agentmods.dev

notebooklm-mcp: Instructions file for Gemini CLI

GEMINI.md

notebooklm-mcp GEMINI.md is an instructions file for Gemini CLI from m4yk3ldev/notebooklm-mcp. It costs 1,854 tokens per session, scanned A, original, MIT.

Repository instructions for a NotebookLM MCP server, which lets AI models manage Google NotebookLM notebooks, add sources, ask questions, and generate studio content.

In plain words
What is it for?
It helps coding agents build, test, authenticate, and run the NotebookLM integration.
Why use it?
It explains the project's TypeScript setup, internal Google API communication, commands, testing requirements, and code structure.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md.

This is m4yk3ldev/notebooklm-mcp's own configuration. It tells Gemini CLI how to work on notebooklm-mcp 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 configures →

not rated 18repo 1mo ago A scan 1,854 tokens original MIT
View source ↗ m4yk3ldev/notebooklm-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to m4yk3ldev/notebooklm-mcp. 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/m4yk3ldev/notebooklm-mcp/main/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/m4yk3ldev/notebooklm-mcp

Made for: Gemini CLI.

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 GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/m4yk3ldev/notebooklm-mcp/gemini-md.svg)](https://agentmods.dev/instructions/m4yk3ldev/notebooklm-mcp/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/m4yk3ldev/notebooklm-mcp/gemini-md"><img src="https://agentmods.dev/badge/instructions/m4yk3ldev/notebooklm-mcp/gemini-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,854 This file is loaded in full into every session.
When invoked 1,854 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 $0.01854 $0.01854
Opus 5 $0.00927 $0.00927
Sonnet 5 $0.00371 $0.00371
Haiku 4.5 $0.00185 $0.00185

Measured 8d ago against content hash c25829b818bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

notebooklm-mcp GEMINI.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 8d 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.

GEMINI.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NotebookLM MCP Server - Project Context

This file provides the foundational context, architecture, and engineering standards for the NotebookLM MCP Server project.

Project Overview

The NotebookLM MCP Server is a Model Context Protocol (MCP) implementation that exposes the capabilities of Google NotebookLM to AI models. It facilitates deep integration of NotebookLM's notebook management, source ingestion, RAG-based querying, and studio content generation into AI-assisted workflows.

Key Technologies

  • Runtime: Node.js (>=18)
  • Language: TypeScript (strict)
  • Package manager: pnpm (pinned via packageManager: "[email protected]"; use corepack enable && pnpm install)
  • Framework: @modelcontextprotocol/sdk
  • Bundler: tsup
  • CLI: commander
  • Validation: zod
  • Testing: vitest + msw (100% statements/branches/functions/lines, enforced by CI)
  • API Communication: Direct interaction with Google's internal batchexecute RPC endpoint via fetch.

Architecture

The project follows a modular SRP-respecting architecture centered around the MCP specification:

  • Entry Points:
    • src/cli.ts: Handles CLI commands (serve, auth). Version read from package.json at runtime.
    • src/server.ts: Initializes the McpServer and orchestrates tool registration.
  • Core Client (domain facade):
    • src/client.ts: NotebookLMClient — public surface for tools. Domain methods (listNotebooks, query, createAudioOverview, etc.) delegate infrastructure to the rpc/* collaborators.
  • RPC layer (extracted 2026-05-17):
    • src/rpc/transport.ts: RpcTransport — HTTP POST/GET to batchexecute and query endpoints. Enforces response.ok, merges Set-Cookie via AuthState, wraps response.text() in a race-with-abort so slow bodies actually honor the timeout.
    • src/rpc/auth-state.ts: AuthState — owns tokens / csrfToken / sessionId / cookies. Provides a single-flight refreshOnce() mutex (concurrent callers share one refresh), reloadIfNewer() disk pickup, and persisted recordSessionId / recordCsrfToken / recordSetCookies writes.
    • src/rpc/wire.ts: Pure parsers — parseResponse (batchexecute envelope) and extractTextFromBlocks.
  • Tools:
    • src/tools/: Directory containing modular tool definitions (e.g., notebook.ts, source.ts, query.ts, studio.ts).
    • src/tools/index.ts: Central registration point; also exports resolveSourceIds() (used by 9 studio tools) and clientResetSignal() (typed replacement for the legacy _client_action: "reset" string).
  • Authentication:
    • src/auth.ts: Logic for token loading, saving (mode 0600), validation, and the manual auth flow. ~/.notebooklm-mcp/ is created with mode 0700.
    • src/browser-auth.ts: Launches Chrome with --remote-debugging-port=0 --remote-debugging-address=127.0.0.1 and discovers the OS-assigned port by parsing the DevTools listening on ws://127.0.0.1:NNNN/ stderr line. Drives it directly via the Chrome DevTools Protocol (CDP) over a raw ws WebSocket — no Puppeteer/Playwright dependency.

Read the full file on GitHub · 95 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. 8d ago First seen · 95 lines · 1,854 tokens per session scan A c25829b818bd

Subscribe to this mod's changes

notebooklm-mcp GEMINI.md is an instructions file published in the GitHub repository m4yk3ldev/notebooklm-mcp (18 stars, last pushed 1mo ago), licensed MIT. It adds 1,854 tokens to every session, about $0.0093 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.

Backend and APIsBuilding agentsaigooglemcpmcp-servermodel-context-protocolnotebooklm
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

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

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