Market

io.github.vistoya由 GitHub 帳號 vistoya 發布v1.0.0更新於 Oct 24, 2026

Search and get fashion products recommendations across multiple e-ecom stores

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取商業與電商

概覽

AI 產生的概覽

Vistoya Market 讓助理跨多個已收錄的時尚商店進行語意搜尋,查找並比較商品與品牌。

可以做什麼
  • 以自然語言查詢加上類別、顏色、性別、價格等篩選條件,在已收錄的時尚商店中搜尋商品
  • 依商品 ID 尋找相似商品,用於「更多類似款」推薦
  • 取得單一商品的完整資訊:描述、店家資訊、圖片、SKU 變體與價格
  • 依風格、產地或美感搜尋品牌,並找出與指定品牌相似的品牌
  • 列出可用的篩選維度(類別、顏色、材質、品牌、價格區間)以輔助查詢
適用情境
適合讓助理協助選購、比較或發掘跨店時尚單品與品牌,例如在預算內找一件外套,或尋找與現有商品相似的替代款。
執行需求
遠端 Streamable HTTP 端點;目前不需驗證、API 金鑰或環境變數。README 另提供以 npx 執行的設定輔助工具,以及供不支援遠端的用戶端使用的 mcp-remote 橋接,這兩種方式需要 Node.js。
安裝前請注意
此端點為公開預覽版且目前無驗證,可用性與行為可能變動。查詢內容與商品 ID 會傳送給第三方 Vistoya 服務。回傳的僅是商品目錄資訊,此伺服器似乎不下單也不處理付款。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Market,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.vistoya%2Fmarket/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "market": {
      "type": "http",
      "url": "https://api.vistoya.com/mcp"
    }
  }
}

README

Vistoya MCP

Semantic search and recommendations across fashion stores, exposed as a Model Context Protocol server. Connect any MCP-compatible AI agent (Claude, Cursor, VS Code, ChatGPT, etc.) and let it discover products, find visually similar items, and explore stores in the Vistoya marketplace.

  • Registry name: io.github.vistoya/market
  • Endpoint: https://api.vistoya.com/mcp
  • Transport: Streamable HTTP
  • Website: https://vistoya.com

Quick setup

sh
npx @vistoya/mcp

Automatically detects and configures Claude Desktop, Claude Code, Cursor, Windsurf, and VS Code. Restart your AI client after running.

What it does

Vistoya indexes fashion products from many stores and embeds them with a vision-language model. The MCP server lets agents query that index in natural language and reason over the results.

Tools

ToolDescription
discover_productsSemantic search across all indexed stores. Accepts a natural-language query plus optional filters (category, color, gender, price, etc.) and returns ranked products.
find_similar_productsGiven a product ID, return visually and semantically similar products.
discover_brandsSemantic search over brand profiles. Find brands by style, origin, or aesthetic (e.g. "Italian streetwear brands", "minimalist Scandinavian labels").
find_similar_brandsGiven a brand name or key, return similar brands using brand-profile vectors.
get_productFetch full details for a single product by ID.
get_filtersList available filter values (categories, colors, materials, brands, …) so the agent knows what's filterable.

Manual install

Claude Desktop / Claude Code

Add to claude_desktop_config.json (or your Claude Code MCP config):

json
{  "mcpServers": {    "vistoya": {      "url": "https://api.vistoya.com/mcp"    }  }}

Cursor

Add to ~/.cursor/mcp.json:

json
{  "mcpServers": {    "vistoya": {      "url": "https://api.vistoya.com/mcp"    }  }}

VS Code (MCP extension)

Add to your mcp.json:

json
{  "servers": {    "vistoya": {      "type": "http",      "url": "https://api.vistoya.com/mcp"    }  }}

Generic stdio fallback (clients that don't support remote yet)

Use mcp-remote as a bridge:

json
{  "mcpServers": {    "vistoya": {      "command": "npx",      "args": ["-y", "mcp-remote", "https://api.vistoya.com/mcp"]    }  }}

Example prompts

Once connected, try:

  • "Find me a black leather jacket under $300"
  • "Show me something similar to this product"
  • "What cozy sweaters do you have for fall?"
  • "Find me running shorts under $100"

Discoverability

This server is published on the official MCP Registry. You can find it at:

https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.vistoya/market

Status

Public preview. The endpoint is publicly reachable and does not currently require authentication.

