A
licenseC
qualityC
maintenanceA Model Context Protocol server enabling product searches across e-commerce platforms, price history tracking, and product specification-based searches using natural language prompts.
2
48 PyPI
19
MIT
BuyWhere Catalog MCP Server
Officialby BuyWhere
BuyWhere MCPサーバー
AIエージェント向けの越境商品カタログ。Model Context Protocolを通じて、シンガポール、東南アジア、米国市場の商品を検索・比較できます。
Claude Desktop、Cursor、VS Code Copilot、Cline、OpenCode、Codex、およびMCP互換クライアントで動作します。
デモ
44秒のデモ：商品検索、お得な情報の発見、価格比較、複数地域対応。
User: "Find me wireless earbuds under $50 available in Singapore"
Agent: [calls search_products → returns 5 matching products]
User: "Compare the top 3"
Agent: [calls compare_prices → side-by-side with best-value pick]Related MCP server: Agentic Product Protocol MCP Server
クイックスタート
export BUYWHERE_API_KEY=bw_live_xxxx
npx -y @buywhere/mcp-server無料のAPIキーを取得 → buywhere.ai/api-keys
ツール
ツール | 説明 |
| キーワード、カテゴリ、価格、地域でカタログを検索 |
| IDによる詳細な商品情報（価格、スペック、画像） |
| 2〜5つの商品の並列比較 |
| 特定商品の全加盟店における現在の価格 |
| 商品のクリック追跡付きアフィリエイトURL |
| 利用可能な商品カテゴリの分類 |
ユースケース
AIエージェント — シンガポール、東南アジア、米国市場の商品をリアルタイムで検索、比較、推奨
開発者 — API統合なしで、MCP互換アプリに越境ショッピング機能を追加
価格比較 — Lazada、Shopee、Amazon、および現地の小売店を横断して、単一のクエリで複数市場の価格を取得
クイックセットアップ
Claude Desktop
claude_desktop_config.json に追加します：
{
"mcpServers": {
"buywhere": {
"command": "npx",
"args": ["-y", "@buywhere/mcp-server"],
"env": { "BUYWHERE_API_KEY": "bw_live_xxxx" }
}
}
}Cursor / VS Code / Cline
設定は同じです。MCP設定ファイルに追加してください：
{
"mcpServers": {
"buywhere": {
"command": "npx",
"args": ["-y", "@buywhere/mcp-server"],
"env": { "BUYWHERE_API_KEY": "bw_live_xxxx" }
}
}
}設定
変数 | デフォルト | 説明 |
| (必須) | buywhere.ai/api-keys から取得したAPIキー |
|
| カスタムAPIベースURL |
インストール
# Run directly (no install)
npx -y @buywhere/mcp-server
# Install globally
npm install -g @buywhere/mcp-server
buywhere-mcp開発
git clone https://github.com/BuyWhere/buywhere-mcp.git
cd buywhere-mcp
npm install
npm run build
npm startなぜBuyWhereなのか？
BuyWhereは、AIエージェント向けに構築された初の越境商品カタログAPIです。シンガポール、東南アジア、米国市場の商品を、エージェントが扱いやすい単一のインターフェースに集約しています。
単一のAPI — すべての市場、すべての小売店に対応
エージェントネイティブ — 初めからMCP向けに構築
リアルタイム — ライブ価格と在庫状況
開発者ファースト — SDK不要、サーバーを追加するだけ
A2Aプロトコル
BuyWhereは、マルチエージェントタスク委任のためのAgent-to-Agent (A2A)プロトコルもサポートしています。/.well-known/agent.json でエージェントカードをご覧ください。
コントリビューション
問題の報告、PRの提出、機能の提案方法については CONTRIBUTING.md を参照してください。
サポート
このプロジェクトが役に立った場合：
⭐ リポジトリにスターを付ける — 他の人がBuyWhereを見つける助けになります
🐛 バグや機能リクエストは Issueを開く
💬 質問やアイデアは ディスカッションを開始
📣 AIエージェントツールを構築している他の開発者に共有してください
ライセンス
MIT
Available Tools
6 toolscompare_pricesA
Compare 2–5 products side-by-side. Returns structured differentiators, price range, pros/cons, and a best-value recommendation — purpose-built for AI agent decision-making.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| product_ids | Yes | Array of 2–5 BuyWhere product IDs to compare |
TDQS
A4.3/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses that the tool returns structured data including differentiators and a recommendation, indicating a read-only operation without side effects. No hidden behaviors are mentioned, but the description is adequate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that efficiently conveys the tool's purpose and outputs with no superfluous words. Front-loaded with key action and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and no output schema, the description sufficiently covers what the tool does and what it returns. An agent can accurately decide to invoke it for multi-product comparisons.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides a description for 'product_ids' (array of 2-5 strings). The description adds 'BuyWhere' specificity, but does not significantly enhance understanding beyond the schema. Schema coverage is 100%, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool compares 2-5 products side-by-side and lists specific outputs (differentiators, price range, pros/cons, recommendation). It distinguishes itself from sibling tools like get_price and get_product which handle single products.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use for multi-product comparison and mentions it is 'purpose-built for AI agent decision-making.' It does not explicitly state when not to use it or name alternatives, but the context from sibling tools makes it clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_affiliate_linkA
Get the click-tracked BuyWhere affiliate link for a product. Share this link with users — it logs the referral and redirects to the merchant page. Always use this instead of raw product URLs when sharing links.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| product_id | Yes | The BuyWhere product ID |
TDQS
