Marketplaces and search surfaces tell different halves of the same story. Trends MCP exposes Amazon product search trends and Google Shopping search trends with the same growth presets so analysts can see divergence before inventory and ad spend lock in.
E-commerce operators rarely trust a single surface. Amazon captures high-intent product search inside a closed retail engine. Google Shopping reflects how people compare merchants and prices in the open web. When those signals disagree, teams discover it late if they only watch one dashboard.
Trends MCP lets analysts and AI assistants pull both sources with the same API key, the same growth windows, and the same JSON shape. That makes diffing Amazon product search trends against Google Shopping trends a repeatable weekly task instead of a bespoke spreadsheet hunt.
Pick the phrasing a shopper would type, then run get_growth twice: once with source set to amazon, once with source set to google shopping. Keep percent_growth identical across calls so the assistant compares apples to apples.
Read the response metadata for recent and baseline dates. Trends MCP reports those explicitly, which matters when a seasonal spike sits on the edge of a window.
Headline growth can hide uneven curves. Use get_trends on each source when buyers need to see preorders ramp, post-holiday cliffs, or delayed reactions to a price change. Weekly mode is the default for long history; daily mode on Google sources can be requested on REST for short windows when supported.
get_top_trends exposes Amazon Best Sellers Top Rated, Amazon Best Sellers by Category, and other live feeds listed in the public docs. Merchants use these lists to spot adjacent SKUs that merit paired Amazon versus Google Shopping tests.
Operations teams increasingly keep briefs inside assistants. Ask for natural language that names Trends MCP explicitly so the tool router fires. Example: “Using TrendsMCP, compare 6M growth for insulated tumbler on amazon and google shopping.”
Normalized scores help compare shape across sources, yet they do not replace margin math, return rates, or fulfillment lead times. Treat divergence as a research ticket, not an automatic purchase order.
Deep dives live on Amazon search trends and Google Shopping trends. For wider discovery, read e-commerce product research and consumer demand signals.
Tools for this workflow
get_trendsPlot multi-year weekly interest for a SKU phrase on Amazon and Google Shopping before committing container quantities.
get_trends(source="amazon", keyword="portable espresso maker")get_growthCompare 30D, 3M, and 12M percent change for the same phrase on amazon versus google shopping.
get_growth(source="google shopping", keyword="portable espresso maker", percent_growth=["30D", "3M", "12M"])get_top_trendsPull Amazon Best Sellers by Category or Top Rated lists when benchmarking adjacent SKUs.
get_top_trends(type="Amazon Best Sellers by Category", limit=25, offset=0)FAQ