OpenClaw NotebookLM Integration
One-command installer for integrating Google NotebookLM with OpenClaw via MCP.
What This Does
This package automatically sets up a NotebookLM skill in OpenClaw, allowing your AI agents to:
- 📚 List all your NotebookLM notebooks
- 📝 Create new notebooks with sources
- 🔍 Query notebooks with natural language
- 📊 Generate study guides
- 🔗 Add sources (URLs, text, files) to notebooks
Quick Start
Installation
pip install openclaw-notebooklm
Setup
Run the installer:
openclaw-notebooklm-install
The installer will:
- ✅ Check prerequisites (OpenClaw, Node.js)
- 📦 Install dependencies (mcporter, notebooklm-mcp)
- 🔐 Authenticate with NotebookLM (opens Chrome)
- 📂 Create the skill in
~/.openclaw/skills/notebooklm/ - ⚙️ Configure OpenClaw to use the skill
- 🔄 Restart the OpenClaw daemon
That's it! 🎉
Usage
From OpenClaw Agents
Start a new OpenClaw session and ask:
List my NotebookLM notebooks
Create a NotebookLM notebook called "AI Research" with this URL: https://example.com
Ask my "Project Notes" notebook: What are the key takeaways?
Generate a study guide for my "Machine Learning" notebook
From Command Line
# List notebooks
~/.openclaw/skills/notebooklm/notebooklm.sh list
# Create a notebook
~/.openclaw/skills/notebooklm/notebooklm.sh create "My Notebook" source_url=https://example.com
# Query a notebook
~/.openclaw/skills/notebooklm/notebooklm.sh ask <notebook-id> "Summarize this"
# Generate study guide
~/.openclaw/skills/notebooklm/notebooklm.sh study_guide <notebook-id>
Requirements
- OpenClaw: Must be installed and configured
- Node.js: Required for npm packages (mcporter, notebooklm-mcp)
- Google Account: For NotebookLM authentication
How It Works
graph LR
A[OpenClaw Agent] --> B[notebooklm skill]
B --> C[notebooklm.sh wrapper]
C --> D[mcporter]
D --> E[notebooklm-mcp server]
E --> F[NotebookLM API]
- OpenClaw loads the
notebooklmskill - The skill uses a wrapper script to route commands
- mcporter manages the MCP server lifecycle
- notebooklm-mcp communicates with NotebookLM
- Responses flow back to the agent
Troubleshooting
Skill not visible to agent
Problem: Agent says "I don't have the notebooklm skill"
Solution:
- Exit your current OpenClaw session
- Start a new session (skills are snapshot at session start)
Authentication expired
Problem: "Error: Not authenticated to NotebookLM"
Solution:
notebooklm-mcp-auth
mcporter not found
Problem: "mcporter: command not found"
Solution:
npm install -g mcporter
Permission denied
Problem: Can't access mcporter config
Solution: The installer places config at ~/.openclaw/mcporter.json which is accessible. If you move it, update the path in ~/.openclaw/openclaw.json:
{
"skills": {
"entries": {
"notebooklm": {
"env": {
"MCPORTER_CONFIG": "/path/to/your/mcporter.json"
}
}
}
}
}
File Locations
After installation:
~/.openclaw/
├── skills/
│ └── notebooklm/
│ ├── SKILL.md # Skill metadata
│ └── notebooklm.sh # Wrapper script
├── mcporter.json # mcporter config
└── openclaw.json # Updated with skill entry
~/.notebooklm-mcp/
└── auth.json # NotebookLM auth tokens
Development
Local Installation
git clone https://github.com/elihat2022/openclaw-notebooklm.git
cd openclaw-notebooklm
pip install -e .
Run Installer
openclaw-notebooklm-install
Uninstall
# Remove the skill
rm -rf ~/.openclaw/skills/notebooklm
# Remove config entries (manual edit)
# Edit ~/.openclaw/openclaw.json and remove the "notebooklm" entry
# Restart daemon
openclaw daemon restart
Contributing
Contributions welcome! Please:
- Fork the repository
- Create a feature branch
- Make your changes
- Submit a pull request
License
MIT License - see LICENSE file for details.
Credits
- OpenClaw: https://docs.openclaw.ai
- mcporter: https://github.com/steipete/mcporter
- notebooklm-mcp: https://github.com/jacob-bd/notebooklm-mcp-cli
- Model Context Protocol: https://modelcontextprotocol.io
Support
Support This Project
If you find this project useful, consider buying me a coffee! ☕
Your support helps maintain and improve this project!
Made with ❤️ for the OpenClaw community
Metadata
Release files for openclaw-notebooklm 0.1.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| openclaw_notebooklm-0.1.2.tar.gz | 10.9 kB | Without provenance | Details for openclaw_notebooklm-0.1.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| openclaw_notebooklm-0.1.2-py3-none-any.whl | Python 3 | none | any | Details for openclaw_notebooklm-0.1.2-py3-none-any.whl |
Total release size: 20.5 kB
Release files / openclaw_notebooklm-0.1.2.tar.gz
| Download URL | openclaw_notebooklm-0.1.2.tar.gz |
|---|---|
| Size | 10.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
9558a1965003c6c879e11dbf4965aa86cb02e6735a1a20682e15ac34beba742d
|
|
BLAKE2b-256 checksum How to use checksums |
aa552c9bc5670ac4eb94e293df8ff32abe8fb277fa56aa1b56650eb5a1f1a264
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.5
|
Release files / openclaw_notebooklm-0.1.2-py3-none-any.whl
| Download URL | openclaw_notebooklm-0.1.2-py3-none-any.whl |
|---|---|
| Size | 9.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
594f84a99862d14f4bd23801b19ed7a5986778a568298915571d9cab12a9673f
|
|
BLAKE2b-256 checksum How to use checksums |
5173bb943e4f00746842cd11e6c7449792dcf7e5be3ed654f4448c20739729e9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.5
|
Security for openclaw-notebooklm 0.1.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.