. See thechangelog.Compare withPleasePrompto/notebooklm-mcpfor when this project is the right pick (REST API, full Studio, auto-reauth).
Note (July 2026):Google rebrandedNotebookLMtoGemini Notebook. It is the same product, existing links redirect, and this project drives the same underlying service — the browser path was updated for the new DOM in v2.3.0 and the RPC path in v3.0.0. Package and repository keep thenotebooklmname.
Unofficial project — good to know before you start
This is not affiliated with Google. It talks to the samebatchexecuteendpoints the NotebookLM web app uses, with a browser fallback when they move. They are undocumented, so they can change without notice — when that happens we ship a fix, as we have for every change so far.
Two practical notes: use adedicated Google accountfor automation, and expect NotebookLM's own quotas to apply at high volume. SeeDisclaimerfor the full text.
🔗No-code automation pipelines— The 33-endpoint REST API means NotebookLM becomes a step in n8n, Zapier, Make, or a plaincurlin cron. No agent, no MCP client, no Node in your stack — just HTTP. This is the half most NotebookLM libraries don't have.
🤖Agent tooling— The same engine over MCP for Claude Code, Cursor and Codex, with a bundled skill that primes the agent on citation formats, the daily-quota-aware batch pattern, and transport selection.
📚Research at volume— Multi-account rotation with automatic re-authentication, built for overnight runs of 1 000+ questions across several notebooks without babysitting.
🎙️Full Studio generation— Audio overviews, video, infographics, reports, presentations, data tables, plus flashcards, quizzes and mind maps — generated and downloaded programmatically.
NotebookLM is agroundedengine: Gemini reads your sources and answersfrom them, with citations. The winning pattern is to let it do the expensive reading while your own stack handles orchestration and the last mile.
Spend fewer tokens — offload the reading
- 🪙 Zero-token synthesis layer— Drop 30 documents in a notebook, let Gemini do the heavy analysis, and spend your agent's context only on the final polish. The reasoning happens server-side; your agent just orchestrates (add_notebook→source_add→notebook_ask).
- 💾 Answer cache you can re-read offline—vault_batchwrites every answer to disk as structured JSON against a publishedschema, so a batch run becomes a corpus you can grep, diff, re-index, or feed to a retrieval layer — without re-querying and re-spending quota.
Wire it into things that aren't agents
- ⚙️ NotebookLM as an n8n / Zapier / Make step— Because it speaks plain HTTP, a citation-backed answer becomes one node in a workflow: a form submission triggers a question, the cited answer lands in a sheet, a Slack message, or a database. No agent runtime involved.
- 📄 Document intake pipeline— Watch a folder or an inbox, push new PDFs and URLs in as sources, and ask a standing set of questions against them on every arrival.
- 🔍 Citations with the actual source text— Answers come back with source namesand the quoted excerptsthey rest on, extracted from the citation panel — so a claim can be checked, not just attributed.
- 🎓 Literature review at thesis scale— Batch 100+ research questions across multiple notebooks, rotate accounts as daily quotas run out, and resume where it stopped. Built for, and tested on, exactly this.
- 🔁 One source set, every format— Fan a single notebook out to a podcast, a video, a slide deck, a report, a quiz and a mind map, then download them all locally.
-
📚 A doctoral literature review at batch scale— The project was built for, and is continuously tested on, overnight runs of1 000+ research questionsspread across several notebooks: multi-account rotation picks up when a daily quota runs out, every answer is written to disk with its citations, and an interrupted run resumes instead of starting over. The batch pattern invault_batchexists because a thesis needed it.
🔌 Replacing a RAG engine with the REST API—musnymubarak/Calim_Docswapped a Gemini-based retrieval engine for this project's HTTP API, running it as a Docker service (notebooklm:3000) behind a full client and worker layer. A good illustration of the REST half: no agent runtime, no MCP client — NotebookLM simply became a backend service their Python app calls.
Built something with it? Open an issue — this section is for other people's work.
- Ask questionsto NotebookLM and get accurate, citation-backed answers
- Source citation extractionwith 5 formats: none, inline, footnotes, json, expanded (97% excerpt success rate)
- Session managementfor multi-turn conversations with auto-reauth on session expiry
Generate multiple content types from your notebook sources:
Video Visual Styles: classroom, documentary, animated, corporate, cinematic, minimalist
Flashcards and quizzes are generated viagenerate_study_aid; mind maps viagenerate_mind_map. v3 also addsshare_notebook,manage_labels, andresearch_sources(web/Drive source discovery) — see the[changelog.
- 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
- Add sources: Files (PDF, TXT, DOCX), URLs, Text, YouTube videos, Google Drive
- List sources: Every source with its ID and title (source_list)
- Read a source in full(source_read): the exact text NotebookLM indexed — what it actually reasons over, which the web UI only shows in fragments. Quote a source verbatim, check what a PDF really yielded, or hand the raw material to another tool. Name the source instead of its ID if you prefer; an ambiguous name is refused rather than guessed. Long sources arriveone page at a time, with an explicit instruction for fetching the next — orpaginate: falsefor the whole document at once.
- Multi-notebook managementwith validation and smart selection
- Auto-discovery: Automatically generate metadata via NotebookLM queries
- Search notebooksby keyword in name, description, or topics
- Scrape notebooks: List all notebooks from NotebookLM with IDs and names
- Bulk delete: Delete multiple notebooks at once
…
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
