notebooklm

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

NotebookLM

NotebookLM = external RAG engine that offloads reading from your context window. Uses the

notebooklm-mcp-cli

MCP server (PyPI, v0.5.0+) to create notebooks, manage sources, generate content, and query with grounded AI responses. Supports batch operations across notebooks, pipelines, and multilingual content generation.

Disclaimer: Uses internal undocumented Google APIs via browser authentication. Sessions last ~20 minutes. API may change without notice.

NotebookLM 是一款外部RAG引擎，可将读取任务从你的上下文窗口中卸载。它借助

notebooklm-mcp-cli

MCP服务器（PyPI，v0.5.0及以上版本）来创建笔记本、管理数据源、生成内容，并基于AI给出有依据的响应。支持跨笔记本、流水线的批量操作，以及多语言内容生成。

免责声明：通过浏览器认证调用谷歌内部未公开API。会话时长约20分钟。API可能会无预警变更。

What's New (March 2026)

新增功能（2026年3月）

Cinematic Video Overviews (Mar 4) — fully animated narrated videos powered by Gemini 3 + Veo 3. Google AI Ultra only, 20/day limit, English only.
4 Audio Formats — Brief, Critique, Debate, Deep Dive (was single podcast style)
8x Source Capacity — 8x more source material per conversation, 6x extended memory
Per-Slide Editing —
```
studio_revise
```
edits individual slides without regenerating the full deck
3-Panel UI — Sources / Chat / Studio layout on notebooklm.google.com
Research timeout (v0.5.0) —
```
research_import
```
now configurable via
```
--timeout
```
/
```
timeout
```
param (default 300s, was 120s)
Deep research errors (v0.5.1) —
```
RPCError
```
class with error codes, auto-retry on transient API failures

影视级视频概览（3月4日）——由Gemini 3 + Veo 3驱动的全动画旁白视频。仅支持Google AI Ultra，每日限额20次，仅英文。
4种音频格式——新增Brief、Critique、Debate、Deep Dive（原仅支持单一播客格式）
8倍数据源容量——每个对话支持的数据源数量提升8倍，内存扩展6倍
单幻灯片编辑——
```
studio_revise
```
可编辑单个幻灯片，无需重新生成整套演示文稿
三面板UI——notebooklm.google.com上的「数据源/聊天/工作室」布局
研究超时设置（v0.5.0）——
```
research_import
```
现在可通过
```
--timeout
```
参数配置超时时间（默认300秒，原120秒）
深度研究错误处理（v0.5.1）——新增带错误码的
```
RPCError
```
类，针对临时API故障自动重试

Prerequisites

前置条件

Install:

uv tool install notebooklm-mcp-cli

(or

pip install notebooklm-mcp-cli

)

Authenticate:
```
nlm login
```
(opens browser, session ~20 min)
Configure MCP:
```
nlm setup add claude-code
```
(auto-configures
```
.mcp.json
```
) or
```
nlm setup add all
```
for multi-tool setup
Verify:
```
nlm login --check
```
to confirm active session
Upgrade:
```
uv tool upgrade notebooklm-mcp-cli
```
— restart MCP server after upgrade

安装：

uv tool install notebooklm-mcp-cli

（或

pip install notebooklm-mcp-cli

）

认证：
```
nlm login
```
（打开浏览器，会话时长约20分钟）
配置MCP：
```
nlm setup add claude-code
```
（自动配置
```
.mcp.json
```
）或
```
nlm setup add all
```
进行多工具配置
验证：
```
nlm login --check
```
确认会话处于活跃状态
升级：
```
uv tool upgrade notebooklm-mcp-cli
```
—— 升级后需重启MCP服务器

