Google's Gemini Notebook (renamed from NotebookLM in July 2026) is the best grounded-answer engine on the market: it only answers from the sources you give it, with citations. This MCP server hands…
notebooklm-mcp-server is an MCP project maintained in the moodrobotics/notebooklm-mcp-server repository. The maintainer describes its purpose as “Google's Gemini Notebook (renamed from NotebookLM in July 2026) is the best grounded-answer engine on the market: it only answers from the sources you give…”. Read the project documentation for the complete scope.
The documented npm package is notebooklm-mcp-server. The configuration below comes from the maintainer’s example; adapt its paths and account values to your environment.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| notebook_list | List all notebooks with sources and metadata |
| notebook_create | Create a new notebook |
| notebook_get | Get one notebook's details and source IDs |
| notebook_rename | Rename a notebook |
| notebook_delete | Delete a notebook (requires confirm) |
| notebook_summarize | AI notebook guide: summary + suggested questions |
| prompts_suggest | AI-suggested prompts to ask about the sources |
| notebook_share | Toggle public link and/or manage collaborators by email |
| notebook_share_status | Read the current sharing configuration |
| notebook_add_url | Add a website or YouTube video as a source |
| notebook_add_text | Add pasted text as a source |
| notebook_add_drive | Add a Google Drive document as a source |
| notebook_add_local_file | Upload a local PDF / TXT / Markdown file |
| source_get_guide | AI guide for one source: summary + key topics |
| source_rename | Rename a source |
| source_check_freshness | Check if a URL/Drive source has newer content |
| source_sync | Re-sync a Drive source to the latest content |
| source_delete | Delete a source (requires confirm) |
| notebook_query | Ask questions about the sources, with citations |
| chat_history_get | Read the latest conversation's Q&A turns |
| chat_history_delete | Clear the chat history (requires confirm) |
| chat_configure | Set the chat persona (default / learning guide / custom) and response length |
| research_start | Launch web or Drive research (fast ≈30s / deep ≈5min) |
| research_poll | Check research progress and discovered sources |
| research_import | Import the discovered sources into the notebook |
| audio_overview_create | Podcast-style Audio Overview (formats: deep dive, brief, critique, debate) |
| video_overview_create | Video Overview (9 visual styles, from whiteboard to anime) |
| report_create | Written report from the sources |
| flashcards_create | Flashcards (quantity and difficulty options) |
| quiz_create | Interactive quiz (quantity and difficulty options) |
| infographic_create | Infographic (landscape / portrait / square) |
| slide_deck_create | Slide deck |
| data_table_create | Structured data table |
| studio_poll | Check generation status of all artifacts |
| studio_delete | Delete a studio artifact |
| artifact_content_get | Fetch generated content (quiz/flashcards HTML, mind map JSON) |
| artifact_rename | Rename an artifact |
| artifact_export | Export an artifact to Google Drive (Docs or Sheets) |
| note_create | Create a note |
| note_list | List all notes |
| note_update | Update a note's content/title |
| note_delete | Delete a note (requires confirm) |
| mind_map_generate | Generate a mind map JSON from sources |
| mind_map_save | Save a mind map to the notebook |
| mind_map_list | List saved mind maps |
| mind_map_delete | Delete a mind map |
| refresh_auth | Reload session cookies from disk after re-running auth |
{
"mcpServers": {
"notebooklm": {
"command": "npx",
"args": [
"-y",
"notebooklm-mcp-server",
"start"
]
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Enables Large Language Models to interact with Anki flashcard software through AnkiConnect using the Model Context Protocol.
Demonstrates building an AI agent using the Model Context Protocol (MCP) with open LLMs like Meta Llama 3, OpenAI, or Google Gemini, and a SQLite
Manages courses, assignments, enrollments, and grades within Canvas using the Canvas API.
Manage educational context based on courses, assignments, and exams using a knowledge graph.
Source profile for Acornonaut. Its purpose and connection details need verification against the maintainer’s documentation.
Model Context Procotol (MCP) server with tools for Cannabis Datasets.