buywhere-singapore-value-intelligence
Semantic product search and price-intelligence API over Singapore e-commerce data. Computes auditable value-scores from Shannon entropy across vendor price distributions, with pay-per-call pricing via x402 (USDC) alongside Stripe.
README
BuyWhere Singapore Value Intelligence API
Semantic product search over Singapore e-commerce (BuyWhere), ranked by an auditable value-score derived from Shannon entropy across vendor price distributions - not just "cheapest first."
Available both as a plain HTTP API and as an MCP server (5 tools) for AI agents.
Base URL
https://useful-data-source-for-agents-production.up.railway.app
Authentication
All business endpoints require an X-API-Key header:
X-API-Key: <your key>
/health requires no authentication.
Pricing
Two ways to pay, same endpoints:
- x402 (pay-per-call, USDC on Base) - currently on Base Sepolia testnet, $0.01/call. A request without payment gets
402 Payment Requiredwith the payment details in thepayment-requiredresponse header. - Stripe (metered billing) - for callers provisioned with an API key and a Stripe customer on the account.
Endpoints
GET /search
Semantic product search over the BuyWhere Singapore catalog, ranked by composite value-score.
Query params:
query(required) - natural-language product descriptionlimit(default 10, 1-50)min_value_score(default 0.0, range 0.0-1.0) - filter out products below this score GET /search?query=noise+cancelling+headphones&limit=5&min_value_score=0.5
Response (ProductSearchResponse):
{
"query": "noise cancelling headphones",
"result_count": 5,
"currency": "SGD",
"products": [
{
"product_id": "abc123",
"title": "Sony WH-1000XM5",
"category": "electronics",
"image_url": "...",
"vendor_offers": ["..."],
"price_min_sgd": 389.00,
"price_max_sgd": 429.00,
"price_mean_sgd": 405.30,
"shannon_entropy_bits": 1.24,
"causal_reliability_score": 0.92,
"value_score": 0.847,
"value_score_explanation": "..."
}
],
"computation_ms": 43.2
}
GET /product/{product_id}/value_breakdown
Full auditable decomposition of the value-score formula for one product - entropy component, reliability component, price-rank component, the formula itself, and the recommended vendor/price.
GET /product/{product_id}/price_distribution
Vendor price distribution for one product: entropy (raw and normalized), price spread, coefficient of variation, and a plain-language interpretation of market fragmentation.
GET /health
Liveness probe. Returns { status, upstream_reachable, api_version, timestamp }. No auth required. Not billed (excluded from both Stripe and x402).
MCP tools
Connect an MCP-compatible client (Claude, Cursor, etc.) to the streamable HTTP endpoint at: https://useful-data-source-for-agents-production.up.railway.app/mcp
Exposes 5 tools:
rank_buywhere_products_by_value_score- ranked search withmax_price_sgdandcategory_filterfetch_buywhere_vendor_price_distribution- vendor spread for a knownproduct_idresolve_buywhere_product_identity- disambiguate a partial/fuzzy product name into candidate product IDscompare_buywhere_products_causal_rank- head-to-head comparison of 2-10 products with confounder adjustmentextract_buywhere_deal_anomalies- z-score based detection of mispriced or outlier listings
Value-score: the method
For each product, prices across vendors are treated as a distribution. The composite value_score blends:
- Entropy component - Shannon entropy of the price distribution across vendors (
H, in bits) normalized against the maximum possible entropy for that vendor count. Higher entropy = genuine price competition, not vendors clustered at the same number. - Reliability component - a causal-reliability score per vendor.
- Price-rank component - where this vendor's price sits in the observed range.
Every response includes the raw components (shannon_entropy_bits, entropy_component, reliability_component, price_rank_component) and, on /product/{id}/value_breakdown, the formula string itself - so an agent can cite the reasoning, not just the number.
Limits
/search:limitup to 50 results per call- MCP
compare_buywhere_products_causal_rank: 2-10 product IDs per call
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.