mcp server

NotebookLM

Google NotebookLM via natural language: create notebooks, add sources (PDF, URL, YouTube) and ask gr

Description as published by the maintainer. Source

• version 0.1.0
• active
• document understanding

active — Registry entry last updated 2026-06-10. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.

What this server can do

43 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

authenticate(token)

MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header `Authorization: Bearer <token>` for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes, or with no args to get the link.

connect

Returns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.

marketplace(limit, query, action, mcp_id, message, tool_id, arguments, immediate, tier_slug, prompt_body, prompt_slug, prompt_tool, prompt_vars, conversation, prompt_title, request_name, cancel_reason, cancel_comment, prompt_targets, report_context, prompt_category, request_details, prompt_description)

The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.

notebooklm_artifact_delete(artifact_id, notebook_id, artifact_ids, notebook_ids)

Apaga um artifact. Bulk support: accepts notebook_ids, artifact_ids for batched execution. Required: notebook_id, artifact_id.

notebooklm_artifact_get(artifact_id, notebook_id, artifact_ids, notebook_ids)

Detalhes/status de um artifact. Bulk support: accepts notebook_ids, artifact_ids for batched execution. Required: notebook_id, artifact_id.

notebooklm_artifact_list(type, notebook_id, notebook_ids)

Lista os artifacts do notebook. `type` filtra (audio|video|slide-deck|quiz|flashcard|infographic|data-table|mind-map|report). Bulk support: accepts notebook_ids for batched execution. Required: notebook_id.

notebooklm_artifact_poll(task_id, task_ids, notebook_id, notebook_ids)

Aguarda/consulta o status de uma geração de artifact. Bulk support: accepts notebook_ids, task_ids for batched execution. Required: notebook_id, task_id.

notebooklm_artifact_rename(new_title, artifact_id, notebook_id, artifact_ids, notebook_ids)

Renomeia um artifact. Bulk support: accepts notebook_ids, artifact_ids for batched execution. Required: notebook_id, artifact_id, new_title.

notebooklm_artifact_retry(artifact_id, notebook_id, artifact_ids, notebook_ids)

Re-tenta a geração de um artifact que falhou. Bulk support: accepts notebook_ids, artifact_ids for batched execution. Required: notebook_id, artifact_id.

notebooklm_artifact_suggestions(notebook_id, notebook_ids)

Sugestões de artifacts para o notebook. Bulk support: accepts notebook_ids for batched execution. Required: notebook_id.

notebooklm_ask(question, notebook_id, notebook_ids)

Pergunta ao notebook; resposta FUNDAMENTADA nas fontes, com citações. Pode demorar. Bulk support: accepts notebook_ids for batched execution. Required: notebook_id, question.

notebooklm_download(kind, artifact_id, notebook_id, artifact_ids, notebook_ids)

Baixa o conteúdo de um artifact. Texto (report/mind_map/quiz/flashcards/data_table) retorna inline em `content`; binário (audio/video/slide_deck/infographic) retorna metadados + tamanho (entrega por URL é tratada à parte). Bulk support: accepts notebook_ids, artifact_ids for batched execution. Required: notebook_id, kind.

notebooklm_generate(kind, options, language, source_ids, notebook_id, instructions)

Gera um artifact do notebook (assíncrono — retorna o artifact em geração). `kind`: audio (podcast), video, cinematic_video, slide_deck, report, mind_map, quiz, flashcards, infographic, data_table. `instructions` = foco/estilo. `options` = flags específicas do tipo (ex.: audio {format:deep-dive|brief|critique|debate, length:short|default|long}; video/cinematic_video {format:explainer|brief|cinematic, style:...}; slide_deck {format:detailed|presenter, length}; report {format:briefing-doc|study-guide|blog-post|custom}; quiz/flashcards {quantity:fewer|standard|more, difficulty:easy|medium|hard}; infographic {orientation, detail, style}; mind_map {kind:interactive|note-backed}). Acompanhe com notebooklm_artifact_list/get. Required: notebook_id, kind.

notebooklm_history(limit, show_all, notebook_id, notebook_ids)

Histórico de Q&A da conversa do notebook. Bulk support: accepts notebook_ids for batched execution. Required: notebook_id.

notebooklm_list

Lista os notebooks do usuário. Retorna [{ id, title, ... }] — use o `id` nas demais tools.

notebooklm_note_create(title, content, notebook_id, notebook_ids)

Cria uma nota no notebook. Bulk support: accepts notebook_ids for batched execution. Required: notebook_id, content.

notebooklm_note_delete(note_id, note_ids, notebook_id, notebook_ids)

Apaga uma nota. Bulk support: accepts notebook_ids, note_ids for batched execution. Required: notebook_id, note_id.

notebooklm_note_get(note_id, note_ids, notebook_id, notebook_ids)

Conteúdo de uma nota. Bulk support: accepts notebook_ids, note_ids for batched execution. Required: notebook_id, note_id.

notebooklm_note_list(notebook_id, notebook_ids)

Lista as notas do notebook. Bulk support: accepts notebook_ids for batched execution. Required: notebook_id.

notebooklm_note_rename(note_id, note_ids, new_title, notebook_id, notebook_ids)

Renomeia uma nota. Bulk support: accepts notebook_ids, note_ids for batched execution. Required: notebook_id, note_id, new_title.

notebooklm_notebook_create(title)

Cria um notebook novo (vazio). Retorna o notebook com seu `id`. Required: title.

notebooklm_notebook_delete(notebook_id, notebook_ids)

Apaga um notebook (irreversível). Bulk support: accepts notebook_ids for batched execution. Required: notebook_id.

notebooklm_notebook_metadata(notebook_id, notebook_ids)

