Kof Notebooklm Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Kof Notebooklm Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
MCP Server for Google NotebookLM — Create notebooks, add sources, and query AI with citations directly from your IDE.
🧠 Part of the KOF-LocalBrain ecosystem
If this project helps you, you can support development here:
👉 https://buymeacoffee.com/keeponfirst
<a href="https://www.buymeacoffee.com/keeponfirst" target="_blank"> <img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" height="45" /> </a>
pip install kof-notebooklm-mcp# Install Playwright browsers
playwright install chromium
# Initialize authentication (opens browser for Google login)
kof-notebooklm-initAdd to your MCP configuration (mcp_config.json):
{
"mcpServers": {
"notebooklm": {
"command": "kof-notebooklm-mcp",
"args": []
}
}
}| Tool | Description |
|---|---|
health_check | Verify connection and auth status |
list_notebooks | List all notebooks |
create_notebook | Create a new notebook (with optional title) |
get_notebook | Get notebook details |
list_sources | List sources in a notebook |
add_source | Add URL or text source |
ask | Query notebook AI with citations |
# Create a research notebook
result = await mcp.call_tool("create_notebook", {"title": "Market Research 2026"})
notebook_id = result["notebook_id"]
# Add a source
await mcp.call_tool("add_source", {
"notebook_id": notebook_id,
"source_type": "url",
"url": "https://example.com/report.pdf"
})
# Ask a question
answer = await mcp.call_tool("ask", {
"notebook_id": notebook_id,
"question": "What are the key market trends?"
})
print(answer["answer"])
print(answer["citations"])Environment variables (optional):
| Variable | Description | Default |
|---|---|---|
KOF_NOTEBOOKLM_HEADLESS | Run browser in headless mode | true |
KOF_NOTEBOOKLM_PROFILE_DIR | Browser profile directory | ~/.kof-notebooklm/profile |
git clone https://github.com/keeponfirst/kof-notebooklm-mcp.git
cd kof-notebooklm-mcp
pip install -e ".[dev]"
pytestMIT License - see LICENSE for details.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.