notebooklm-mcp and notebooklm-mcp-secure

notebooklm-mcp
58
Established
notebooklm-mcp-secure
43
Emerging
Maintenance 10/25
Adoption 13/25
Maturity 18/25
Community 17/25
Maintenance 10/25
Adoption 7/25
Maturity 9/25
Community 17/25
Stars: 38
Forks: 11
Downloads: 622
Commits (30d): 0
Language: TypeScript
License: MIT
Stars: 38
Forks: 10
Downloads: —
Commits (30d): 0
Language: TypeScript
License: MIT
No risk flags
No Package No Dependents

About notebooklm-mcp

roomi-fields/notebooklm-mcp

MCP server for NotebookLM - Let your AI agents (Claude Code, Codex) research documentation directly with grounded, citation-backed answers from Gemini. Persistent auth, library management, cross-client sharing. Zero hallucinations, just your knowledge base.

# Technical Summary Implements full NotebookLM automation through browser automation, exposing Q&A, podcast/video/infographic generation, and source management via MCP protocol or HTTP REST API. Uses session-based authentication with auto-reauth on expiry and supports 80+ languages for content generation across multiple formats (podcast, video, report, presentation, infographic, data table). Deploys as Node.js MCP server for Claude/Cursor/Codex, HTTP API for n8n/Zapier integration, or containerized Docker setup with noVNC for headless authentication on NAS devices.

About notebooklm-mcp-secure

Pantheon-Security/notebooklm-mcp-secure

Secure NotebookLM MCP Server - Query Google NotebookLM from Claude/AI agents with 14 security hardening layers

Implements MCP's handler architecture pattern with domain-specific modules (9 modules covering notebook management, audio/video generation, and Gemini integration), uses stdio transport for Claude integration, and supports both browser-based authentication and optional Gemini API for deep research—all enforced through 17 security layers including post-quantum encryption, constant-time auth validation, and audit logging. Enables programmatic notebook creation, audio/video overview generation, and structured data extraction without requiring manual UI interaction, alongside source-grounded Q&A that integrates with Claude and other MCP-compatible AI agents.

Scores updated daily from GitHub, PyPI, and npm data. How scores work