MCP tools reference
The 6 tools the retailerapi MCP server exposes to your AI agent.
lookup_product
Resolve any identifier into a product summary.
Inputs:
identifier: string # required. UPC, EAN, ISBN, or item_id
identifier_type?: "UPC" | "EAN" | "ISBN" | "item_id"
include_cross_retailer?: boolean
Returns:
{
item_id, title, brand, image, current_price,
buybox_price, offers_count, walmart_url,
queried_identifier,
cross_retailer?: [...] // when requested
}Cost: 1-11 tokens depending on includes (1 base + optional 5 offers/reviews + optional 2 cross-retailer + optional 3 force-refresh).
price_history
Return price-history time series.
Inputs:
identifier: string
timeframe?: "7d" | "30d" | "90d" | "1y" | "all" # default 30d
retailer?: "walmart" | "amazon" | "ebay" | ... | "all" # default walmart
Returns:
{
identifier, retailer, timeframe,
observations: [{ observed_at, price, in_stock }],
stats: { current, lowest, highest, average, observation_count }
}Cost: 2 tokens.
get_offers
Current Walmart sellers for an item_id.
Inputs:
item_id: string
Returns:
{
item_id,
offers: [{ seller_id, seller_name, price, is_buy_box, in_stock }],
buy_box_seller_id
}Cost: 6 tokens (1 base lookup + 5 offers/reviews bundle).
get_seller
Walmart Marketplace seller profile.
Inputs:
seller_id: string
Returns:
{
seller_id, seller_name, rating, rating_count,
active_listings, account_age_days,
performance: { on_time_shipment_rate, return_rate_30d, is_pro_seller }
}Cost: 2 tokens.
get_reviews
Reviews summary + top reviews for a product.
Inputs:
identifier: string
start_date?: "YYYY-MM-DD"
end_date?: "YYYY-MM-DD"
Returns:
{
summary: { average_rating, total_reviews, rating_distribution },
top_reviews: [{ rating, title, body, reviewer_name, reviewed_at, verified_purchase }]
}Cost: 3 tokens.
What ships next
compare_retailers(June 2026) — single-call cross-retailer comparison without chainingwatch_product(July 2026) — server-side price-drop alerts via webhookbulk_lookup(August 2026) — batched UPC lookup at discounted token rate