700+Data Points

Real-time sales

23Marketplaces

100%Normalized Data

99.9%Uptime SLA

Built for Gemini

Amazon data Gemini can query at scale

100+ Amazon sources joined into one schema. SKU-level profit, 23 marketplaces, real-time sales data. Wire it into Gemini API, AI Studio, or Vertex.

Try for Free

Rated 4.7/5 onTrustpilot

How it works

From fragmented Amazon APIs to Gemini, in one flow

Nova absorbs SP-API, Ads, and Reports complexity. Gemini reads one clean schema.

Step 1

Amazon APIs

Fragmented, schema-shifting

SP-APIrate-limited

Ads APIshifting schemas

Reports APIlags 24 to 48h

We absorb the chaos so Gemini does not have to.

Step 2

One schema, pre-modeled for AI

Sales & Profit

Net Profit at SKU levelOrdersFeesCOGSSettlementsReturns

Advertising & Discoverability

PPC KeywordsSearch TermsSessionsBuy BoxBSR

Catalog & Inventory

FBA InventoryListingsCatalogueSubscribe & Save

700+

metrics

marketplaces

SKU

level grain

in real time

orders and units

Step 3

Gemini

Reads Nova in one query. Returns profit, fees, ads, inventory answers in seconds.

Real-time sales

Gemini is fast and cheap to run at scale, which makes it perfect for daily briefings, agents, and Sheets-native workflows. The catch: it is only as smart as the data it reads. Nova gives Gemini the joined-up seller model, one endpoint away.

What Gemini answers once it reads Nova

Real prompts from real seller teams. Real answers in seconds.

Rank my 10 worst-margin SKUs this month with the fee breakdown.

Ranked list with contribution margin, FBA fees, referral fees, storage fees, ad waste per ASIN. One query, joined Nova model.

Reads from: Orders × Fees × Ads

Which marketplaces are growing profit and which are bleeding?

Side-by-side profit trend per marketplace with the SKUs driving each direction.

Reads from: Settlements × Orders

Draft a Monday morning briefing for my Amazon business.

Concise written summary backed by actual rows: revenue, profit, ad spend, refunds, inventory risk, top movers.

Reads from: Orders × Ads × FBA Inventory

Find ASINs where Buy Box loss correlates with profit drop this week.

Joins Buy Box %, sales velocity and net profit. Returns ASIN, Buy Box delta, profit delta, suggested action.

Reads from: Buy Box × Orders × Settlements

Show search terms wasting more than $50/day with zero conversions.

Per-search-term ad spend with conversion data attached, sorted by waste. Names the campaigns to fix.

Reads from: Ads × Search Terms

Want more than five? The prompt library has 32, grouped by profit, PPC, keywords, inventory and listings. They run the same in Gemini.

query_reviews: query_reviews returns reviews and ratings per ASIN and marketplace on Seller Central accounts: review counts are available only in North America (US, CA, MX, BR), while ratings are available on every marketplace.

query_subscribe_and_save: query_subscribe_and_save returns Subscribe & Save programme health, offers and each product's state from Amazon's replenishment data.

The rest of the Amazon MCP guide

Every page in this cluster answers a different question. Start at the pillar if you want the full picture.

Why Gemini on Nova beats Gemini on raw SP-API

Same prompt. Nova returns an answer. Raw plumbing returns an error and a token bill.

100+ Amazon sources, pre-modeled

Orders, ads, fees, settlements, inventory, organic. Joined, deduped, ready for one query.

SKU-level profit, to the cent

200+ fee types reconciled per SKU. Net margin, not gross sales dressed up as margin.

Real-time sales, always fresh

Orders and units reach Nova within seconds of the sale, with sales estimated until Amazon confirms the exact amounts. Ad spend refreshes every two hours, search term data three times a day, Amazon finance transactions hourly, and the remaining reports daily.

23 marketplaces, one model

Consolidated or per-marketplace, same schema. No per-region rebuild.

See the full head-to-head with raw MCP

Live in 24 hours, not 24 weeks

Three steps from Amazon to Gemini.

Step 01

Connect Amazon

Auth your Seller Central and Ads accounts in Nova. 23 marketplaces supported.

Step 02

Point Gemini at Nova

Drop the Nova endpoint into Gemini's context. No schema authoring on your side.

Step 03

Ask anything

Gemini reads SKU profit, ads, inventory and answers from one joined model.

Also available for

Claude ChatGPT Nova MCP server 32 prompts to run first Data Warehouses pillar

Questions about Amazon data for Gemini

Everything teams ask before plugging Nova into their AI stack

Nova exposes the Nova MCP server, a remote endpoint any MCP-capable client can call. Gemini (via Gemini API, AI Studio, or any Gemini-powered app) queries the pre-modeled schema directly. No SP-API plumbing.

Yes. Anywhere you can call Gemini with tool use or function calling, you can wire in the Nova endpoint. Same schema, same answers.

Yes. 370 Amazon transaction lines reconciled into 154 P&L lines per SKU: Amazon fees, FBA fees, ad spend, refunds, COGS, VAT. Gemini answers in actual margin.

Nova MCP reads by default. Listing edits are available only when a workspace owner turns them on, and every edit is previewed and confirmed before it reaches Amazon. Prices and stock levels are never changed, and Nova does not change campaigns or budgets.

All 23 Amazon marketplaces Nova supports. Gemini answers consolidated or per-marketplace questions out of the same model.

Connect your Amazon accounts in Nova, point your Gemini app at the Nova endpoint, start asking questions. Most teams are live in under 24 hours.

Raw SP-API takes 8 to 20 tool calls per question, breaks on schema changes, and never returns profit. Nova gives Gemini one query that returns a profit-accurate answer.

Feed your Amazon data to Gemini

Live in 24 hours. Profit-accurate. 23 marketplaces.