Faceabot Stores for AI agents

Where an AI agent can shop by country: UCP stores verified by Faceabot, big retailers. Free.

使うべきか

品質と安全性

A
説明の品質
90%
スキーマの完全性
79%
命名の品質
92%
ポイズニングのリスク
100%
権限の一致
100%
プロトコルへの準拠
100%

検出事項(1)

  • LOWTool 'list_store_categories' description lacks action verblist_store_categories 内

ツール定義とプロトコルへの準拠に関する自動分析に基づいています。

コンテキストコスト

~847トークン数(ツール定義)
~697 B一般的なレスポンスサイズ
注意への影響は中程度(128k コンテキストの 0.66%)

これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。

インストール

ワンクリックインストール

これを `claude_desktop_config.json` ファイルに追加してください:

{
  "mcpServers": {
    "stores": {
      "url": "https://faceabot.com/tools-mcp/stores"
    }
  }
}

リモートエンドポイント

https://faceabot.com/tools-mcp/storesstreamable-http

できること

ツール一覧

ツール(5)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢find_store(query, country, category, agent_checkout_only, limit)

Where can I (an AI agent) shop for this product, for my human's country? Returns stores that Faceabot verified for agents: their UCP MCP endpoint (search_catalog, get_product, checkout), whether they ship to the country, plus the country's big retailers that let agents read (robots.txt) and the Shopify cross-store search. Any language. Use when: your user wants to buy something (washing machine, running shoes, perfume…). Example: {"query":"washing machine","country":"BE"}

入力スキーマ

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Product or need in any language, e.g. washing machine, lave-linge, 洗濯機"
    },
    "country": {
      "type": "string",
      "description": "Your human's country (ISO code or name), e.g. BE, Japan"
    },
    "category": {
      "type": "string",
      "description": "Optional category id (see list_store_categories)"
    },
    "agent_checkout_only": {
      "type": "boolean",
      "description": "true = only stores declaring agent checkout"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 20,
      "default": 5
    }
  },
  "required": [
    "query"
  ]
}
🟢store_details(domain, country, query)

One store's record: UCP version and MCP endpoint, capabilities, tools listed, countries it ships to, robots.txt rules for agents, last checks, and the exact search_catalog call. Example: {"domain":"allbirds.com","country":"US"}

入力スキーマ

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "description": "Store domain, e.g. allbirds.com"
    },
    "country": {
      "type": "string",
      "description": "Optional: your human's country, to check shipping"
    },
    "query": {
      "type": "string",
      "description": "Optional product words for the call template"
    }
  },
  "required": [
    "domain"
  ]
}
🟡get_agent_profile(agent_name)

UCP stores (Shopify and others) ask every agent for meta['ucp-agent'].profile: the https URL of a JSON file describing it. No website to publish one? Faceabot hosts yours, free: one URL per agent name, browse-only (catalog search and product lookup, no payment handler: it cannot pay). Same name = same URL. Faceabot never sees your searches. Example: {"agent_name":"Travel helper by Acme"}

入力スキーマ

{
  "type": "object",
  "properties": {
    "agent_name": {
      "type": "string",
      "description": "Your agent's name (2-80 characters), ideally with its maker, e.g. \"Travel helper by Acme\""
    }
  },
  "required": [
    "agent_name"
  ]
}
🟢list_store_categories

The product categories Faceabot uses to classify stores, with how many verified stores each has.

入力スキーマ

{
  "type": "object",
  "properties": {}
}
🟢ai_shopping_observatory(days)

What AIs look for on Faceabot (by country and category), which stores let AI agents in, who charges what to be shown in AI answers (Google, OpenAI, Meta, Perplexity, Shopify… dated facts with sources), and Faceabot's weekly test for paid placements in Shopify's cross-store search. Example: {}

入力スキーマ

{
  "type": "object",
  "properties": {
    "days": {
      "type": "integer",
      "minimum": 1,
      "maximum": 365,
      "default": 30
    }
  }
}

コミュニティ

このサーバーを評価する

エビデンス

最近の観測

検証済みバージョンは記録されていませんツール 5 件