NotebookLM
This NotebookLM MCP server by Kangkhengyun from FPT University provides professional automation for Google's NotebookLM platform through browser automation using Selenium and undetected-chromedriver. Built with Python and featuring persistent Chrome profile sessions, streaming response support, and comprehensive error handling, it offers tools for sending chat messages, retrieving AI responses with completion detection, navigating between notebooks, and managing authentication state through automated browser interactions. The implementation includes advanced streaming detection with stability checks, multiple fallback selectors for UI elements, health monitoring with Prometheus metrics, and Docker deployment support, making it valuable for researchers and developers who need programmatic access to NotebookLM's AI capabilities for automated document analysis, batch processing of research queries, or integration of NotebookLM insights into larger AI workflows.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- cloud-infra
- Source
- PulseMCP
- Repository
- github.com/khengyun/notebooklm-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve NotebookLM from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.