Decision Tree — Which Rule to Read

决策树 —— 查阅对应规则

What are you trying to do?
│
├── Create / manage notebooks
│   ├── List / get / rename ──────► notebook_list, notebook_get, notebook_rename
│   ├── Create new notebook ──────► notebook_create
│   └── Delete notebook ──────────► notebook_delete (irreversible!)
│
├── Add sources to a notebook
│   ├── URL / YouTube ────────────► source_add(type=url)
│   ├── Plain text ───────────────► source_add(type=text)
│   ├── Local file ───────────────► source_add(type=file)
│   ├── Google Drive ─────────────► source_add(type=drive)
│   ├── Rename a source ──────────► source_rename
│   └── Manage sources ──────────► rules/setup-quickstart.md
│
├── Query a notebook (AI chat)
│   ├── Ask questions ────────────► notebook_query
│   └── Configure chat style ────► chat_configure
│
├── Generate studio content
│   ├── 10 artifact types ───────► rules/workflow-studio-content.md
│   ├── Revise slides ───────────► studio_revise (creates new deck)
│   └── Export to Docs/Sheets ──► export_artifact
│
├── Research & discovery
│   └── Web/Drive research ──────► rules/workflow-research-discovery.md
│
├── Notes (capture insights)
│   └── Create/list/update/delete ► note (unified tool)
│
├── Sharing & collaboration
│   └── Public links / invites / batch ► rules/workflow-sharing-collaboration.md
│
├── Batch & cross-notebook
│   ├── Query across notebooks ────► cross_notebook_query
│   ├── Bulk operations ───────────► batch (query, add-source, create, studio)
│   └── Multi-step pipelines ──────► rules/workflow-batch-pipelines.md
│
├── Organization
│   └── Tag notebooks ─────────────► tags
│
└── Workflow patterns
    ├── Second brain ─────────────► rules/workflow-second-brain.md
    ├── Research offload ─────────► rules/workflow-research-offload.md
    └── Knowledge base ──────────► rules/workflow-knowledge-base.md

你想要执行什么操作？
│
├── 创建/管理笔记本
│   ├── 列出/获取/重命名 ──────► notebook_list, notebook_get, notebook_rename
│   ├── 创建新笔记本 ──────► notebook_create
│   └── 删除笔记本 ──────────► notebook_delete（不可撤销！）
│
├── 为笔记本添加数据源
│   ├── 网址/YouTube ────────────► source_add(type=url)
│   ├── 纯文本 ───────────────► source_add(type=text)
│   ├── 本地文件 ───────────────► source_add(type=file)
│   ├── Google云端硬盘 ─────────────► source_add(type=drive)
│   ├── 重命名数据源 ──────────► source_rename
│   └── 管理数据源 ──────────► rules/setup-quickstart.md
│
├── 调用笔记本（AI聊天）
│   ├── 提问 ────────────► notebook_query
│   └── 配置聊天风格 ────► chat_configure
│
├── 生成工作室内容
│   ├── 10种产物类型 ───────► rules/workflow-studio-content.md
│   ├── 修改幻灯片 ───────────► studio_revise（生成新的演示文稿）
│   └── 导出至文档/表格 ──► export_artifact
│
├── 研究与发现
│   └── 网页/云端硬盘研究 ──────► rules/workflow-research-discovery.md
│
├── 笔记（记录见解）
│   └── 创建/列出/更新/删除 ► note（统一工具）
│
├── 分享与协作
│   └── 公开链接/邀请/批量操作 ► rules/workflow-sharing-collaboration.md
│
├── 批量与跨笔记本操作
│   ├── 跨笔记本调用 ────► cross_notebook_query
│   ├── 批量操作 ───────────► batch（查询、添加数据源、创建、工作室）
│   └── 多步骤流水线 ──────► rules/workflow-batch-pipelines.md
│
├── 整理分类
│   └── 为笔记本添加标签 ─────────────► tags
│
└── 工作流模式
    ├── 第二大脑 ─────────────► rules/workflow-second-brain.md
    ├── 研究任务卸载 ─────────► rules/workflow-research-offload.md
    └── 知识库 ──────────► rules/workflow-knowledge-base.md

Quick Reference

快速参考

Category	Rule	Impact	Key Pattern
Setup	`setup-quickstart.md`	HIGH	Auth, MCP config, source management, session refresh
Workflows	`workflow-second-brain.md`	HIGH	Decision docs, project hub, agent interop
Workflows	`workflow-research-offload.md`	HIGH	Synthesis, onboarding, token savings
Workflows	`workflow-knowledge-base.md`	HIGH	Debugging KB, security handbook, team knowledge
Workflows	`workflow-studio-content.md`	HIGH	10 artifact types (audio, cinematic video, slides, infographics, mind maps...)
Research	`workflow-research-discovery.md`	HIGH	Web/Drive research async flow
Collaboration	`workflow-sharing-collaboration.md`	MEDIUM	Public links, collaborator invites, batch sharing
Batch	`workflow-batch-pipelines.md`	HIGH	Cross-notebook queries, batch ops, pipelines
Release	`workflow-versioned-notebooks.md`	HIGH	Per-release notebooks with changelog + diffs