License

MIT — see LICENSE.

Contact

Issues and feature requests: open an issue on this repo.

來源:README.md,提交 5bd4e2a

工具

6

discover_products

Find fashion products using natural language and/or structured filters. Provide a `query` for semantic ranking via multimodal text+image embeddings ("oversized wool coat", "black leather jacket", "minimalist gold jewelry", "linen shirt for a beach wedding under $200") — best for open-ended discovery. Keep queries concrete: noun-led with up to one or two modifiers works best ("summer linen shirt" beats "breathable linen shirt perfect for summer"). Provide only structured filters (category, brand, colors, gender, price, etc.) for pure browse — results are recency-ranked and paginate cleanly. Combine both for filtered semantic search. At least one of query or a filter must be provided. Example calls (notice the sparse filter population — descriptive attributes stay in `query`, not in structured fields): - "linen wedding guest dress under $200" → {query: "linen wedding guest dress", gender: "women", max_price: 200, materials: ["linen"]} - "wool coat under $300" → {query: "wool coat", gender: "women", max_price: 300, materials: ["wool"]} - "browse women's black dresses $100-$300" → {gender: "women", category: "clothing/dresses", colors: ["black"], min_price: 100, max_price: 300} - "Acne Studios outerwear" → {query: "outerwear", brand: "Acne Studios", gender: "women"} Returns compact product cards: AI-generated summary, price, images, tags, and compact availability by color/size; variant price differences are nested under the availability dimension that determines price. For merchant description, store info, SKU-level variants, exact variant prices, and all product images, call get_product with a product ID from these results. Multi-currency prices supported (e.g. "under 200 zł" or min_price=200 + currency="PLN"); returned prices render in the requested currency when provided.

輸入參數pagebrandlimitquerycolorsgenderseasonstylescountrypatternsleevescategory另有 13 個

find_similar_products

Given a product ID, find similar products across the entire catalog. Useful for "more like this" recommendations or finding alternatives. Returns compact product cards, not full variant detail; call get_product for SKU-level variants, exact variant prices, merchant description, store info, and all images. Returns page and hasNextPage. Returns up to 20 results per page, paginated (max 3 pages).

輸入參數pagelimitcountrycurrencyproduct_id必填

discover_brands

Find fashion brands using natural language, structured filters, or both. Best for queries like "Italian streetwear brands", "Scandinavian minimalist brands", "Japanese technical outerwear", "brands with avant-garde tailoring", or qualified similarity such as "brands like Rick Owens for technical outerwear". For a plain "brands like X" request, use find_similar_brands. Country adjectives ("Italian", "Scandinavian", "Nordic", "Japanese", "Iberian", "Benelux") are parsed server-side into shipping-origin filters; you don't need to translate them to ISO codes. `query` is optional — provide a query, structured filters, or both. Brand country/shipping signals are best-effort and separate from product availability.

輸入參數limitquerystylecountryprice_tiergender_focuscategory_focusships_from_country

find_similar_brands

Given an active catalog brand name or merged alias, find similar brands using brand-profile vectors generated during product indexing. Unknown or ambiguous seeds return no brands. Returns up to 20 brands.

輸入參數brand必填limitcountry

get_product

Get the detailed response for a specific product ID. Use this after discover_products or find_similar_products when you need merchant description, store info, all images, SKU-level availability variants, SKU, colorKey/size matrix, exact variant prices/compareAtPrice in the requested currency, and the direct link to purchase.

輸入參數countrycurrencyproduct_id必填

get_filters

Returns available filter values in the catalog. By default returns categoryTree plus brands, colors, materials, genders, occasions, seasons, styles, silhouettes, currencies, and price range. Use "fields" to request only specific dimensions — faster and less data. "categoryTree" is a flat DFS-ordered list of { value, label } entries; hierarchy is encoded in the value slug (e.g. "clothing/jackets/bomber-jackets"), parents appear before descendants, and every value can be passed directly to discover_products.category. Use "brand_search" to search brands by prefix instead of listing all. Pass "gender" to scope categoryTree to that gender (women/men/girls/boys); omit to see the merged union.

輸入參數fieldsgendercountrybrand_pagebrand_search

版本歷史

1
  1. v1.0.0最新Sep 16, 2026

評分

已滿足適用檢查項的 100%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分