OneClickLM
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@OneClickLM List my NotebookLM notebooks"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Hi! I'm CR š
I built OneClickLM because I was tired of every NotebookLM MCP server breaking on me every few days.
After connecting NotebookLM to a 6-domain AI chatbot platform (BEYOND HUMAN), I hit literally every failure mode ā expired tokens, Chrome crashes, concurrent query timeouts, you name it. So I built the tool I wished existed.
OneClickLM just works. Login once, forget about it forever.
Related MCP server: notebooklm-mcp-2026
š„ The Problem
Every NotebookLM MCP server on GitHub shares the same fatal flaw: they break within days.
Google silently rotates auth tokens, and no one handles it.
What happens | What you see |
| š“ 400 Bad Request, zero explanation |
CSRF token goes stale | š“ Queries silently fail |
Chrome already running | š“ Login crashes with CDP conflict |
Two queries at once | š“ Timeout cascade, server dies |
Python + pipx + virtualenv | š“ 30 minutes just to install |
Connection drops | š“ Queries hang forever |
Sound familiar? Yeah, I went through all of this. So you don't have to.
ā The Solution
Feature | How it works |
Auto-healing auth | Detects expired tokens ā refreshes automatically ā you never notice |
Zero config |
|
No Chrome conflicts | Uses system Chrome for login, then pure HTTP. No CDP, no conflicts. |
Smart queue | Serializes concurrent calls. No timeouts, no crashes. |
6 powerful tools | List, query, create notebooks + add sources. Everything you need. |
TypeScript native | No Python, no virtualenv, no pipx. Just Node.js. |
š Quick Start
Step 1: Login (one time only)
npx oneclicklm loginA browser opens ā sign in with Google ā done. Your cookies are saved locally (~/.oneclicklm/).
Step 2: Add to your MCP client
{
"mcpServers": {
"notebooklm": {
"command": "npx",
"args": ["oneclicklm"]
}
}
}Step 3: Start talking to your notebooks!
"List my NotebookLM notebooks"
"What are the key findings in my Research notebook?"
"Create a new notebook called 'Project Alpha'"
"Add this URL to my notebook: https://example.com/paper.pdf"That's it. No API keys, no profiles, no metadata.json, no build_label hunting.
š Available Tools
Tool | What it does | Example prompt |
| List all your notebooks | "Show me my NotebookLM notebooks" |
| Get notebook details + sources | "What sources are in my Research notebook?" |
| Ask questions, get cited answers | "What does my notebook say about X?" |
| Create a new notebook | "Create a notebook called 'Q1 Report'" |
| Add URL, YouTube, or text sources | "Add this article to my notebook" |
| List all sources + their status | "Show sources in my Project notebook" |
Pro tip: notebook_query uses the same AI (Gemini) as the NotebookLM web app ā your answers are grounded in your actual sources with zero hallucination.
š» IDE Setup
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"notebooklm": {
"command": "npx",
"args": ["oneclicklm"]
}
}
}claude mcp add notebooklm -- npx oneclicklmAdd to .vscode/mcp.json:
{
"servers": {
"notebooklm": {
"command": "npx",
"args": ["oneclicklm"]
}
}
}Add to ~/.windsurf/mcp.json:
{
"mcpServers": {
"notebooklm": {
"command": "npx",
"args": ["oneclicklm"]
}
}
}š How OneClickLM Compares
Feature | OneClickLM | notebooklm-mcp (Python) | notebooklm-mcp-cli |
Auto token refresh | ā | ā | ā |
Auto build_label update | ā | ā | ā |
Auto-reconnect on failure | ā | ā | ā |
Request queue (no crashes) | ā | ā | ā |
Zero-config install | ā
| ā pipx + profiles | ā pipx + profiles |
Language | TypeScript | Python | Python |
Chrome conflicts | None | Common | Common |
Human-readable errors | ā | ā | ā |
Create notebooks via MCP | ā | ā | ā |
Add sources via MCP | ā | ā | ā |
āļø Configuration
OneClickLM works with zero configuration. But if you need it:
# Custom config directory
ONECLICKLM_DIR=~/.my-config npx oneclicklm
# Debug logging (see what's happening under the hood)
ONECLICKLM_LOG=debug npx oneclicklm
# Custom request timeout (default: 30s, queries may need longer)
ONECLICKLM_TIMEOUT=60000 npx oneclicklm
# Custom Chrome path
CHROME_PATH=/path/to/chrome npx oneclicklm loginConfig is stored in ~/.oneclicklm/:
~/.oneclicklm/
āāā cookies.json # Google auth cookies (auto-managed)
āāā tokens.json # CSRF + session + build_label (auto-refreshed)š§ How It Works (for the curious)
OneClickLM speaks the same language as the NotebookLM web app ā Google's internal batchexecute RPC protocol.
Here's what happens when you ask a question:
You: "What are the key findings?"
ā
MCP Client (Cursor/Claude/VS Code) sends tool call
ā
OneClickLM checks tokens ā auto-refreshes if stale
ā
Fetches source IDs from notebook (RPC: rLM1Ne)
ā
Sends query via streaming endpoint (GenerateFreeFormStreamed)
ā
Parses streaming response ā extracts answer
ā
Returns grounded, cited answer to your AIThe magic is in the auto-healing auth:
On startup: loads saved cookies + cached tokens
If tokens expired (>1 hour): fetches NotebookLM page ā extracts fresh
SNlM0e(CSRF) +FdrFJe(session) +build_labelIf cookies expired (~30 days): prompts for re-login
If API returns 400/401: auto-refreshes tokens and retries once
All requests serialized through a queue ā no concurrent crash
OneClickLM uses Google's internal web protocol, not an official API. This means it works with your existing Google account ā no API keys, no billing, no quotas. Google AI Pro subscribers get full NotebookLM access.
š§ Troubleshooting
Make sure Chrome/Chromium is installed. OneClickLM detects it automatically on macOS, Windows, and Linux.
# If using a non-standard Chrome location:
CHROME_PATH=/path/to/chrome npx oneclicklm loginOneClickLM auto-refreshes tokens, but if it persists:
# Force token refresh
npx oneclicklm refresh
# Nuclear option: re-login
npx oneclicklm loginThis is normal. NotebookLM processes your query against all uploaded sources in real-time (this is the Gemini model working). The NotebookLM web app has similar response times. For faster results, use notebooks with fewer sources.
npx oneclicklm statusThis verifies cookies, extracts fresh tokens, and tells you if anything is wrong.
š¤ Contributing
Contributions welcome! Bug reports, feature requests, and PRs are all appreciated.
git clone https://github.com/CRtheHILLS/OneClickLM.git
cd OneClickLM
npm install
npm run build
node dist/src/index.js # Run locallyā Star History
If OneClickLM saved you from NotebookLM auth hell, consider starring the repo!
License
MIT Ā© CRtheHILLS
Available Tools
6 toolsnotebook_createA
Create a new empty NotebookLM notebook. After creating, use source_add to add content.
Inputs: title (required).
notebook_getA
Get detailed information about a specific notebook, including all its sources and their status.
Inputs: notebook_id (required).
notebook_listA
List all your NotebookLM notebooks. Returns notebook IDs, titles, and source counts. Use this first to discover available notebooks.
Inputs: no named parameters.
notebook_queryA
Ask a natural language question to a NotebookLM notebook. The AI will analyze all sources in the notebook and return a grounded, cited answer. This is the main tool for getting information from your notebooks.
Inputs: query (required), notebook_id (required).
source_addA
Add a source to a NotebookLM notebook. Supports URLs (web pages, articles), YouTube videos, and plain text content. The source will be processed and made available for queries.
Inputs: type (required), notebook_id (required), url, title, +1 more.
source_listA
List all sources in a NotebookLM notebook, including their titles and processing status (ready, processing, error).
Inputs: notebook_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogā¦
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose: listing, getting, querying, creating notebooks, and adding/listening to sources. No overlapping functionality.
All tool names follow a consistent noun_verb pattern (e.g., notebook_list, source_add), with snake_case throughout.
6 tools is well-scoped for managing NotebookLM notebooks, covering creation, querying, and source management without being excessive or insufficient.
Covers core workflows well but lacks delete or update operations for notebooks and sources, which may be needed for full lifecycle management.
Maintenance
Related MCP Connectors
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
One MCP server for the services your AI needs: memory, files, Microsoft 365, kanban and more.
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
The Google Compute Engine MCP server is a fully-managed Model Context Protocol server that provides tools to manage Google Compute Engine resources through AI agents. It enables capabilities including instance management (creating, starting, stopping, resetting, listing), disk management, handling instance templates and group managers, viewing machine and accelerator types, managing images, and accessing reservation and commitment information. The server operates as a zero-deployment, enterprise-grade endpoint at https://compute.googleapis.com/mcp with built-in IAM-based security.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceSecure MCP server for querying Google NotebookLM notebooks. Enables AI assistants to list notebooks, read sources, and ask the NotebookLM AI questions about your sources.38 PyPI19MIT
- AlicenseNot gradedqualityCmaintenanceMCP server for querying Google NotebookLM notebooks, enabling AI assistants to list notebooks, read sources, and ask questions about them.MIT
- FlicenseBqualityDmaintenanceA production-ready, fully asynchronous MCP server that bridges AI agents with Google NotebookLM, enabling notebook creation, source management, audio generation, and more through natural language.12-
- AlicenseNot gradedqualityDmaintenanceMCP server that connects AI agents to Google NotebookLM, enabling natural language interaction with notebooks, including Q&A, source ingestion, and audio overview generation.5,121 npmMIT