A4.4/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that the link logs referrals and redirects, which is key behavioral info. With no annotations, this is nearly sufficient; could mention if any authentication is needed but acceptable for a simple tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two efficient sentences with no filler. Front-loads the core action and immediately provides usage guidance.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers purpose, usage, and behavioral aspects adequately for a simple tool with one parameter and no output schema. Slightly lacking on return value details but sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema already fully describes the only parameter (product_id) as 'The BuyWhere product ID'. Description does not add extra semantic detail beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the action ('get') and the specific resource ('click-tracked BuyWhere affiliate link'). Distinguishes from sibling tools like get_product or get_price by focusing on affiliate link generation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly advises to use this tool instead of raw product URLs when sharing links, and explains why (referral logging, redirect). Provides clear context for when to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_catalogA
List available product categories in the BuyWhere catalog. Use this to discover what categories exist before searching or filtering.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| parent_slug | No | Parent category slug to list subcategories (optional — omit for top-level categories) |
TDQS
A4/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description lists categories but does not disclose any additional behavioral traits like pagination or rate limits. Adequate for a simple list operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with front-loaded purpose. No redundant information, every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple list tool with full schema coverage, the description is fairly complete. Could mention return format, but not essential.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a well-described parameter. The description adds no extra meaning beyond the schema, meeting baseline for adequate parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses specific verb 'List' and resource 'product categories', clearly distinguishing from sibling tools like search_products or get_product.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Use this to discover what categories exist before searching or filtering', providing clear usage context. No need to exclude alternatives as no sibling overlaps.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_priceA
Get current prices for a product across all available merchants. Returns a ranked list of listings with price, shipping, merchant rating, and stock status. Use this to find the cheapest place to buy a specific product.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| product_id | Yes | The BuyWhere product ID |
TDQS
A4/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description mentions it returns a ranked list with price, shipping, merchant rating, stock status, but doesn't discuss freshness, pagination, or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded, every word adds value; no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers purpose, expected output structure, and usage context; missing details like response format completeness, but adequate for a simple tool without output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Only one parameter (product_id) with schema description identical to tool description; no additional meaning added beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it retrieves current prices for a product across merchants, distinguishes from siblings like get_product and compare_prices.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'use this to find the cheapest place to buy a specific product,' providing clear usage context, though lacks explicit when-not-to-use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_productB
Fetch full details for a single product by its BuyWhere product ID.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| product_id | Yes | The BuyWhere product ID (returned by search_products as product_id) |
TDQS
B3.3/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description carries full burden. Lacks details on what 'full details' includes, error behavior for invalid IDs, or any side effects. Vague behavioral expectations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with no wasted words. Front-loaded with the core action and qualifier.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequate for a simple single-param tool, but missing details about output content and error states. No output schema to supplement, so description should clarify what 'full details' means.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a clear property description. Tool description adds no extra context beyond the schema's property text, so it meets baseline without enhancement.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the action (fetch), resource (full details for a single product), and uniqueness (by BuyWhere product ID). It distinguishes from sibling tools like search_products which return multiple results.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this vs alternatives (e.g., get_price, get_catalog). No mention of prerequisites or when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_productsA
Search the BuyWhere product catalog using keywords or natural language. Returns matching products with title, price, availability, merchant, and URL.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Keyword or natural-language query (e.g. 'wireless earbuds under $50', 'red dress size M') | |
| country | No | Country code to scope results (e.g. 'sg' for Singapore). Defaults to 'sg'. | |
| category | No | Category slug filter (e.g. 'electronics/smartphones', 'fashion/dresses') | |
| limit | No | Maximum number of results to return (1–50, default 10) |
TDQS
A3.8/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description implies read-only search behavior but does not explicitly state side effects, authentication, or rate limits. Minimal transparency for a search tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences that front-load purpose and output. No extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers purpose, parameters, and return fields adequately for a search tool. Lacks mention of pagination, error responses, or empty result handling, but these are minor gaps given low complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers 100% parameters with descriptions. Description adds no meaningful detail beyond the schema, such as query format examples or category slug usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states verb 'Search' and resource 'BuyWhere product catalog'. Specifies output fields (title, price, availability, merchant, URL). Distinguishes from siblings like compare_prices and get_product by focusing on keyword search.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Describes when to use (keyword search), but lacks explicit guidance on when not to use or alternatives. No mention of when to prefer compare_prices or get_product over this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
6 tool updates
v1.0.0- First observed
compare_prices - First observed
get_affiliate_link - First observed
get_catalog - First observed
get_price - First observed
get_product - First observed
search_products
TDQS
A4/5.0
Scored across 6 tools
Disambiguation5/5
Each tool has a clearly distinct purpose: compare_prices does side-by-side comparison, get_affiliate_link provides affiliate links, get_catalog lists categories, get_price shows merchant prices, get_product fetches details, search_products searches catalog. No overlapping functionality.
Naming Consistency5/5
All tool names follow a consistent verb_noun pattern in snake_case (e.g., compare_prices, search_products). The naming is predictable and easy to understand.
Tool Count5/5
With 6 tools, the set is well-scoped for a price comparison and affiliate linking service. Each tool serves a necessary function without unnecessary bloat.
Completeness4/5
Core workflows are covered: search, get details, compare, get prices, affiliate links, and category discovery. Minor gaps like lack of explicit filtering or sorting in search are acceptable for the scope.
Maintenance
ActivityActive
ResponsivenessWithin a week
Related MCP Connectors
AI-agent product catalog: search, lookup & purchase routing over verified merchant data.
Cross-vendor B2B catalog for AI agents: search, compare, find equivalents, request a quote.
Agent-native product catalog: 300M+ products, 150,000+ stores, deliver_to ranking.
AI agent product discovery via open marketplace. Search, compare and discover advertiser products.
Related MCP Servers
- AlicenseAqualityDmaintenanceKlarna-style product discovery for AI shopping agents. Makes product catalogs machine-readable so AI agents can search, compare, and purchase products programmatically.6MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to search, compare, buy, and sell products across multiple e-commerce platforms through 13 marketplace tools.1MIT
- AlicenseNot gradedqualityDmaintenanceReal-time Shopee competitor price monitoring, powered by AI agents through the Model Context Protocol (MCP). Enables AI agents to track, analyze, and alert on price movements across Shopee Southeast Asia.1MIT