Total: 9 rules across 5 categories

分类	规则	影响程度	核心模式
设置	`setup-quickstart.md`	高	认证、MCP配置、数据源管理、会话刷新
工作流	`workflow-second-brain.md`	高	决策文档、项目中心、Agent互操作
工作流	`workflow-research-offload.md`	高	成果合成、新员工入职、Token节省
工作流	`workflow-knowledge-base.md`	高	调试知识库、安全手册、团队知识管理
工作流	`workflow-studio-content.md`	高	10种产物类型（音频、影视级视频、幻灯片、信息图、思维导图...）
研究	`workflow-research-discovery.md`	高	网页/云端硬盘研究异步流程
协作	`workflow-sharing-collaboration.md`	中	公开链接、协作者邀请、批量分享
批量操作	`workflow-batch-pipelines.md`	高	跨笔记本调用、批量操作、流水线
版本发布	`workflow-versioned-notebooks.md`	高	每个小版本对应一个笔记本，上传CHANGELOG和关键技能差异作为数据源

总计：5个分类下的9条规则

MCP Tools by API Group

按API分组的MCP工具

Group	Tools	Count
Notebooks	notebook_list, notebook_create, notebook_get, notebook_describe, notebook_rename, notebook_delete	6
Sources	source_add, source_rename, source_list_drive, source_sync_drive, source_delete, source_describe, source_get_content	7
Querying	notebook_query, chat_configure	2
Studio	studio_create, studio_status, studio_list_types, studio_revise, studio_delete	5
Research	research_start, research_status, research_import	3
Sharing	notebook_share_status, notebook_share_public, notebook_share_invite, notebook_share_batch	4
Notes	note (unified: list/create/update/delete)	1 (4 actions)
Downloads	download_artifact	1
Export	export_artifact (Google Docs/Sheets)	1
Batch	batch (multi-notebook ops), cross_notebook_query	2
Pipelines	pipelines (ingest-and-podcast, research-and-report, multi-format)	1
Tags	tags (organize and smart-select notebooks)	1
Auth	save_auth_tokens, refresh_auth, server_info	3

Total: 37 tools across 13 groups (v0.5.0+)

分组	工具	数量
笔记本	notebook_list, notebook_create, notebook_get, notebook_describe, notebook_rename, notebook_delete	6
数据源	source_add, source_rename, source_list_drive, source_sync_drive, source_delete, source_describe, source_get_content	7
调用	notebook_query, chat_configure	2
工作室	studio_create, studio_status, studio_list_types, studio_revise, studio_delete	5
研究	research_start, research_status, research_import	3
分享	notebook_share_status, notebook_share_public, notebook_share_invite, notebook_share_batch	4
笔记	note（统一工具：列出/创建/更新/删除）	1（4种操作）
下载	download_artifact	1
导出	export_artifact（谷歌文档/表格）	1
批量操作	batch（多笔记本操作）, cross_notebook_query	2
流水线	pipelines（导入并生成播客、研究并生成报告、多格式输出）	1
标签	tags（整理并智能选择笔记本）	1
认证	save_auth_tokens, refresh_auth, server_info	3

