Disclose MCP Server

Disclose MCP Server

Enables AI agents to query merchant operational signals like return rates, fulfillment accuracy, and chargeback ratios published through the Disclose protocol. Provides tools to fetch merchant disclosures and check signal coverage for completeness.

Category
访问服务器

README

Disclose MCP Server

An MCP server for querying merchant disclosure signals published via Disclose.

What it does

Merchants publish operational signals — return rates, fulfillment accuracy, chargeback ratios — along with permitted use terms. This MCP server lets any AI agent query that data directly.

The server checks four discovery paths in order:

  1. /.well-known/disclose — canonical path
  2. /.well-known/disclose.json — canonical path with explicit extension
  3. /disclose.json — fallback for hosted platforms like Shopify that do not support the /.well-known/ directory
  4. JSON-LD block in page <head> — for merchants using script-tag injection

Signals sourced from the Shopify API and computed by Sure Signal are returned with full provenance metadata: source, reported_by, computed_by, attestation_level, and attestation. Attestation is null until a third-party Signatory (such as Loop Returns) cryptographically signs the signal.

Available Tools

get_merchant_disclosure(domain)

Fetches a merchant's published disclosure signals from their domain. Returns all signals the merchant has chosen to publish, with provenance metadata, or an error if no disclosure is found.

Example: get_merchant_disclosure("example.com")

check_signal_coverage(domain)

Returns a structured coverage report for the seven Sure Signal V1 signals: which are present, which are missing, whether any carry attestation, and an overall coverage percentage. Useful for agents evaluating merchant data completeness before a purchase decision.

The seven V1 signals:

  • product_return_rate
  • on_time_shipment_rate
  • refund_processing_time_median_days
  • chargeback_rate
  • dispute_win_rate
  • platform_seller_tenure_days
  • order_accuracy_rate

Example: check_signal_coverage("example.com")

Setup

Prerequisites

  • Python 3.10 or higher
  • uv package manager

Installation

  1. Clone this repository:

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选