Skip to main content
Glama
houtini-ai

Amazon Creators MCP

by houtini-ai

search_items

Read-only

Search Amazon's catalog by keyword or filters (title, actor, author, brand, browse node), with pagination and prices in local currency, and create embeddable HTML for blog posts.

Instructions

Search Amazon's catalog by keywords (plus optional title/actor/author/brand/browse-node filters). Returns up to 10 items per page; paginate via itemPage: 2..10 (100 items max). totalResultCount = results that exist, not results accessible. Prices are in the marketplace's currency.

PRESENTATION GUIDANCE (important): default to format: 'markdown' or format: 'json'. After the tool returns, DO NOT paste the raw output into the chat. Instead, summarise the results conversationally — e.g. "I found 5 coffee grinders. The standouts are: • Baratza Encore ($179, highly rated burr grinder) • OXO Brew ($99, solid budget pick) …" — then END your reply by asking the user whether they'd like an embeddable HTML card/grid for their blog. Only call the tool with format: 'html-card' or format: 'html-grid' when the user has explicitly asked for a preview, card, widget, embed, or paste-ready HTML. Never default to HTML output.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actorNo
brandNo
titleNoSearch within product titles.
artistNo
authorNo
formatNoOutput format. DEFAULT TO 'markdown' OR 'json' when you plan to summarise the results in chat. Use 'html-card' / 'html-grid' ONLY when the user has explicitly asked for an embed, preview, card, widget, grid, or paste-ready HTML — these formats return a full HTML document the user pastes into their blog and are not for in-chat reading. 'markdown' = friendly summary source; 'json' = raw API data for programmatic use; 'html-card' = single product card; 'html-grid' = responsive grid of all items.markdown
sortByNo
itemPageNoPage number (1-10).
keywordsNoSearch keywords. Required unless a different scoping field (title/actor/author/brand/browseNodeId) is provided.
maxPriceNoMax price in smallest currency unit (cents/pence).
merchantNo
minPriceNoMin price in smallest currency unit (cents/pence).
conditionNo
itemCountNoItems per page (max 10).
resourcesNoWhich fields Amazon should return. Names are camelCase (e.g. "itemInfo.title"). Omit to use a sensible default set.
searchIndexNoProduct category, e.g. "Electronics", "Books", "All".
availabilityNo
browseNodeIdNoRestrict results to a browse node (category).
customStylesNoExtra CSS appended to the default stylesheet when format is 'html-card' or 'html-grid'. Target stable class-name anchors: .amzn-card, .amzn-card__image, .amzn-card__title, .amzn-card__meta, .amzn-card__brand, .amzn-card__rating, .amzn-card__price, .amzn-card__price--unavailable, .amzn-card__savings, .amzn-card__cta, .amzn-card__disclosure, .amzn-grid. Ignored for 'markdown' and 'json'.
deliveryFlagsNo
titleMaxCharsNoMaximum rendered title length for HTML card/grid output. Amazon titles are often 150+ chars of keyword stuffing; clamping to ~80 keeps cards one-line on typical widths. Defaults to 80. Set to 0 to disable. Ignored by 'markdown' and 'json' — those formats get the full untruncated title.
minReviewsRatingNoMinimum star rating (1-5).
minSavingPercentNo
hideItemsWithoutPriceNoWhen format is 'html-grid', drop items that have no price. Defaults to true — cards without a price are weak embeds (no deal hook, reader must click through to learn anything). Set false for comparison tables where availability can lapse but you still want the product visible. Ignored for 'html-card', 'markdown', and 'json'.
languagesOfPreferenceNo
Behavior5/5

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

Beyond the readOnlyHint and openWorldHint annotations, the description discloses pagination limits (itemPage 2..10, 100 items max), the totalResultCount caveat, and marketplace currency. It also spells out that HTML formats return a full document only when explicitly requested, and that raw output should not be pasted into chat. No contradiction with annotations.

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?

The description is front-loaded with a one-sentence purpose, then adds concise pagination and currency facts, and closes with an important (clearly labeled) presentation block. The example summary is a bit verbose, but it vividly illustrates the expected chat behavior. No fluff; structure is logical.

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

Completeness4/5

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

For a 25-parameter tool with no output schema, the description covers the essential operational model: search scoping, pagination, result-count caveat, currency, and output-format semantics. It doesn't describe the exact response shape (e.g., where items live in the JSON) or error/empty cases, but the resource parameter and presentation guidance partially cover that. Overall it is complete enough for effective autonomous use.

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

Parameters4/5

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

The description groups actor/author/brand/title/browseNodeId as optional search scoping filters, adding meaning beyond their bare schema entries. It also clarifies that minPrice/maxPrice are in cents/pence implicitly via 'prices are in the marketplace's currency'. However, several enum parameters (sortBy, condition, merchant, availability) remain unexplained in both prose and schema, so parameter coverage is only partially enhanced.

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

Purpose5/5

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

The description opens with 'Search Amazon's catalog by keywords', a specific verb and resource. It lists optional filters (title/actor/author/brand/browse-node) which distinguishes it from sibling tools like get_items that likely retrieve by ID. The purpose is unmistakable.

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

Usage Guidelines3/5

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

The description provides clear context that this tool is for searching the catalog, but it never names sibling tools or says when not to use it. The PRESENTATION GUIDANCE covers output-format choice (markdown/json vs html-card/grid), which is intra-tool usage, not tool-vs-alternative guidance. Thus usage is implied, not explicit.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/houtini-ai/amazon-creators-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server