About
What is notebooklm-mcp?
notebooklm-mcp is a server designed to bridge the gap between AI agents like Claude Code, Codex, and Cursor, and Google's NotebookLM. It allows these agents to directly query NotebookLM for information, ensuring zero-hallucination answers grounded in your own documentation. The tool addresses common problems with traditional AI research, such as massive token consumption, inaccurate retrieval, and hallucinations, by leveraging NotebookLM's pre-processed knowledge base. It supports persistent authentication, library management with tags and descriptions, and cross-client sharing, enabling deep, iterative research where agents automatically ask follow-up questions to build complete understanding before generating code or responses. This eliminates the need for manual copy-pasting and significantly improves the accuracy and efficiency of AI-driven research.
Best used for
Ideal for developers and data scientists who need to ensure their AI agents provide accurate, hallucination-free responses based on specific documentation, and to automate the research process for coding tasks. Especially valuable for building complex workflows or understanding new APIs where precision and grounded answers are critical.
Common actions
open-sourceautomated workflowworkflowslow-code/no-codedeepfakecollaboration"AI Agents"github copilotface swapping
Capabilities
Key features
- Zero hallucinations
- Autonomous research
- Smart library management
- Deep iterative research
- Cross-tool sharing
- Deep cleanup tool
- Configurable tool profiles
Target Audience
developerdata scientist
Integrations
Not yet documentedPricing & Plans
Open Source · Likely Free
FAQs
How does notebooklm-mcp prevent AI hallucinations?
NotebookLM is specifically designed to only answer from uploaded sources. If the information is not present in your documents, it will refuse to answer rather than inventing plausible-sounding but incorrect information, ensuring zero hallucinations.
Can I use notebooklm-mcp with multiple AI agents?
Yes, notebooklm-mcp supports cross-tool sharing. Once set up, it works with various MCP clients like Claude Code, Codex, and Cursor, allowing all your agents to share the same NotebookLM library and research capabilities.
What is the difference between the MCP Server and the Claude Code Skill?
The MCP Server offers persistent sessions and works with multiple MCP clients. The Claude Code Skill provides a simpler, Python-based setup for stateless queries, but only works with local Claude Code. Both use the same browser automation for NotebookLM.
How does notebooklm-mcp handle rate limits for NotebookLM?
NotebookLM's free tier has daily query limits per Google account. notebooklm-mcp supports quick account switching, allowing you to continue research by changing the Google account used for NotebookLM interactions.
Can I see the AI agent's interaction with NotebookLM in real-time?
Yes, you can instruct your AI agent to "Show me the browser." This command will open a Chrome window, allowing you to watch the live conversation and interactions between your agent and NotebookLM.
Shypd.aiThe largest open index of AI tools
