π¦
Kof Notebooklm MCP
MCP server for Google NotebookLM
0 installs
2 stars
1 forks
Trust: 56 β Fair
Devtools
Installation
npx kof-notebooklm-mcpAsk AI about Kof Notebooklm MCP
Powered by Claude Β· Grounded in docs
I know everything about Kof Notebooklm MCP. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Loading tools...
Reviews
Documentation
kof-notebooklm-mcp
MCP Server for Google NotebookLM β Create notebooks, add sources, and query AI with citations directly from your IDE.
π§ Part of the KOF-LocalBrain ecosystem
β Support this project
If this project helps you, you can support development here:
π https://buymeacoffee.com/keeponfirst
Features
- π Create Notebooks β Programmatically create and name NotebookLM notebooks
- π Add Sources β Upload URLs or paste text directly into notebooks
- π¬ Ask Questions β Query the AI and get answers with source citations
- π List & Inspect β Browse notebooks and their sources
- π Persistent Auth β Login once, reuse session across runs
Installation
pip install kof-notebooklm-mcp
Post-install Setup
# Install Playwright browsers
playwright install chromium
# Initialize authentication (opens browser for Google login)
kof-notebooklm-init
Quick Start
As MCP Server
Add to your MCP configuration (mcp_config.json):
{
"mcpServers": {
"notebooklm": {
"command": "kof-notebooklm-mcp",
"args": []
}
}
}
Available Tools
| 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 |
Example Usage (via MCP client)
# 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"])
Configuration
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 |
Development
git clone https://github.com/keeponfirst/kof-notebooklm-mcp.git
cd kof-notebooklm-mcp
pip install -e ".[dev]"
pytest
License
MIT License - see LICENSE for details.
Related Projects
- KOF-LocalBrain β Local-first brain capture system
- Model Context Protocol β The standard for AI tool integration
