NotebookLMSAFE
Bridge Google NotebookLM with Claude via MCP. Full programmatic access to create notebooks, manage sources, and generate AI-powered content — podcasts, videos, slides, mind maps, quizzes, flashcards, and reports — all through natural language.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A powerful MCP (Model Context Protocol) server that brings Google NotebookLM into Claude Desktop and Claude Code.
Features
- Research: List and create notebooks
- Content: Add URLs, text, and files as sources
- Generation: Create Podcasts, Videos, Slides, Mind Maps, Infographics, Quizzes, Flashcards, and Reports
- Natural Interaction: Chat directly with your sources using Claude's reasoning
Prerequisites
1. Install uv (Python Package Manager)
macOS / Linux
# Using curl curl -LsSf https://astral.sh/uv/install.sh | sh # Or with Homebrew (macOS) brew install uv
Default install location: ~/.local/bin/uv
Windows
# Using PowerShell powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex" # Or with Scoop scoop install uv # Or with winget winget install --id=astral-sh.uv -e
Default install location: %USERPROFILE%\.local\bin\uv.exe
Verify installation:
uv --version
2. Clone and Install Dependencies
# Clone the repository git clone https://github.com/alfredang/notebooklm-mcp.git # Navigate to the project folder cd notebooklm-mcp # Install dependencies (includes notebooklm-py and fastmcp) uv sync
This will:
- Create a
.venvvirtual environment - Install notebooklm-py (Python client for NotebookLM API)
- Install fastmcp (MCP server framework)
Note: These dependencies are required for both Claude Desktop and Claude Code.
Step 1: Authenticate with NotebookLM
NotebookLM uses browser-based authentication. You must login once to save your session cookies.
cd notebooklm-mcp uv run notebooklm login
What happens:
- A browser window will open automatically
- Log in to your Google account
- Navigate to NotebookLM if not redirected automatically
4.
8cadb0226496OBSERVED · 2026-10-08Connect
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-assistant -- uvx notebooklm-assistant
{
"mcpServers": {
"notebooklm-assistant": {
"command": "uvx",
"args": [
"notebooklm-assistant"
]
}
}
}Exposed tools (15)
12 read · 3 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
add_source_text | write | Add raw text as a source to a notebook. |
add_source_url | write | Add a website URL as a source to a notebook. |
ask_notebook | read | Ask a question based on the sources in a specific notebook. |
create_notebook | write | Create a new notebook with the given title. |
generate_audio_overview | read | |
generate_data_table | read | |
generate_flashcards | read | |
generate_infographic | read | |
generate_mind_map | read | |
generate_quiz | read | |
generate_slide_deck | read | |
generate_summary_report | read | |
generate_video_overview | read | |
get_notebook_summary | read | Get the summary and key insights of a notebook. |
list_notebooks | read | List all notebooks in your NotebookLM account. |
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 | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (5)
1. Open System Properties → Environment Variables
Add to your shell profile (`~/.zshrc` or `~/.bashrc`):
Add to your PATH:
curl -LsSf https://astral.sh/uv/install.sh | sh
Gates applied: no_behavioural_pass, no_license.
8cadb0226496full audit observations/trust-audit/mcp-server/alfredang__notebooklm-6.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 |
|---|---|---|---|---|---|
| 2026-10-08 | 8cadb0226496 | SAFE | B | 89 | first audit |
Questions
What is the NotebookLM MCP server?
Bridge Google NotebookLM with Claude via MCP. Full programmatic access to create notebooks, manage sources, and generate AI-powered content — podcasts, videos, slides, mind maps, quizzes, flashcards, and reports — all through natural language.
What tools does NotebookLM expose?
15 in total: 12 read-only, 3 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is NotebookLM 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.
What credentials does NotebookLM need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (8cadb0226496), read on 2026-10-08. The repository is watched and re-audited when it changes.