ShopGraph
Извлечение данных о товаре из ссылки на интернет-магазин
Добавьте сервер в «Мои MCP» — получите адрес подключения для Claude и ChatGPT.
Добавить в «Мои MCP»Нужно войти или зарегистрироваться — вернём на эту страницу.
Описание
ShopGraph вытаскивает структурированные данные о товаре из страницы интернет-магазина: название, цену, бренд, изображения, наличие. Пригодится тем, кто сравнивает цены, собирает каталоги или готовит товары для продажи через ИИ-агентов. Сервер извлекает полные или базовые сведения о товаре по ссылке, используя разметку schema.org и при необходимости языковую модель, и умеет разобрать уже загруженный HTML без повторного запроса. Отдельный инструмент выставляет товару оценку от 0 до 100 — насколько полны и понятны данные о нём для ИИ-агентов. Базовое извлечение бесплатно в пределах месячной квоты, дальнейшие вызовы и полное извлечение оплачиваются за запрос.
Инструменты · 4
из ответа tools/list
enrich_basic
enrich_basic
Extract basic product attributes from a URL (name, price, brand, availability). Faster and cheaper than enrich_product. 50 free calls/month — no payment needed. Paid: $0.01 per call after free tier. Each field carries verification metadata in _shopgraph: provenance (field_method — which source/tier produced it: schema_org, llm, or hybrid), freshness (field_freshness — recency + volatility_class, for volatile fields like price & availability), and abstain (a field is null when ShopGraph cannot verify it on the page). Rely on provenance, freshness, and the abstain signal to decide what to trust.
enrich_basic(url: string, format?: string, force_refresh?: boolean, include_score?: boolean, payment_method_id?: string, minimum_confidence?: number, strict_confidence_threshold?: number)
// inputSchema
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Product page URL to extract data from"
},
"format": {
"enum": [
"default",
"ucp"
],
"type": "string",
"default": "default",
"description": "Output format. \"ucp\" returns UCP line_item format. Default: \"default\"."
},
"force_refresh": {
"type": "boolean",
"description": "Bypass cache entirely. Always triggers live extraction. Costs 3x credits."
},
"include_score": {
"type": "boolean",
"description": "Include agent-readiness score in response."
},
"payment_method_id": {
"type": "string",
"description": "Stripe payment method ID for MPP payment"
},
"minimum_confidence": {
"type": "number",
"maximum": 1,
"minimum": 0,
"description": "Auto-refresh if any cached field's DECAYED confidence falls below this threshold. Costs 2x credits when refresh triggers, 0.25x on cache hit."
},
"strict_confidence_threshold": {
"type": "number",
"maximum": 1,
"minimum": 0,
"description": "Fields below this confidence will be nulled with explanation. Default: off."
}
},
"additionalProperties": false
}
enrich_html
enrich_html
Extract product data from raw HTML you already have (no HTTP fetch needed). Ideal when using Bright Data, Firecrawl, or any scraping API — pipe the HTML through ShopGraph for structured product data. Uses schema.org + LLM fallback. Costs $0.02 per call (cached results are free). Each field carries verification metadata in _shopgraph: provenance (field_method — which source/tier produced it: schema_org, llm, or hybrid), freshness (field_freshness — recency + volatility_class, for volatile fields like price & availability), and abstain (a field is null when ShopGraph cannot verify it on the page). Rely on provenance, freshness, and the abstain signal to decide what to trust.
enrich_html(url: string, html: string, format?: string, force_refresh?: boolean, include_score?: boolean, payment_method_id?: string, minimum_confidence?: number, strict_confidence_threshold?: number)
// inputSchema
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"html",
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Original URL of the page (used for context and caching)"
},
"html": {
"type": "string",
"description": "Raw HTML content of the product page"
},
"format": {
"enum": [
"default",
"ucp"
],
"type": "string",
"default": "default",
"description": "Output format. \"ucp\" returns UCP line_item format. Default: \"default\"."
},
"force_refresh": {
"type": "boolean",
"description": "Bypass cache entirely. Always triggers live extraction. Costs 3x credits."
},
"include_score": {
"type": "boolean",
"description": "Include agent-readiness score in response."
},
"payment_method_id": {
"type": "string",
"description": "Stripe payment method ID for MPP payment"
},
"minimum_confidence": {
"type": "number",
"maximum": 1,
"minimum": 0,
"description": "Auto-refresh if any cached field's DECAYED confidence falls below this threshold."
},
"strict_confidence_threshold": {
"type": "number",
"maximum": 1,
"minimum": 0,
"description": "Fields below this confidence will be nulled with explanation. Default: off."
}
},
"additionalProperties": false
}
enrich_product
enrich_product
Extract comprehensive product data from a URL including name, price, brand, images, availability, and more. Uses schema.org structured data when available, with LLM fallback. Costs $0.02 per call (cached results are free). Each field carries verification metadata in _shopgraph: provenance (field_method — which source/tier produced it: schema_org, llm, or hybrid), freshness (field_freshness — recency + volatility_class, for volatile fields like price & availability), and abstain (a field is null when ShopGraph cannot verify it on the page). Rely on provenance, freshness, and the abstain signal to decide what to trust.
enrich_product(url: string, format?: string, force_refresh?: boolean, include_score?: boolean, payment_method_id?: string, minimum_confidence?: number, strict_confidence_threshold?: number)
// inputSchema
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Product page URL to extract data from"
},
"format": {
"enum": [
"default",
"ucp"
],
"type": "string",
"default": "default",
"description": "Output format. \"ucp\" returns UCP line_item format. Default: \"default\"."
},
"force_refresh": {
"type": "boolean",
"description": "Bypass cache entirely. Always triggers live extraction. Costs 3x credits."
},
"include_score": {
"type": "boolean",
"description": "Include agent-readiness score in response."
},
"payment_method_id": {
"type": "string",
"description": "Stripe payment method ID for MPP payment"
},
"minimum_confidence": {
"type": "number",
"maximum": 1,
"minimum": 0,
"description": "Auto-refresh if any cached field's DECAYED confidence falls below this threshold. Costs 2x credits when refresh triggers, 0.25x on cache hit."
},
"strict_confidence_threshold": {
"type": "number",
"maximum": 1,
"minimum": 0,
"description": "Fields below this confidence will be nulled with explanation. Default: off."
}
},
"additionalProperties": false
}
score_product
score_product
Extract product data and return agent-readiness score (0-100). Scores structured data completeness, semantic richness, UCP compatibility, pricing clarity, and inventory signals. Full scoring breakdown included.
score_product(url: string, format?: string, payment_method_id?: string, strict_confidence_threshold?: number)
// inputSchema
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Product page URL to extract and score"
},
"format": {
"enum": [
"default",
"ucp"
],
"type": "string",
"default": "default",
"description": "Output format. \"ucp\" returns UCP line_item format. Default: \"default\"."
},
"payment_method_id": {
"type": "string",
"description": "Stripe payment method ID for MPP payment"
},
"strict_confidence_threshold": {
"type": "number",
"maximum": 1,
"minimum": 0,
"description": "Fields below this confidence will be nulled with explanation. Default: off."
}
},
"additionalProperties": false
}Вопросы, новые серверы, обсуждение MCP
t.me/rusmcp · t.me/RusMcp_bot