Skip to main content
Glama
houtini-ai

Amazon Creators MCP

by houtini-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DEBUGNoNoisy stderr logging. Off by default.
AMAZON_CLIENT_IDYes"Credential Id" from your Creators API app
AMAZON_MARKETPLACEYesThe full marketplace host, e.g. www.amazon.com
AMAZON_PARTNER_TAGYesYour Associates tracking ID
AMAZON_CLIENT_SECRETYes"Secret" from the same place
AMAZON_MAX_CONCURRENCYNoMax requests in flight at once. Default 4.4
AMAZON_CREDENTIAL_VERSIONYesRegion-specific version: NA = 3.1, EU = 3.2, FE = 3.3

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}
resources
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
search_itemsA

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.

get_itemsA

Look up 1–10 ASINs on Amazon. IMPORTANT: the returned items array is NOT guaranteed to be in the same order as the input asins array — always match items to inputs by the asin field, not by index. Invalid or inaccessible ASINs appear in a separate errors array rather than in items — check both.

PRESENTATION GUIDANCE (important): default to format: 'markdown' or format: 'json'. After the tool returns, summarise conversationally (e.g. "Here's what I found for those 3 ASINs: • Echo Show 5 ($79.99) • Kindle Paperwhite ($139.99) …") — DO NOT paste the raw tool output. Then ASK the user whether they'd like an embeddable HTML card/grid before calling the tool again with an HTML format. Only use format: 'html-card' or format: 'html-grid' when the user has explicitly asked for a preview, card, widget, embed, or paste-ready HTML.

get_variationsA

List colour/size/style variations of a parent ASIN. Max 10 variations per call; paginate via variationPage (1–10). Pass the parent ASIN of a product that has variants — non-variant products return an empty result.

PRESENTATION GUIDANCE (important): default to format: 'markdown' or format: 'json'. Summarise the variations conversationally (e.g. "The Echo Show 5 comes in 3 colours: • Charcoal ($79.99) • Glacier White ($79.99) • Deep Sea Blue ($84.99)") — DO NOT paste the raw tool output. Then ASK the user whether they'd like an embeddable HTML grid of the variations for their blog. Only use format: 'html-card' or format: 'html-grid' when the user has explicitly asked for a preview, card, widget, embed, or paste-ready HTML.

get_browse_nodesA

Returns browse-node metadata (category tree) for up to 10 IDs — ancestor chain and direct children for each node. Use the browseNodeInfo.websiteSalesRank resource to find top-selling categories. Supports markdown and json output; HTML product-card formats don't apply here.

format_itemsA

Re-render Amazon items you already have (from a previous search_items, get_items, or get_variations call) without hitting the API again. Pass the exact structuredContent you received back as response, or pass items directly as an array. This tool IS for producing HTML embeds — the user has by this point explicitly asked for a card/grid/preview. Use it specifically when iterating on customStyles ("make the border hotpink", "dark mode", "bigger price") — it avoids rate-limit pressure and is much faster than re-querying Amazon.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription
Amazon Creators previewSandboxed renderer for Amazon Creators tool output — displays the HTML card/grid (or falls back to the raw markdown/JSON) inside a nested iframe.
Deploy Server
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

TDQS

A4.4/5.0

Scored across 5 tools

Disambiguation5/5

Each tool targets a distinct operation: fetching variations, searching by keywords, fetching by ASIN, retrieving browse node metadata, and formatting items. The descriptions clearly separate these concerns, with no overlapping purposes.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern: get_variations, search_items, get_items, get_browse_nodes, format_items. This makes the tool set predictable and easy to navigate.

Tool Count5/5

Five tools is well-scoped for an Amazon product data server. Each tool serves a distinct, necessary role without redundancy or bloat.

Completeness5/5

The tool surface covers the core workflows for Amazon product lookup: searching, retrieving by identifier, viewing variations, exploring category structure, and formatting results. No critical gaps are apparent for a read-only product retrieval server.

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources