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
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。