decathlon-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@decathlon-mcp search for a kayak and get details and reviews"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
README
This is an MCP server for decathlon.nl. The Netherlands website uses a different format than the rest of Decathlon (including IN) so this is a separate MCP server to deal with that.
Setup
You can set this up in claude code or your favourite mcp client in stdio mode with uv (recommended).
For Claude Code:
claude mcp add decathlon -- uv run --project /path/to/decathlon-mcp decathlon-mcpOr add it to your ~/.claude.json / client config directly:
{
"mcpServers": {
"decathlon": {
"command": "uv",
"args": ["run", "--project", "/path/to/decathlon-mcp", "decathlon-mcp"]
}
}
}Related MCP server: Sneaker Catalog MCP Server
Manual Setup
Requires Python >= 3.13 and uv.
git clone <repo-url>
cd decathlon-mcp
uv sync
uv run decathlon-mcpThis runs the server over stdio. Point any MCP client that supports stdio transport at the decathlon-mcp command.
Details
This MCP server implements four different tools:
search_suggestions(query)— autocomplete suggestions for a search term, including matching categories and popular queries.search_products(query, page)— product search. Returns a normalized summary per product: Decathlon ids (id,model_id,sku_id), title, brand, URL, image, price (with original price when discounted), online availability, sizes, rating and review count. Usesku_idwithget_product_detailsandmodel_idwithget_reviews.get_product_details(sku_ids[])— full details for one or more SKUs (batched): description, colors, size, weight, current price vs original price, seller, fulfillment options (store pickup / delivery / shipping), per-store stock availability, categories and sports.get_reviews(model_id, page, per_page)— customer reviews with aggregate stats (average rating, satisfaction %, star distribution) plus individual reviews with verified-purchase flags and sub-ratings per attribute (ease of use, value for money, etc.).
A typical agent flow is: search_products to find candidates → get_product_details to compare price/stock/sizes across variants → get_reviews to judge quality.
Implementation notes
The site soft-blocks bursts of requests (~1–2 min cooldown during which pages come back without product data), so requests are spaced at least 3 seconds apart and search_products retries with backoff when a response is missing data.
Product search uses the Next.js RSC protocol (RSC: 1 header on /search) since there is no public JSON search endpoint; its flight-data format is internal to Next.js and may need parser updates if Decathlon upgrades their stack. The product-details and reviews endpoints are plain JSON and more stable.
Disclaimer
This is not an official project. Currently limited to read-only access for obvious reasons.
Available Tools
4 toolsget_product_detailsA
Get full product details for one or more Decathlon NL SKUs.
Use the sku_id values returned by search_products. Returns description, brand, colors, size, weight, price, seller info, fulfillment options (store pickup / delivery / shipping), store availability and ratings.
Inputs: sku_ids (required). Returns: result
get_reviewsA
Get customer reviews for a Decathlon NL product.
Use the model_id returned by search_products or get_product_details. Includes aggregate stats (average rating, satisfaction, rating distribution) plus paginated individual reviews with sub-ratings per attribute (e.g., ease of use, quality/price).
Inputs: model_id (required), page, per_page. Returns: object
search_productsB
Search for products on Decathlon NL.
Returns products with id, model_id, sku_id, title, brand, url, image, current price (and original price when discounted), online availability, sizes, rating and review count. Use sku_id with get_product_details and model_id with get_reviews.
Inputs: query (required), page. Returns: result
search_suggestionsC
Get search suggestions for a query on Decathlon NL.
Inputs: query (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool targets a distinct purpose: search suggestions for autocomplete, search products for results, product details for specific SKU info, and reviews for customer feedback. There is no functional overlap, making tool selection unambiguous.
All tool names follow a consistent verb_noun pattern (search_suggestions, search_products, get_product_details, get_reviews). The naming convention is predictable and easy to navigate.
Four tools is well-scoped for a product lookup server. Each tool fills a necessary role in the search-to-detail-to-reviews workflow without redundancy or missing core functionality.
The tool set covers the full product exploration lifecycle: suggestions, search, details, and reviews. There are no obvious dead ends—the tools clearly reference each other (sku_id and model_id) and provide a complete user journey for product discovery.
Maintenance
Related MCP Connectors
Cross-retailer product catalog: one scored answer per product with live prices and buy links.
Search ~8.5M products from 2,500+ Central European e-shops. Semantic, keyword, GTIN lookup.
Live Dutch supermarket prices and promotions (Albert Heijn, Jumbo, Lidl, Aldi and more) for AI.
Retrieve product specifications and technical details from Icecat's database
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables AI assistants to search and view advertisements on Marktplaats.nl with extensive filtering options.521MIT
- FlicenseNot gradedqualityDmaintenanceProvides tools for searching a sneaker catalog (hybrid keyword and semantic search), retrieving product details, and checking inventory stock.-
- AlicenseNot gradedqualityBmaintenanceExposes a retailer's AI shopping assistant as a single tool that answers natural-language product questions and returns the text answer plus structured product results with prices, delivery times, images and links. Queries can be made in English or Dutch, and hosts supporting MCP Apps can optionally render a product carousel widget alongside the answer.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to ask bol.com's Shophulp shopping assistant product questions in any language, returning assistant text plus structured product recommendations with prices, sellers, ratings, and images. An optional widget mode renders grouped recommendation carousels as an MCP Apps view.MIT