smart-retail-mcp
🤖 Smart Retail MCP Server
AIエージェントに在庫予測分析機能を提供する、Model Context Protocol (MCP) ベースのツールサーバーです。
利用可能なツール
ツール | 説明 |
| 全商品の現在の在庫と、サプライヤーの納期を取得します |
| 過去N日間の商品ごとの平均日次販売速度を計算します |
| 在庫が次の納品前に切れる場合に、補充アラートを作成します |
Related MCP server: vanam-erp-mcp
アーキテクチャ
src/
├── index.ts → Definición e implementación de herramientas MCP (stdio transport)
├── db.ts → Pool de conexión a PostgreSQL
└── seed.ts → Script para insertar datos de prueba設定
環境変数 (.env)
DATABASE_URL=postgresql://usuario:password@localhost:5432/smart_retailスクリプト
npm start # Ejecutar el servidor MCP
npm run dev # Desarrollo con hot-reload (tsx watch)
npm run seed # Insertar datos de prueba
npm run build # Compilar TypeScript依存関係
@modelcontextprotocol/sdk— MCP公式SDKpg— PostgreSQLクライアントdotenv— 環境変数
通信
サーバーはstdio(stdin/stdout)経由で通信します。Next.jsフロントエンドは、MCP SDKのStdioClientTransportを使用して子プロセスとして起動します。HTTPポートは公開しません。
ライセンス
ISC
Available Tools
3 toolscreate_ai_recommendationA
Crea una alerta de reabastecimiento en la base de datos cuando detectas que el stock se agotará antes de que el proveedor pueda entregar.
Inputs: reason (required), product_id (required), recommended_order_qty (required).
get_current_stockA
Obtiene los niveles actuales de inventario de todos los productos y los tiempos de entrega del proveedor.
Inputs: no named parameters.
get_sales_velocityA
Calcula el promedio de ventas diarias de los productos en los últimos X días. Útil para predecir cuándo se agotará el stock.
Inputs: days (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool targets a distinct inventory concern: current stock and lead times, sales velocity, and creating restock alerts. There is no meaningful overlap, so an agent can select the correct tool without ambiguity.
All tool names follow a consistent verb_noun pattern: get_current_stock, get_sales_velocity, create_ai_recommendation. The naming is predictable and clear.
Three tools is at the low end, but each tool has a clear role in the inventory-alerting workflow. The count feels appropriate for a narrow purpose, though the broad server name could imply more coverage.
The set covers the input side well, but create_ai_recommendation is a create-only operation with no way to list, update, or delete existing recommendations. This leaves agents with a dead end for managing alert state.
Related MCP Connectors
MCP server for building and testing AI agents with multi-model experimentation and insights.
Hosted MCP for e-commerce: live product catalog, stock, and pricing for AI agents.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
MCP server connecting AI agents to non-custodial staking data across 130+ networks.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceInventory Management AI - MCP server providing AI-powered tools and automation by MEOK AI Labs8 npm36 PyPIMIT
- FlicenseAqualityDmaintenanceMCP server for querying inventory items and stock levels via internal API, enabling AI chatbots to look up product codes and current quantities.2-
- AlicenseNot gradedqualityDmaintenancePredictive supply-chain MCP server that forecasts material confirmation risks and enables AI clients to interact with the system via natural language.MIT
- FlicenseNot gradedqualityCmaintenanceEnterprise-grade MCP server for intelligent supply chain analytics, enabling managers to investigate forecast accuracy, vendor performance, demand trends, and root causes using natural language.-