NotebookLM MCP

Exposes Google's NotebookLM via a command-line interface and Model Context Protocol server for programmatic access to notes and documents.

Exposes Google's NotebookLM via a command-line interface and Model Context Protocol server for programmatic access to notes and documents.

The gist

NotebookLM MCP is an open-source Python tool that wraps Google's NotebookLM. It solves the problem of being unable to access NotebookLM notes programmatically by providing both a command-line interface and a Model Context Protocol (MCP) server. This allows developers and AI agents to query notebooks directly without using the web UI, removing the need for manual copy-pasting of information from the browser.

What it does

  • Query NotebookLM notebooks directly from the command line.
  • Serve notebook content via a Model Context Protocol (MCP) server for AI agents.
  • Authenticate with an existing Google browser session to access notebook data.
  • Fetch structured answers from queries, not just raw text dumps.
  • Integrate personal knowledge bases in NotebookLM with agent frameworks like Claude.

How it works

A user clones the GitHub repository, installs the Python package, and follows instructions to extract authentication credentials from their browser. It runs locally as a command-line tool, taking text queries as input and returning structured answers from NotebookLM. The tool can also be run as a local server to expose the MCP interface for AI agent integration. It is open-source and free to use.

Best for

Developers building AI agents that need to reference personal knowledge bases or document collections stored in NotebookLM. It's also ideal for users who want to query their notes from the terminal.

Watch out for

The tool relies on NotebookLM’s internal, undocumented API, which could change or break without warning. The authentication process requires manually extracting credentials from a browser session, which may be less robust than a standard OAuth flow.