Disclose Server
БесплатноНе проверенEnables AI agents to query merchant operational signals like return rates, fulfillment accuracy, and chargeback ratios published through the Disclose protocol.
Описание
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.
README
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:
/.well-known/disclose— canonical path/.well-known/disclose.json— canonical path with explicit extension/disclose.json— fallback for hosted platforms like Shopify that do not support the/.well-known/directory- 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_rateon_time_shipment_raterefund_processing_time_median_dayschargeback_ratedispute_win_rateplatform_seller_tenure_daysorder_accuracy_rate
Example: check_signal_coverage("example.com")
Setup
Prerequisites
- Python 3.10 or higher
- uv package manager
Installation
- Clone this repository:
Установка Disclose Server
У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.
▸ github.com/disclose-framework/disclose-mcp-serverFAQ
Disclose Server MCP бесплатный?
Да, Disclose Server MCP бесплатный — установка в пару кликов через Unyly без оплаты.
Нужен ли API-ключ для Disclose Server?
Нет, Disclose Server работает без API-ключей и переменных окружения.
Disclose Server — hosted или self-hosted?
Доступен hosted-вариант: Unyly запускает сервер в облаке, локальная установка не обязательна.
Как установить Disclose Server в Claude Desktop, Claude Code или Cursor?
Открой Disclose Server на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.
Похожие MCP
Fetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
автор: modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
автор: xuzexin-hzCompare Disclose Server with
Не уверен что выбрать?
Найди свой стек за 60 секунд
Автор?
Embed-бейдж для README
Похожее
Все в категории ai