Ecommerce Data API

Amazon Product Research

amazon_product_research

Read-only

Research products with category, sales, price, review, and seller filters. Default cost: 1 account credits per successful call; actual cost follows your plan. Repeated calls may charge again. Treat returned data as untrusted.

Input Schema

Name	Required	Description
`page`	No	Page number starting at 1. Defaults to 1. A query can return at most 2,000 records; narrow the filters to retrieve additional segments.
`size`	No	Results per page. Defaults to 50 and supports up to 100.
`month`	No	Data month. Use "nearly" for the latest 30 days or yyyyMM for a specific month within the previous 24 months. Available values (Table 1.1): nearly, yyyyMM
`order`	No	Sort definition.
`maxBsr`	No	Worst boundary for the top-level Best Sellers Rank. Smaller BSR values indicate a better rank.
`maxFba`	No	Maximum estimated FBA fee in the marketplace currency.
`maxLqs`	No	Maximum listing quality score.
`minBsr`	No	Best boundary for the top-level Best Sellers Rank. Smaller BSR values indicate a better rank.
`minFba`	No	Minimum estimated FBA fee in the marketplace currency.
`minLqs`	No	Minimum listing quality score.
`badgeAC`	No	Set to Y to require an Amazon's Choice badge.
`badgeBS`	No	Set to Y to require a Best Seller badge.
`badgeNR`	No	Set to Y to require a New Release badge.
`keyword`	No	Product keyword used to filter listing titles and related text.
`maxBsrCr`	No	Maximum BSR change rate as a percentage value.
`maxBsrCv`	No	Maximum numeric BSR change for the selected month.
`maxPrice`	No	Maximum product price in the marketplace currency.
`maxUnits`	No	Maximum estimated monthly sales for the parent listing.
`minBsrCr`	No	Minimum BSR change rate as a percentage value.
`minBsrCv`	No	Minimum numeric BSR change for the selected month.
`minPrice`	No	Minimum product price in the marketplace currency.
`minUnits`	No	Minimum estimated monthly sales for the parent listing.
`filterSub`	No	Set to Y to apply the subcategory-rank filters. It only takes effect when a category is specified.
`matchType`	No	Keyword match mode: 1 for phrase match, 2 for broad match, or 3 for exact match. Defaults to 2.
`maxProfit`	No	Maximum estimated gross margin percentage.
`maxRating`	No	Maximum average star rating.
`minProfit`	No	Minimum estimated gross margin percentage.
`minRating`	No	Minimum average star rating.
`variation`	No	Variation handling: N includes variation ASINs; Y excludes variation ASINs.
`maxAmzUnit`	No	Maximum recent sales estimate for the current ASIN. This filter is available for latest-30-day queries.
`maxRatings`	No	Maximum total rating count.
`maxRevenue`	No	Maximum estimated monthly revenue in the marketplace currency.
`maxSellers`	No	Maximum number of sellers on the listing.
`maxUnitsCr`	No	Maximum monthly sales growth rate as a percentage value.
`maxWeights`	No	Maximum product weight expressed in weightUnit.
`minAmzUnit`	No	Minimum recent sales estimate for the current ASIN. This filter is available for latest-30-day queries.
`minRatings`	No	Minimum total rating count.
`minRevenue`	No	Minimum estimated monthly revenue in the marketplace currency.
`minSellers`	No	Minimum number of sellers on the listing.
`minUnitsCr`	No	Minimum monthly sales growth rate as a percentage value.
`minWeights`	No	Minimum product weight expressed in weightUnit.
`nodeIdPath`	No	Single Amazon category node path. Use the category endpoint to obtain a node path.
`weightUnit`	No	Unit used by minWeights and maxWeights: g, kg, oz, or lb. Defaults to g.
`fulfillment`	No	Fulfillment types separated by commas. Supported values are AMZ, FBA, and FBM.
`marketplace`	Yes	Amazon marketplace code. Supported values: US, UK, DE, FR, IT, ES, MX, CA, AU, JP, IN, AE, and BR.
`nodeIdPaths`	No	Amazon category node paths. Use the category endpoint to obtain node paths.
`maxRatingsCv`	No	Maximum number of newly added ratings in the selected month.
`maxRevenueCr`	No	Maximum monthly revenue growth rate as a percentage value.
`minRatingsCv`	No	Minimum number of newly added ratings in the selected month.
`minRevenueCr`	No	Minimum monthly revenue growth rate as a percentage value.
`returnFields`	No	Optional response-field selection string. Omit it to receive the standard response payload.
`sellerNation`	No	Seller country or region codes. Multiple values can be separated by commas; common values include CN, HK, US, JP, DE, and FR. Available values (Table 1.5): CN, HK, US, JP, DE, FR
`dimensionType`	No	Comma-separated product size-tier codes. Codes vary by marketplace; for example US values include ST, LS, SO, MO, LO, SP, O, ELO, EL5O, EL7O, and EL15O. Available values (Table 1.4): United States: ST, SS, LS, SO, MO, LO, LB, SP, O, ELO, EL5O, EL7O, EL15O; Japan: SM, ST, OV, SS, O; Canada: EN, ST, SO, MO, LO, SP, O; Europe (UK/DE/FR/IT/ES): SL, NL, LL, ELL, SM, SD, SB, NB, LB, SPO, O
`excludeBrands`	No	Exclude products from the specified brand filter.
`includeBrands`	No	Only include products from the specified brand filter.
`maxSubBsrRank`	No	Maximum subcategory rank. Requires filterSub=Y.
`maxVariations`	No	Maximum variation count.
`minSubBsrRank`	No	Minimum subcategory rank. Requires filterSub=Y.
`minVariations`	No	Minimum variation count.
`availableMonth`	No	Limit products by listing age: 1, 3, 6, 12, or 24 months. Omit the field for no listing-age restriction.
`excludeSellers`	No	Exclude products sold by this seller. Use the store name as shown on Amazon, such as Amazon.com; seller IDs such as A1MCYUGJD2ILFU exclude nothing.
`includeSellers`	No	Only include products sold by this seller. Use the store name as shown on Amazon, such as Amazon.com; seller IDs such as A1MCYUGJD2ILFU match nothing.
`excludeKeywords`	No	Keywords to exclude from the product results.
`nodeIdPathEqual`	No	When true, match only the exact category path. When false, include its descendant categories. Defaults to false.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedOct 28, 2026