总计：13个分组下的37个工具（v0.5.0及以上版本）

Key Decisions

关键决策建议

Decision	Recommendation
New notebook vs existing	One notebook per project/topic; add sources to existing
Source type	URL for web, text for inline, file for local docs, drive for Google Docs
Large sources	Split >50K chars into multiple sources for better retrieval
Auth expired?	`nlm login --check` ; sessions last ~20 min, re-auth with `nlm login`
Studio content	Use studio_create, poll with studio_status (generation takes 2-5 min)
Cinematic video	`studio_create(artifact_type="cinematic_video")` — requires Ultra, English only, 20/day
Audio format	Choose brief/critique/debate/deep_dive via `audio_format` param
Research discovery	research_start for web/Drive discovery, then research_import (timeout=300s default)
Deep research	`research_start(mode="deep")` for multi-source synthesis (v0.5.1+, auto-retries)
Release notebooks	One notebook per minor version; upload CHANGELOG + key skill diffs as sources
Query vs search	notebook_query for AI-grounded answers; source_get_content for raw text
Notes vs sources	Notes for your insights/annotations; sources for external documents
Infographic style	11 visual styles via `infographic_style` param on studio_create
Slide revision	Use `studio_revise` to edit individual slides (creates a new deck)
Export artifacts	`export_artifact` sends reports → Google Docs, data tables → Sheets
Language	`language` param on studio_create accepts BCP-47 codes (e.g., `he` for Hebrew, `en` , `es` , `ja` )
Batch operations	Use `batch` for multi-notebook ops; `cross_notebook_query` for aggregated answers
Pipelines	`ingest-and-podcast` / `research-and-report` / `multi-format` for multi-step workflows

决策场景	推荐方案
创建新笔记本还是使用现有笔记本	每个项目/主题对应一个笔记本；将数据源添加到现有笔记本中
数据源类型	网页用URL，内联内容用文本，本地文档用文件，谷歌文档用云端硬盘
大型数据源	将超过50000字符的内容拆分为多个数据源，以提升检索效果
认证过期？	执行 `nlm login --check` 检查；会话时长约20分钟，使用 `nlm login` 重新认证
工作室内容生成	使用studio_create，通过studio_status轮询进度（生成需2-5分钟）
影视级视频	调用 `studio_create(artifact_type="cinematic_video")` —— 需Ultra权限，仅支持英文，每日限额20次
音频格式	通过 `audio_format` 参数选择brief/critique/debate/deep_dive
研究发现	使用research_start进行网页/云端硬盘发现，再用research_import（默认超时300秒）
深度研究	调用 `research_start(mode="deep")` 进行多数据源合成（v0.5.1及以上版本，支持自动重试）
版本发布笔记本	每个小版本对应一个笔记本；上传CHANGELOG和关键技能差异作为数据源
调用与搜索	notebook_query用于AI给出的有依据的答案；source_get_content用于获取原始文本
笔记与数据源	笔记用于记录你的见解/注释；数据源用于存储外部文档
信息图风格	在studio_create中通过 `infographic_style` 参数选择11种视觉风格
幻灯片修改	使用 `studio_revise` 编辑单个幻灯片（会生成新的演示文稿）
导出产物	`export_artifact` 将报告导出至谷歌文档，数据表导出至谷歌表格
语言设置	studio_create的 `language` 参数支持BCP-47代码（如 `he` 代表希伯来语， `en` 、 `es` 、 `ja` ）
批量操作	使用 `batch` 进行多笔记本操作；使用 `cross_notebook_query` 获取汇总答案
流水线	使用 `ingest-and-podcast` / `research-and-report` / `multi-format` 执行多步骤工作流

Example

示例

bash

undefined

bash

undefined

1. Create a notebook for your project

1. 为项目创建笔记本

notebook_create(title="Auth Refactor Research")

2. Add sources (docs, articles, existing code analysis)

2. 添加数据源（文档、文章、现有代码分析）

source_add(notebook_id="...", type="url", url="https://oauth.net/2.1/") source_add(notebook_id="...", type="text", content="Our current auth uses...") source_add(notebook_id="...", type="file", path="/docs/auth-design.md")

3. Query with grounded AI responses

3. 调用AI获取有依据的答案

notebook_query(notebook_id="...", query="What are the key differences between OAuth 2.0 and 2.1?")

4. Generate a deep dive audio overview (supports language param)

4. 生成深度解析音频概述（支持语言参数）

studio_create(notebook_id="...", artifact_type="audio", audio_format="deep_dive", language="he", confirm=True) studio_status(notebook_id="...") # Poll until complete

studio_create(notebook_id="...", artifact_type="audio", audio_format="deep_dive", language="he", confirm=True) studio_status(notebook_id="...") # 轮询直到完成

5. Generate a cinematic video overview (Ultra only, English)

5. 生成影视级视频概述（仅Ultra权限，英文）

studio_create(notebook_id="...", artifact_type="cinematic_video", confirm=True) studio_status(notebook_id="...") # Poll — takes 3-8 minutes

studio_create(notebook_id="...", artifact_type="cinematic_video", confirm=True) studio_status(notebook_id="...") # 轮询 —— 需3-8分钟

