notebooklm-mcp-serverSAFE
Universal installer and configuration guide for NotebookLM MCP server.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
NotebookLM MCP Server
Give your AI agents full control of Google Gemini Notebook (formerly NotebookLM): grounded answers, deep research, podcasts, quizzes, and more — 47 tools, zero hallucinations.
English • Español • Français • Português • Deutsch
2721c633abd5OBSERVED · 2026-10-12Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add notebooklm-mcp-server -- npx -y [email protected]
{
"mcpServers": {
"notebooklm-mcp-server": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (47)
17 read · 23 write · 7 destructive. Blast radius: 7 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
artifact_content_get | read | Get a completed artifact |
artifact_export | read | Export an artifact to the user |
artifact_rename | write | Rename a studio artifact |
audio_overview_create | write | Generate an Audio Overview (podcast) for the notebook |
chat_configure | read | Configure notebook chat settings (goal, response length) |
chat_history_delete | destructive | Delete the notebook |
chat_history_get | read | Get the notebook |
data_table_create | write | Generate a data table from notebook sources |
flashcards_create | write | Generate flashcards from notebook sources (retrieve with artifact_content_get once completed) |
infographic_create | write | Generate an infographic from notebook sources |
mind_map_delete | destructive | Delete a Mind Map from a notebook |
mind_map_generate | read | Generate a Mind Map JSON from notebook sources |
mind_map_list | read | List all Mind Maps in a notebook |
mind_map_save | write | Save a generated Mind Map to a notebook |
note_create | write | Create a note in a notebook (user-written content, distinct from AI artifacts) |
note_delete | destructive | Delete a note from a notebook. IRREVERSIBLE. |
note_list | read | List all notes in a notebook (excludes mind maps) |
note_update | write | Update a note |
notebook_add_drive | write | Add a Google Drive document as a source |
notebook_add_local_file | write | Add a local PDF or text/markdown file as a source |
notebook_add_text | write | Add pasted text as a source to a notebook |
notebook_add_url | write | Add a URL (website or YouTube) as a source to a notebook |
notebook_create | write | Create a new notebook |
notebook_delete | destructive | Delete a notebook permanently. IRREVERSIBLE. |
notebook_get | read | Get full details of a notebook: title, sources with IDs, metadata |
notebook_list | read | List all notebooks with their sources and metadata |
notebook_query | read | Ask AI about EXISTING sources in a notebook. NOT for finding new sources. |
notebook_rename | write | Rename a notebook |
notebook_share | destructive | Manage notebook sharing: toggle public link access, or grant/update/remove a collaborator by email |
notebook_share_status | read | Get a notebook |
notebook_summarize | read | Get the AI-generated notebook guide: overall summary plus suggested questions |
prompts_suggest | read | Get AI-suggested prompts/questions to ask about a notebook |
quiz_create | write | Generate an interactive quiz from notebook sources (retrieve with artifact_content_get once completed) |
refresh_auth | write | Reload authentication cookies from disk. Run |
report_create | write | Generate a written report from notebook sources |
research_import | write | Import discovered research sources into a notebook |
research_poll | read | Poll for research status and results |
research_start | write | Start web or Drive research to find NEW sources. Workflow: research_start → research_poll → research_import |
slide_deck_create | write | Generate a slide deck from notebook sources |
source_check_freshness | read | Check whether a URL/Drive source has newer content available (use source_sync to refresh) |
source_delete | destructive | Delete a source permanently. IRREVERSIBLE. |
source_get_guide | read | Get the AI-generated guide for a source (summary and key topics) |
source_rename | write | Rename a source |
source_sync | write | Sync a Google Drive source to get the latest content |
studio_delete | destructive | Delete a studio artifact |
studio_poll | read | Check status of studio artifacts (Audio, Video, Report, etc.) |
video_overview_create | write | Generate a Video Overview for the notebook |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (2 observation(s))
- Shell
- declared (1 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
chat_history_delete, mind_map_delete, note_delete, notebook_delete, notebook_share, source_delete, studio_delete
@modelcontextprotocol/sdk, axios, chalk, commander, dotenv, ora, pdf-parse, playwright
Gates applied: no_behavioural_pass.
2721c633abd5full audit observations/trust-audit/mcp-server/moodrobotics__notebooklm-mcp-server.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | 2721c633abd5 | SAFE | B | 89 | first audit |
Questions
What is the notebooklm-mcp-server MCP server?
Universal installer and configuration guide for NotebookLM MCP server.
What tools does notebooklm-mcp-server expose?
47 in total: 17 read-only, 23 that write, and 7 that can delete or overwrite (chat_history_delete, mind_map_delete, note_delete, notebook_delete, notebook_share). Every one is listed on this page with its risk.
Is notebooklm-mcp-server safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 7 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does notebooklm-mcp-server need?
No credential environment variables were found in its source, so it appears to need none.
How does notebooklm-mcp-server run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as notebooklm-mcp-server at 4.0.2.
How current is this page?
The grade is for one exact copy of the source (2721c633abd5), read on 2026-10-12. The repository is watched and re-audited when it changes.