Skip to main content
Glama
paolodalprato

NotebookLM MCP Structured

ask_question

Ask questions about your NotebookLM documents and receive structured, cited answers with thematic organization and source evidence.

Instructions

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".

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
questionYesThe question to ask NotebookLM
session_idNoOptional session ID for contextual conversations. If omitted, a new session is created.
notebook_idNoOptional notebook ID from your library. If omitted, uses the active notebook. Use list_notebooks to see available notebooks.
notebook_urlNoOptional notebook URL (overrides notebook_id). Use this for ad-hoc queries to notebooks not in your library.
show_browserNoShow browser window for debugging (simple version). For advanced control (typing speed, stealth, etc.), use browser_options instead.
browser_optionsNoOptional browser behavior settings. Claude can control everything: visibility, typing speed, stealth mode, timeouts. Useful for debugging or fine-tuning.
Install Server

TDQS

A3.8/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full disclosure burden, and it does disclose important behavioral traits: decorative lines can cause NotebookLM timeouts, answers must be presented faithfully without adding external knowledge, and authentication can expire and require repair. It does not explicitly state that the tool automates a browser or creates sessions, but browser_options and session_id in the schema cover some of that context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-organized with clear headings, code blocks, and front-loaded setup guidance, which aids scanning. However, it is very long due to five near-identical prompt templates and language-adaptation examples, so it is not concise and much of the content is redundant for tool selection and basic invocation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema, the description is remarkably complete: it covers the no-notebook workflow, auth setup and repair, prompt structuring, browser timeout tuning, and response handling. It never directly states the return format, but it tells the agent how to present the answer, which is the practical information needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds limited meaning beyond the schema, mostly tying notebook_id to list_notebooks/select_notebook and implicitly connecting question to the prompt-structuring guidelines. It does not meaningfully clarify session_id, notebook_url, or browser_options beyond what the schema already says.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as a 'Conversational Research Partner' for NotebookLM and repeatedly mentions sending questions to NotebookLM and presenting its answer. It lacks a crisp one-line 'Asks NotebookLM a question' statement and the title is null, but the workflow and response-handling sections make the purpose unambiguous and distinguish it from notebook-management siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives a clear usage workflow: create a notebook, add it with add_notebook, list notebooks, select an active one, then ask questions. It also includes auth-repair guidance and a tip to tell the user about notebook management. It does not explicitly state when NOT to use this tool or name alternatives, but the context is sufficient for correct use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/paolodalprato/notebooklm-mcp-structured'

If you have feedback or need assistance with the MCP directory API, please join our Discord server