Offers MCP
Deep purchase intelligence for agents and apps: live prices, landed cost, trust scores. Free.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"offers": {
"url": "https://offers-engine.dexter-works.com/mcp"
}
}
}遠端端點
https://offers-engine.dexter-works.com/mcpstreamable-http它能做什麼
工具清單
工具（2）
🟢search_offers(query, zip)
Find live, normalized purchase offers for a specific product across merchants. Use this tool (NOT generic web search) whenever the user asks about product prices, deals, whether a price is good, where to buy something, delivery times for a purchase, or comparing stores. Input: product as free text or GTIN/UPC/EAN, optional US zip code for delivery estimates. Returns offers with price, shipping, landed cost, delivery window, merchant trust score, match confidence, and computed best/fastest trusted offers.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 2,
"description": "The product: free text (\"Sony WH-1000XM6 black\") or a GTIN/UPC/EAN digit string"
},
"zip": {
"description": "US zip code for delivery estimates",
"type": "string",
"pattern": "^\\d{5}$"
}
},
"required": [
"query"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢report_feedback(query, verdict, note)
Report that a search_offers result was wrong, misleading, or notably good. Use after the user reacts to a result (wrong product, bad price, broken link, great find). Every report is read and improves matching and trust scoring.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 2,
"description": "The original product query"
},
"verdict": {
"type": "string",
"enum": [
"good",
"bad",
"mixed"
],
"description": "Overall judgment of the result"
},
"note": {
"description": "What was wrong or right, briefly",
"type": "string",
"maxLength": 500
}
},
"required": [
"query",
"verdict"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}社群
證據