Loading…
Provides AI agent access to Google NotebookLM for notebook management and document analysis.
Do not connect
The assessed surface is high-risk. Remediate the findings before connecting.
Scanned 1 month ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The mcp-ai MCP server exposes 43 tools, focused primarily on developer and AI capabilities. Its published description reads: "Provides AI agent access to Google NotebookLM for notebook management and document analysis". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates mcp-ai D — the assessed surface is high-risk and should be remediated before use. Its most notable findings include "Cross-tool shadowing" and "Data-exfiltration parameters". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check mcp-ai's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add mcp-ai to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://api.mcp.ai/p_notebooklmStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Lista os notebooks do usuário. Retorna [{ id, title, ... }] — use o `id` nas demais tools.
Cria um notebook novo (vazio). Retorna o notebook com seu `id`.
Renomeia um notebook. Bulk support: accepts notebook_ids for batched execution.
Apaga um notebook (irreversível). Bulk support: accepts notebook_ids for batched execution.
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: notebooklm_generate
A tool description tries to alter the model’s use of another tool.
. Acompanhe com notebooklm_artifact_list/get.RecommendationDescriptions must describe only their own tool.
tool: report_bug
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
ck. Include the conversation array with recent messages for reproduction. {"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: marketplace
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
the MCP needs a credential/login, invoke returns a connect link; if it isRecommendationRemove side-channel parameters; constrain tool inputs.
tool: marketplace
A tool description tries to alter the model’s use of another tool.
er-MCP billing; report_bug sends feedback; request_mcp asks us to build aRecommendationDescriptions must describe only their own tool.
tool: authenticate
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
owser, copy the access token. Best: add it to this server's config as a headRecommendationRemove side-channel parameters; constrain tool inputs.
tool: (server instructions)
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
g in and copy a token. No other tools will work until authenticated.RecommendationRemove side-channel parameters; constrain tool inputs.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
ion"), call the show_version tool. NEW MCPs/tools/integrations (capabilitiesRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: marketplace
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
Financial data service providing fundamental information for 30,000+ listed companies across the US, Japan, and Korea, sourced directly from SEC, EDINET, and DART regulatory filings.
Search tours, attraction tickets, and holiday packages across 24 countries.
Agentic visitor analytics with five tools for CRO and session analysis.
52 paid x402 API endpoints for AI agents — crypto, data, DeFi, and market intelligence, settled on Base.
Access Vonage API documentation, code snippets, tutorials, and troubleshooting resources.
Enables AI agents to issue and manage Brazilian electronic service invoices (NFS-e) through the Nota Fiscal API.
Connects AI agents to the Omie ERP platform for financial and operational management in Brazilian businesses.
Access 99Pay financial data via Brazil's Open Finance for AI assistants.
Connects to Olist Tiny ERP for products, stock, orders, invoices, receivables, contacts, shipping, CRM, and price lists.
Connects to Nuvemshop stores for products, orders, customers, categories, and coupons through the official API.
Connects to Microvix retail ERP for products, inventory, customers, suppliers, sales, billing, orders, sellers, and stores.
Resumo do notebook com insights gerados por IA. `topics:true` inclui tópicos sugeridos. Bulk support: accepts notebook_ids for batched execution.
Metadados do notebook + lista de fontes. Bulk support: accepts notebook_ids for batched execution.
Pergunta ao notebook; resposta FUNDAMENTADA nas fontes, com citações. Pode demorar. Bulk support: accepts notebook_ids for batched execution.
Histórico de Q&A da conversa do notebook. Bulk support: accepts notebook_ids for batched execution.
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.
Lista as fontes do notebook. Retorna [{ id, title, ... }]. Bulk support: accepts notebook_ids for batched execution.
Detalhes de uma fonte. Bulk support: accepts notebook_ids, source_ids for batched execution.
Texto completo indexado de uma fonte. Bulk support: accepts notebook_ids, source_ids for batched execution.
Resumo + palavras-chave de uma fonte (gerado por IA). Bulk support: accepts notebook_ids, source_ids for batched execution.
Renomeia uma fonte. Bulk support: accepts notebook_ids, source_ids for batched execution.
Reprocessa uma fonte de URL/Drive (re-indexa o conteúdo atual). Bulk support: accepts notebook_ids, source_ids for batched execution.
Remove uma fonte do notebook. Bulk support: accepts notebook_ids, source_ids for batched execution.
Pesquisa na web (ou Drive) e adiciona fontes a partir dos resultados. Bulk support: accepts notebook_ids for batched execution.
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. `in
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.
Detalhes/status de um artifact. Bulk support: accepts notebook_ids, artifact_ids for batched execution.
Aguarda/consulta o status de uma geração de artifact. Bulk support: accepts notebook_ids, task_ids for batched execution.
Sugestões de artifacts para o notebook. Bulk support: accepts notebook_ids for batched execution.
Renomeia um artifact. Bulk support: accepts notebook_ids, artifact_ids for batched execution.
Re-tenta a geração de um artifact que falhou. Bulk support: accepts notebook_ids, artifact_ids for batched execution.
Apaga um artifact. Bulk support: accepts notebook_ids, artifact_ids for batched execution.
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 U
Cria uma nota no notebook. Bulk support: accepts notebook_ids for batched execution.
Lista as notas do notebook. Bulk support: accepts notebook_ids for batched execution.
Conteúdo de uma nota. Bulk support: accepts notebook_ids, note_ids for batched execution.
Renomeia uma nota. Bulk support: accepts notebook_ids, note_ids for batched execution.
Apaga uma nota. Bulk support: accepts notebook_ids, note_ids for batched execution.
Status de compartilhamento do notebook. Bulk support: accepts notebook_ids for batched execution.
Liga/desliga o link público do notebook. Bulk support: accepts notebook_ids for batched execution.
Compartilha o notebook com um email (editor/viewer). Bulk support: accepts notebook_ids for batched execution.
Atualiza a permissão de um colaborador. Bulk support: accepts notebook_ids for batched execution.
Remove o acesso de um colaborador. Bulk support: accepts notebook_ids for batched execution.
Define o nível de acesso do link público: full (notebook todo) ou chat (só chat). Bulk support: accepts notebook_ids for batched execution.
Show the current MCP platform and adapter versions.
Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.
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
Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.
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
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 conne