Metadados do notebook + lista de fontes. Bulk support: accepts notebook_ids for batched execution. Required: notebook_id.

notebooklm_notebook_rename(new_title, notebook_id, notebook_ids)

Renomeia um notebook. Bulk support: accepts notebook_ids for batched execution. Required: notebook_id, new_title.

notebooklm_notebook_summary(topics, notebook_id, notebook_ids)

Resumo do notebook com insights gerados por IA. `topics:true` inclui tópicos sugeridos. Bulk support: accepts notebook_ids for batched execution. Required: notebook_id.

notebooklm_share_add(email, message, permission, notebook_id, notebook_ids)

Compartilha o notebook com um email (editor/viewer). Bulk support: accepts notebook_ids for batched execution. Required: notebook_id, email.

notebooklm_share_public(enable, notebook_id, notebook_ids)

Liga/desliga o link público do notebook. Bulk support: accepts notebook_ids for batched execution. Required: notebook_id.

notebooklm_share_remove(email, notebook_id, notebook_ids)

Remove o acesso de um colaborador. Bulk support: accepts notebook_ids for batched execution. Required: notebook_id, email.

notebooklm_share_status(notebook_id, notebook_ids)

Status de compartilhamento do notebook. Bulk support: accepts notebook_ids for batched execution. Required: notebook_id.

notebooklm_share_update(email, permission, notebook_id, notebook_ids)

Atualiza a permissão de um colaborador. Bulk support: accepts notebook_ids for batched execution. Required: notebook_id, email.

notebooklm_share_view_level(level, notebook_id, notebook_ids)

Define o nível de acesso do link público: full (notebook todo) ou chat (só chat). Bulk support: accepts notebook_ids for batched execution. Required: notebook_id, level.

notebooklm_source_add(type, title, content, notebook_id, notebook_ids)

Adiciona uma fonte ao notebook: URL (página/YouTube) ou texto. `type` é auto-detectado; use `type:"text"` + `title` para colar texto. Bulk support: accepts notebook_ids for batched execution. Required: notebook_id, content.

notebooklm_source_add_research(mode, query, import_all, from_source, notebook_id, notebook_ids)

Pesquisa na web (ou Drive) e adiciona fontes a partir dos resultados. Bulk support: accepts notebook_ids for batched execution. Required: notebook_id, query.

notebooklm_source_delete(source_id, source_ids, notebook_id, notebook_ids)

Remove uma fonte do notebook. Bulk support: accepts notebook_ids, source_ids for batched execution. Required: notebook_id, source_id.

notebooklm_source_fulltext(format, source_id, source_ids, notebook_id, notebook_ids)

Texto completo indexado de uma fonte. Bulk support: accepts notebook_ids, source_ids for batched execution. Required: notebook_id, source_id.

notebooklm_source_get(source_id, source_ids, notebook_id, notebook_ids)

Detalhes de uma fonte. Bulk support: accepts notebook_ids, source_ids for batched execution. Required: notebook_id, source_id.

notebooklm_source_guide(source_id, source_ids, notebook_id, notebook_ids)

Resumo + palavras-chave de uma fonte (gerado por IA). Bulk support: accepts notebook_ids, source_ids for batched execution. Required: notebook_id, source_id.

notebooklm_source_list(notebook_id, notebook_ids)

Lista as fontes do notebook. Retorna [{ id, title, ... }]. Bulk support: accepts notebook_ids for batched execution. Required: notebook_id.

notebooklm_source_refresh(source_id, source_ids, notebook_id, notebook_ids)

Reprocessa uma fonte de URL/Drive (re-indexa o conteúdo atual). Bulk support: accepts notebook_ids, source_ids for batched execution. Required: notebook_id, source_id.

notebooklm_source_rename(new_title, source_id, source_ids, notebook_id, notebook_ids)

Renomeia uma fonte. Bulk support: accepts notebook_ids, source_ids for batched execution. Required: notebook_id, source_id, new_title.

report_bug(context, message, conversation)

Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction. Required: message.

show_version

Show the current MCP platform and adapter versions.

toolkit_info

Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.

Last successful function declaration observed on 2026-08-13. Source: https://api.mcp.ai/p_notebooklm. We list what the server declared; we do not call any of these functions.

Endpoint status observed on 2026-08-13. Source: https://api.mcp.ai/p_notebooklm.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Where to get it

• Repository — https://github.com/mcp-dir/notebooklm-mcp
• Remote endpoint (streamable-http) — https://api.mcp.ai/p_notebooklm

Also from mcp-dir

• 99Pay MCP
  Connect your 99Pay account to AI via Brazil's Open Finance: balances, statements, cards, investments
• Ágora MCP
  Connect your Ágora account to AI via Brazil's Open Finance: balances, statements, cards, investments
• ASA MCP
  Connect your ASA account to AI via Brazil's Open Finance: balances, statements, cards, investments.
• Asaas
  Digital account and billing on Asaas with the full official REST API v3 (api.asaas.com), balance, ch
• Astrea (Aurum)
  Reporting and queries over Astrea (Aurum), Brazilian legal-practice software: cases per client, cale
• Atacadão MCP
  Connect your Atacadão account to AI via Brazil's Open Finance: balances, statements, cards, investme
• Investidor B3
  Your consolidated B3 investment portfolio (the central depository): position by asset, net worth, tr
• Banrisul MCP
  Connect your Banrisul account to AI via Brazil's Open Finance: balances, statements, cards, investme
• Banco do Brasil MCP
  Connect your Banco do Brasil account to AI via Brazil's Open Finance: balances, statements, cards, i
• Bity
  Bity crypto bank (Bitybank / Bitypreço), account balance per coin, market data (ticker, order book,