Provides tools for document Q&A powered by Google's Gemini File Search API, allowing users to upload documents and ask questions with grounded citations.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@notebooklm-api What does the document say about refunds?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
NotebookLM-quality document Q&A — but through MCP, powered by the official Gemini File Search API.
You upload your documents. You ask a question. Every sentence in the answer cites the exact passage from your files. No hallucination, no guessing, no "I think the document says...". Just grounded answers with receipts.
Every existing NotebookLM MCP server reverse-engineers Google's internal web UI. They scrape the page with Playwright, steal cookies, and pray Google doesn't change a CSS selector. Spoiler: Google changes things. Your MCP breaks. Your Google account gets flagged.
This one uses the official Gemini File Search API. It doesn't scrape anything. It doesn't need your Google login. Just an API key from aistudio.google.com.
Related MCP server: Gemini RAG MCP Server
Upload PDFs, DOCX, TXT, HTML, or any of 80+ supported formats. Ask questions across one or multiple document stores. Get answers like this:
The maximum liability is limited to the total fees paid
in the preceding twelve months [1]. Clients must pay all
invoices within forty-five days of receipt [2].
---
Citations:
[1] Contract_A.pdf: "The maximum liability under this agreement
shall not exceed the total fees paid in the preceding
twelve (12) months." (confidence: 92%)
[2] Contract_A.pdf: "The Client shall pay all invoices within
forty-five (45) days of receipt." (confidence: 88%)Every [1], [2] maps to the exact passage from your document. Not a summary. The actual text.
# Set your Gemini API key
export GEMINI_API_KEY=your-key-from-aistudio.google.com
# Add to Claude Code
claude mcp add notebooklm-api npx @mcpware/notebooklm-api
# Or add to Claude Desktop (~/.claude/mcp.json)
{
"mcpServers": {
"notebooklm-api": {
"command": "npx",
"args": ["@mcpware/notebooklm-api"],
"env": { "GEMINI_API_KEY": "your-key" }
}
}
}Then just talk to Claude naturally. The three-step workflow:
Step 1: Create a store (one time per topic)
"Create a store called 'Legal Docs'"
Step 2: Upload your files (one time per topic)
"Upload all PDFs from ~/contracts/ to the Legal Docs store"
Step 3: Ask questions (as many as you want)
"What are the liability clauses across all contracts?" "Which contract has the shortest termination notice period?" "Does any contract mention non-compete?"
Claude calls create_store, upload_document, and ask automatically. You don't need to know store names or API details. Each store is independent, so you can have separate stores for different topics (legal docs, tax records, research papers, etc.) and query them individually or together.
Tool | What it does |
| Create a document store |
| List all stores |
| Upload a file (PDF, DOCX, TXT, etc.) to a store. Waits for indexing to finish. |
| List documents in a store |
| Ask a question. Returns answer with per-passage citations. |
| Remove a document |
| Remove a store |
When you call ask, the Gemini File Search API does three things:
Searches your uploaded documents for relevant passages (vector similarity, not keyword match)
Generates an answer grounded in those passages
Returns groundingSupports — a map from each sentence in the answer to the exact source passage
We parse that map into inline [1], [2] markers and a citation list. This is the part every competitor gets wrong — they dump the raw API response without parsing it. We give you something you can actually read and verify.
You should, if the web UI works for you. This tool is for when you want:
Document Q&A inside your coding agent (Claude Code, Cursor, etc.)
Programmatic access — upload 100 documents, ask 50 questions, extract structured data
Stability — no browser automation, no cookies, no scraping
Your own API key — you control the cost and the data
On the free tier, Google may use your data to improve products. On the paid tier (link a billing account), they don't. If your documents are sensitive, use the paid tier. Details.
Go to aistudio.google.com
Click "Get API key"
Set it as GEMINI_API_KEY
The free tier gives you enough to try everything. Paid tier for production use.
MIT
Ask a question about your documents. Returns an answer with per-passage citations mapping every claim to its source document and exact passage. This is the core tool — use it after uploading documents to a store.
Inputs: question (required), store_names (required), model.
Create a new document store for uploading and searching files.
Inputs: display_name.
Delete a document from a store.
Inputs: document_name (required).
Delete a store and optionally all its documents.
Inputs: store_name (required), force.
List all documents in a store.
Inputs: store_name (required).
List all document stores.
Inputs: no named parameters.
Upload a document to a store. Supports PDF, DOCX, TXT, HTML, CSV, and more. Waits for processing to complete before returning.
Inputs: file_path (required), store_name (required), display_name.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 7 tools
Each tool targets a distinct resource action: store creation/listing/deletion, document upload/listing/deletion, and question answering. The 'ask' tool is clearly separated from file management operations, so an agent should not confuse any two tools.
Most tools follow a clear verb_noun snake_case pattern (create_store, list_documents, delete_document). The plural forms in list_stores/list_documents and the bare-verb 'ask' are minor deviations, but they do not undermine readability.
Seven tools is a well-scoped size for this document Q&A server. Each tool covers a necessary part of the workflow without redundancy or bloat.
The store and document lifecycles are mostly covered: create, list, delete, and upload, plus the core ask/search capability. The only noticeable gaps are update/replace operations and a simple get-document detail operation, but these are not critical for the intended workflow.
Ingest, manage, and retrieve documents for RAG-powered AI applications
Search, read and cite documents. Add, replace and delete files with write access. OAuth required.
Build a RAG pipeline station by station and search your own documents with cited answers.
Private, multimodal knowledge store for agents: hybrid search with cited, provenance-backed results.