6. Capture insights as notes

6. 记录见解为笔记

note(notebook_id="...", action="create", content="Key takeaway: PKCE is mandatory in 2.1")

undefined

note(notebook_id="...", action="create", content="Key takeaway: PKCE is mandatory in 2.1")

undefined

Common Mistakes

常见错误

Forgetting auth expiry — Sessions last ~20 min. Always check with
```
nlm login --check
```
before long workflows. Re-auth with
```
nlm login
```
.
One giant notebook — Split by project/topic. One notebook with 50 sources degrades retrieval quality.
Huge single sources — Split documents >50K characters into logical sections for better chunking and retrieval.
Not polling studio_status — Studio content generation takes 2-5 minutes. Poll
```
studio_status
```
instead of assuming instant results.
Ignoring source types — Use
```
type=url
```
for web pages (auto-extracts),
```
type=file
```
for local files. Using
```
type=text
```
for a URL gives you the URL string, not the page content.
Deleting notebooks without checking —
```
notebook_delete
```
is irreversible. List contents with
```
source_list_drive
```
and
```
note(action=list)
```
first.
Skipping research_import —
```
research_start
```
discovers content but does not add it. Use
```
research_import
```
to actually add findings as sources.
Raw queries on empty notebooks —
```
notebook_query
```
returns poor results with no sources. Add sources before querying.
Ignoring language param —
```
studio_create
```
supports BCP-47
```
language
```
codes (e.g.,
```
he
```
,
```
ar
```
,
```
ja
```
). Defaults to English if omitted.
Batch without purpose —
```
batch
```
and
```
cross_notebook_query
```
are powerful but add latency. Use for multi-project synthesis, not single-notebook tasks.

忘记认证过期 —— 会话时长约20分钟。执行长时间工作流前务必用
```
nlm login --check
```
检查。使用
```
nlm login
```
重新认证。
创建超大笔记本 —— 按项目/主题拆分。一个包含50个数据源的笔记本会降低检索质量。
单个数据源过大 —— 将超过50000字符的文档拆分为逻辑章节，以优化分块和检索效果。
未轮询studio_status —— 工作室内容生成需2-5分钟。应轮询
```
studio_status
```
而非假设即时完成。
忽略数据源类型 —— 网页用
```
type=url
```
（自动提取内容），本地文件用
```
type=file
```
。如果对URL使用
```
type=text
```
，只会得到URL字符串而非页面内容。
未检查就删除笔记本 ——
```
notebook_delete
```
不可撤销。删除前先用
```
source_list_drive
```
和
```
note(action=list)
```
列出内容。
跳过research_import ——
```
research_start
```
仅发现内容但不会添加。需使用
```
research_import
```
将研究结果实际添加为数据源。
对空笔记本执行原始查询 —— 无数据源时
```
notebook_query
```
返回结果质量差。查询前先添加数据源。
忽略语言参数 ——
```
studio_create
```
支持BCP-47
```
language
```
代码（如
```
he
```
、
```
ar
```
、
```
ja
```
）。若省略默认使用英文。
无意义的批量操作 ——
```
batch
```
和
```
cross_notebook_query
```
功能强大但会增加延迟。仅用于多项目合成，不要用于单笔记本任务。

notebooklm

Original

Translation

NotebookLM

NotebookLM

What's New (March 2026)

新增功能（2026年3月）

Prerequisites

前置条件

Decision Tree — Which Rule to Read

决策树 —— 查阅对应规则

Quick Reference

快速参考

MCP Tools by API Group

按API分组的MCP工具

Key Decisions

关键决策建议

Example

示例

1. Create a notebook for your project

1. 为项目创建笔记本

2. Add sources (docs, articles, existing code analysis)

2. 添加数据源（文档、文章、现有代码分析）

3. Query with grounded AI responses

3. 调用AI获取有依据的答案

4. Generate a deep dive audio overview (supports language param)

4. 生成深度解析音频概述（支持语言参数）

5. Generate a cinematic video overview (Ultra only, English)

5. 生成影视级视频概述（仅Ultra权限，英文）

6. Capture insights as notes

6. 记录见解为笔记

Common Mistakes

常见错误

Related Skills

相关技能