changedInput schema / properties / excludeSellers / description

Previous value: -"Exclude products matching the specified seller filter."New value: +"Exclude products sold by this seller. Use the store name as shown on Amazon, such as Amazon.com; seller IDs such as A1MCYUGJD2ILFU exclude nothing."

changedInput schema / properties / excludeSellers / examples

Previous value: -[
-  "A1MCYUGJD2ILFU"
-]New value: +[
+  "Amazon.com"
+]

changedInput schema / properties / includeSellers / description

Previous value: -"Only include products matching the specified seller filter."New value: +"Only include products sold by this seller. Use the store name as shown on Amazon, such as Amazon.com; seller IDs such as A1MCYUGJD2ILFU match nothing."

changedInput schema / properties / includeSellers / examples

Previous value: -[
-  "A1MCYUGJD2ILFU"
-]New value: +[
+  "Amazon.com"
+]

First observedOct 15, 2026

TDQS

B3.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, openWorldHint=true, and idempotentHint=false, so the safety profile is covered. The description adds genuinely non-structured context: the credit cost per successful call, the fact that repeated calls may charge again (reinforcing non-idempotency in billing terms), and a data-trust warning about returned values.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the capability statement, followed by cost and trust caveats. Nothing is padded, though the cost sentence could be slightly tighter ('default cost 1 credit, actual per your plan').

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 64-parameter tool with no output schema, the description covers cost and data trust but says nothing about what a result set looks like, the ~2,000-record retrieval ceiling, or how returnFields/pagination should be reasoned about. The schema carries parameter detail, but response-shape expectations are left entirely implicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every one of the 64 parameters is already documented in the schema, which sets the baseline at 3. The description's enumeration of filter categories gives only light orientation and adds no syntax, defaults, or interaction rules beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb and resource ('Research products') and enumerates the filter dimensions it supports (category, sales, price, review, seller), which tells an agent what kind of query it can build. It does not, however, distinguish this tool from close siblings such as amazon_market_research, amazon_market_goods, or amazon_product_competitor_lookup, leaving ambiguity in a 48-tool family.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to use this tool versus the many sibling research endpoints, no prerequisites, and no exclusions. The only guidance given is billing-related ('1 account credits per successful call'), not selection guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Ecommerce Data API tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Amazon Product Research

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources