Conversational Research Partner (NotebookLM • Gemini 2.5 • Session RAG)

No Active Notebook

• Visit https://notebooklm.google to create a notebook and get a share link

• Use add_notebook to add it to your library (explains how to get the link)

• Use list_notebooks to show available sources

• Use select_notebook to set one active

Auth tip: If login is required, use the prompt 'notebooklm.auth-setup' and then verify with the 'get_health' tool. If authentication later fails (e.g., expired cookies), use the prompt 'notebooklm.auth-repair'.

Tip: Tell the user you can manage NotebookLM library and ask which notebook to use for the current task.

PROMPT STRUCTURING GUIDELINES

Before sending any question to NotebookLM, structure it to get a well-organized, evidence-based response.

Core rules:

• Write the prompt in the user's language

• Keep the user's original question wording intact

• Never use decorative lines (===, ---) as they cause NotebookLM timeouts

• Always include: thematic output format, citation format, completeness signal, and the [NOT FOUND] placeholder

How to structure: Pick the matching question type below and adapt its pattern to the user's question.

Question Type Patterns

1. Comparison (compare, vs, difference, similarities)

[user's question]

Organize the response by points of comparison. Cover all aspects discussed in the documents.
For each point:
1. How each element addresses it, with direct quotes ("text" [Source: document])
2. Similarities and differences, with textual evidence

Cross-references: highlight where documents agree or contradict each other.
If information is not found: [NOT FOUND IN DOCUMENTS]

2. List / Identification (list, identify, which, what are the)

[user's question]

Organize the response by thematic topics. Cover all aspects discussed in the documents.
For each topic:
- TOPIC: [identifying title]
- DESCRIPTION: [synthesis with context, connecting information across documents]
- EVIDENCE: "direct quote" [Source: document]

If the same item appears in multiple documents, show all occurrences and any discrepancies.
If information is not found: [NOT FOUND IN DOCUMENTS]

3. Analysis (analyze, examine, evaluate, assess)

[user's question]

Organize the response by thematic topics. Cover all aspects discussed in the documents.
For each topic:
- TOPIC: [identifying title]
- DESCRIPTION: [synthesis with context, connecting information across documents]
- EVIDENCE: "direct quote" [Source: document]

Cross-document connections: where different documents address the same topic, show evidence from each.
If information is not found: [NOT FOUND IN DOCUMENTS]

4. Explanation (explain, why, how, what does it mean)

[user's question]

Answer based on what the documents explain. Cover all aspects discussed in the documents.
1. Core concept or answer, with supporting quotes ("text" [Source])
2. Examples or cases mentioned in the documents
3. Related concepts that the documents connect to this topic
4. Limitations or caveats noted in the documents

If information is not found: [NOT FOUND IN DOCUMENTS]

5. Extraction (default for all other questions)

[user's question]

Organize the response by thematic topics. Cover all aspects discussed in the documents.
For each topic:
- TOPIC: [identifying title]
- DESCRIPTION: [synthesis with context, connecting information across documents]
- EVIDENCE: "direct quote" [Source: document]

If a topic appears in multiple documents, show evidence from each.
If information is not found: [NOT FOUND IN DOCUMENTS]

Language Adaptation

Translate the entire prompt to the user's language. Examples:

• "Organize the response by thematic topics" → "Organizza la risposta per argomenti tematici"

• "Cover all aspects" → "Cerca di coprire tutti gli aspetti trattati nei documenti"

• "TOPIC/DESCRIPTION/EVIDENCE" → "ARGOMENTO/DESCRIZIONE/EVIDENZE"

• "Source:" → "Fonte:"

• "[NOT FOUND IN DOCUMENTS]" → "[NON PRESENTE NEI DOCUMENTI]"

Response Handling (for Claude, not NotebookLM)

After receiving NotebookLM's answer, present it faithfully to the user WITHOUT adding external knowledge or "improvements".

PERMISSION REQUIRED — Only when user explicitly asks to add a notebook.

Conversation Workflow (Mandatory)

When the user says: "I have a NotebookLM with X"

1. Ask URL: "What is the NotebookLM URL?"

2. Ask content: "What knowledge is inside?" (1–2 sentences)

3. Ask topics: "Which topics does it cover?" (3–5)

4. Ask use cases: "When should we consult it?"

5. Propose metadata and confirm:

   • Name: [suggested]

   • Description: [from user]

   • Topics: [list]

   • Use cases: [list] "Add it to your library now?"

6. Only after explicit "Yes" → call this tool

Rules

• Do not add without user permission

• Do not guess metadata — ask concisely

• Confirm summary before calling the tool

Example

User: "I have a notebook with n8n docs" You: Ask URL → content → topics → use cases; propose summary User: "Yes" You: Call add_notebook

How to Get a NotebookLM Share Link

Visit https://notebooklm.google/ → Login (free: 100 notebooks, 50 sources each, 500k words, 50 daily queries)

1. Click "+ New" (top right) → Upload sources (docs, knowledge)

2. Click "Share" (top right) → Select "Anyone with the link"

3. Click "Copy link" (bottom left) → Give this link to Claude

(Upgraded: Google AI Pro/Ultra gives 5x higher limits)

List all library notebooks with metadata (name, topics, use cases, URL). Use this to present options, then ask which notebook to use for the task.

Get detailed information about a specific notebook by ID

Set a notebook as the active default (used when ask_question has no notebook_id).

When To Use

• User switches context: "Let's work on React now"

• User asks explicitly to activate a notebook

• Obvious task change requires another notebook

Auto-Switching

• Safe to auto-switch if the context is clear and you announce it: "Switching to React notebook for this task..."

• If ambiguous, ask: "Switch to [notebook] for this task?"

Example

User: "Now let's build the React frontend" You: "Switching to React notebook..." (call select_notebook)

Update notebook metadata based on user intent.

Pattern

1. Identify target notebook and fields (topics, description, use_cases, tags, url)

2. Propose the exact change back to the user

3. After explicit confirmation, call this tool

Examples

• User: "React notebook also covers Next.js 14" You: "Add 'Next.js 14' to topics for React?" User: "Yes" → call update_notebook

• User: "Include error handling in n8n description" You: "Update the n8n description to mention error handling?" User: "Yes" → call update_notebook

Tip: You may update multiple fields at once if requested.

Dangerous — requires explicit user confirmation.

Confirmation Workflow

1. User requests removal ("Remove the React notebook")

2. Look up full name to confirm

3. Ask: "Remove '[notebook_name]' from your library? (Does not delete the actual NotebookLM notebook)"

4. Only on explicit "Yes" → call remove_notebook

Never remove without permission or based on assumptions.

Example: User: "Delete the old React notebook" You: "Remove 'React Best Practices' from your library?" User: "Yes" → call remove_notebook

Search library by query (name, description, topics, tags). Use to propose relevant notebooks for the task and then ask which to use.

Get statistics about your notebook library (total notebooks, usage, etc.)

List all active sessions with stats (age, message count, last activity). Use to continue the most relevant session instead of starting from scratch.

Close a specific session by session ID. Ask before closing if the user might still need it.

Reset a session's chat history (keep same session ID). Use for a clean slate when the task changes; ask the user before resetting.

Get server health status including authentication state, active sessions, and configuration. Use this to verify the server is ready before starting research workflows.

If authenticated=false and having persistent issues: Consider running cleanup_data(preserve_library=true) + setup_auth for fresh start with clean browser session.

Google authentication for NotebookLM access - opens a browser window for manual login to your Google account. Returns immediately after opening the browser. You have up to 10 minutes to complete the login. Use 'get_health' tool afterwards to verify authentication was saved successfully. Use this for first-time authentication or when auto-login credentials are not available. For switching accounts or rate-limit workarounds, use 're_auth' tool instead.

TROUBLESHOOTING for persistent auth issues: If setup_auth fails or you encounter browser/session issues:

1. Ask user to close ALL Chrome/Chromium instances

2. Run cleanup_data(confirm=true, preserve_library=true) to clean old data

3. Run setup_auth again for fresh start This helps resolve conflicts from old browser sessions and installation data.

Switch to a different Google account or re-authenticate. Use this when:

• NotebookLM rate limit is reached (50 queries/day for free accounts)

• You want to switch to a different Google account

• Authentication is broken and needs a fresh start

This will:

1. Close all active browser sessions

2. Delete all saved authentication data (cookies, Chrome profile)

3. Open browser for fresh Google login

After completion, use 'get_health' to verify authentication.

TROUBLESHOOTING for persistent auth issues: If re_auth fails repeatedly:

1. Ask user to close ALL Chrome/Chromium instances

2. Run cleanup_data(confirm=false, preserve_library=true) to preview old files

3. Run cleanup_data(confirm=true, preserve_library=true) to clean everything except library

4. Run re_auth again for completely fresh start This removes old installation data and browser sessions that can cause conflicts.

ULTRATHINK Deep Cleanup - Scans entire system for ALL NotebookLM MCP data files across 8 categories. Always runs in deep mode, shows categorized preview before deletion.

⚠️ CRITICAL: Close ALL Chrome/Chromium instances BEFORE running this tool! Open browsers can prevent cleanup and cause issues.

Categories scanned:

1. Legacy Installation (notebooklm-mcp-nodejs) - Old paths with -nodejs suffix

2. Current Installation (notebooklm-mcp) - Active data, browser profiles, library

3. NPM/NPX Cache - Cached installations from npx

4. Claude CLI MCP Logs - MCP server logs from Claude CLI

5. Temporary Backups - Backup directories in system temp

6. Claude Projects Cache - Project-specific cache (optional)

7. Editor Logs (Cursor/VSCode) - MCP logs from code editors (optional)

8. Trash Files - Deleted notebooklm files in system trash (optional)

Works cross-platform (Linux, Windows, macOS). Safe by design: shows detailed preview before deletion, requires explicit confirmation.

LIBRARY PRESERVATION: Set preserve_library=true to keep your notebook library.json file while cleaning everything else.

RECOMMENDED WORKFLOW for fresh start:

1. Ask user to close ALL Chrome/Chromium instances

2. Run cleanup_data(confirm=false, preserve_library=true) to preview

3. Run cleanup_data(confirm=true, preserve_library=true) to execute

4. Run setup_auth or re_auth for fresh browser session

Use cases: Clean reinstall, troubleshooting auth issues, removing all traces before uninstall, cleaning old browser sessions and installation data.