notebooklm-mcp-structured: Instructions file for Claude Code

CLAUDE.md

notebooklm-mcp-structured CLAUDE.md is an instructions file for Claude Code from paolodalprato/notebooklm-mcp-structured. It costs 1,898 tokens per session, scanned A, original, MIT.

Project instructions for a NotebookLM MCP server that structures prompts and connects agents to NotebookLM, a research and document-analysis tool. They describe its TypeScript codebase, browser automation, validation, and tests.

In plain words
What is it for?
Developing, testing, and maintaining the notebooklm-mcp-structured project.
Why use it?
They give agents the project's conventions and checks for working with a server that aims to keep document analysis faithful to its sources.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is paolodalprato/notebooklm-mcp-structured's own configuration. It tells Claude Code how to work on notebooklm-mcp-structured itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything notebooklm-mcp-structured configures →

Reuse

Borrowing it

Nothing to install: this file belongs to paolodalprato/notebooklm-mcp-structured. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/paolodalprato/notebooklm-mcp-structured/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/paolodalprato/notebooklm-mcp-structured

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for notebooklm-mcp-structured CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/paolodalprato/notebooklm-mcp-structured/claude-md/github.svg)](https://agentmods.dev/instructions/paolodalprato/notebooklm-mcp-structured/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/paolodalprato/notebooklm-mcp-structured/claude-md"><img src="https://agentmods.dev/badge/instructions/paolodalprato/notebooklm-mcp-structured/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for notebooklm-mcp-structured CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/paolodalprato/notebooklm-mcp-structured/claude-md"><img src="https://agentmods.dev/badge/instructions/paolodalprato/notebooklm-mcp-structured/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,898 This file is loaded in full into every session.
When invoked 1,898 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.01898 $0.01898
Opus 5 $0.00949 $0.00949
Sonnet 5 $0.00380 $0.00380
Haiku 4.5 $0.00190 $0.00190

Measured 10d ago against content hash 53f0ae35a7ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

notebooklm-mcp-structured CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NotebookLM MCP Structured

Enhanced MCP server for NotebookLM with client-side prompt structuring for source fidelity in professional document analysis.

Stack

  • Language: TypeScript (ES2022, Node16 modules)
  • Runtime: Node.js >= 18.0.0
  • Framework: MCP SDK (@modelcontextprotocol/sdk)
  • Browser automation: Patchright (Playwright fork with stealth features)
  • Validation: Zod
  • Testing: node:test unit tests for the singleton module (npm run test:unit) plus an integration script (npm run test:singleton); the rest of the server is manually tested via tsx src/index.ts

Structure

src/
├── index.ts                    # Entry point: role dispatch (proxy/backend/direct) + CLI commands
├── server-core.ts              # Shared server core: managers + MCP Server factory, reused by all three roles
├── config.ts                   # Configuration: defaults, ENV overrides, paths, timing constants
├── errors.ts                   # Custom errors + page closed detection helper
├── selectors.ts                # Centralized DOM selectors for NotebookLM UI
├── types.ts                    # Global TypeScript interfaces
├── singleton/
│   ├── proxy.ts                 # Proxy role: stdio<->HTTP JSON-RPC pipe, handshake replay on reconnect
│   ├── backend.ts               # Backend role: shared server over localhost Streamable HTTP
│   ├── spawn.ts                 # Backend discovery, spawn lock, version-skew handling
│   └── registry.ts              # singleton.json / singleton.lock read-write helpers
├── auth/
│   └── auth-manager.ts         # Google auth: login, cookies, state persistence
├── session/
│   ├── session-manager.ts      # Session lifecycle, cleanup, limits
│   ├── browser-session.ts      # Page interactions, question/answer flow
│   └── shared-context-manager.ts # Shared browser context (fingerprint)
├── library/
│   ├── notebook-library.ts     # Notebook collection management (CRUD)
│   └── types.ts                # Library-specific types
├── tools/
│   ├── index.ts                # Exports definitions + handlers
│   ├── definitions.ts          # Tool definitions aggregator
│   ├── handlers.ts             # Tool implementation logic
│   ├── definitions/
│   │   ├── ask-question.ts     # Core tool with structuring guidelines
│   │   ├── notebook-management.ts # Library tools
│   │   ├── session-management.ts # Session tools
│   │   └── system.ts           # Health, auth, cleanup tools
│   └── templates/
│       └── structuring-guidelines.ts # Prompt structuring template
├── resources/
│   └── resource-handlers.ts    # MCP resources for notebooks
└── utils/
    ├── cleanup-manager.ts      # Deep cleanup of browser data
    ├── cli-handler.ts          # CLI config commands
    ├── connection-checker.ts   # Chrome state detection
    ├── logger.ts               # Colored console logging (testable with DI)
    ├── page-utils.ts           # Response detection, streaming handling
    ├── settings-manager.ts     # Profile-based tool filtering
    └── stealth-utils.ts        # Human-like typing/mouse

Read the full file on GitHub · 170 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 170 lines · 1,898 tokens per session scan A 53f0ae35a7ab

Subscribe to this mod's changes

notebooklm-mcp-structured CLAUDE.md is an instructions file published in the GitHub repository paolodalprato/notebooklm-mcp-structured (45 stars, last pushed 20d ago), licensed MIT. It adds 1,898 tokens to every session, about $0.0095 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens