GoBuy Product Trust

io.github.digitalmentes7-maker由 GitHub 账号 digitalmentes7-maker 发布v1.0.0更新于 Oct 24, 2026

Marketplace-evidence trust scores for AI agents: a 0-100 Evidence Score with signal breakdown.

已验证Streamable HTTP可网页运行商业与电商

概览

AI 生成的概览

一个远程 MCP 端点,为商品返回 0-100 的市场证据可信度评分及信号明细。

可以做什么
GoBuy Product Trust 是通过托管端点访问的远程 MCP 服务器。根据其注册表描述,它为 AI 代理提供市场证据可信度评分:一个 0-100 的 Evidence Score 以及底层信号的明细。所提供的清单未列出具体工具,因此此处不说明其确切操作。
适用场景
当助手需要快速获得市场商品的可信度或证据评级,并需要信号明细来解释该评级时,可以考虑使用。若你需要的是商品搜索、比价或购买而非评分,则不太适用。
运行要求
需要支持 streamable HTTP 传输的客户端以及对远程端点的网络访问。清单声明无需身份验证、无环境变量、无请求头,也不需要本地软件包或运行时。
安装前请注意
清单未声明任何凭据,但该服务器是第三方托管端点,发送给它的任何商品或查询数据都会离开你的设备。所提供材料未说明评分方法与信号来源,因此应把评分视为参考而非权威结论。

安装

在 SourceWeft 中

  1. 打开 控制台中的 GoBuy Product Trust,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.digitalmentes7-maker%2Fgobuy-product-trust/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "gobuy-product-trust": {
      "type": "http",
      "url": "https://mcp.gobuy.ai/mcp"
    }
  }
}

工具

5

check_product_trust

Check Product Trust Score

Return the GoBuy Evidence Score (0-100) and complete signal breakdown for a single retailer listing on Amazon, Walmart, Target, or Best Buy. This is the GPV-1 gate evaluator: score >= 55 PASS, 35-54 FLAG, < 35 or not-indexed BLOCK. The returned verdict is an evidence tier (strong/moderate/weak), not a computed GPV-1 checkout decision. Use this for individual product lookups. To compare and rank multiple products, use `compare_products` instead. Use `analyze_reviews` only for explicitly requested Amazon review-sample analysis; this lookup never fetches reviews. Read-only — does not modify any state or place orders. Scores describe available marketplace records, not product quality or purchase recommendations.

输入参数retailer必填product_id必填

compare_products

Compare and Rank Products

Fetch Evidence Scores for 2-20 retailer listings and rank them by GoBuy Evidence Score (highest first). Use this when an agent is choosing between multiple products. For a single product lookup, use `check_product_trust` instead. Read-only — does not modify any state or place orders, and never fetches reviews. Unindexed products rank last. This is not purchase advice.

输入参数products必填

analyze_reviews

Analyze Amazon Review Sample

Analyzes up to 100 recent reviews (~30-90 seconds). Bright Data can take longer. Use only when Amazon review-sample analysis is explicitly requested; use `check_product_trust` for an existing evidence score or `compare_products` to rank listings. On-demand sampling without your cookie; reviews are sorted within the returned sample, but the provider does not guarantee the listing's newest 100. May trigger paid Bright Data collection and writes a seven-day analysis cache. force_refresh bypasses that cache and may start another paid scrape. A later explicit call without force_refresh resumes a pending job without a new scrape. Heuristics do not prove authenticity.

输入参数retailer必填product_id必填force_refresh

check_store_score

Check Store Trust and Readiness Score

Retrieve a previously scored independent store or Shopify storefront by domain: agent-readiness, trust signals, structured data, and review system. Use this first for an existing store score; it is read-only and does not crawl. If not scored yet, use `scan_store` for an explicit fresh scan. For a retailer product listing rather than a storefront, use `check_product_trust`.

输入参数domain必填

scan_store

Scan and Score Store Live

Score any online store live with a fresh crawl (~20 seconds). Use when `check_store_score` returns 404 or a fresh scan is explicitly requested. Use `check_store_score` instead to retrieve an existing result without crawling. Requires a full HTTP(S) URL and updates the stored store score; repeated calls can trigger new scans. For marketplace product evidence, use `check_product_trust` instead. Docs: https://docs-gobuy.pages.dev

输入参数url必填

版本历史

1
  1. v1.0.0最新Sep 16, 2026

评分

已满足适用检查项的 83%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分

    请声明包含 README 的 GitHub 仓库,或在 OAuth 受保护资源元数据中提供 resource_documentation。

  • 许可证不适用

    托管服务按其提供方的条款使用,因此这里不要求许可证。此检查项不计入百分比。