MCP Inflow Ingredients
Enables AI assistants to interact with Inflow Inventory API for managing ingredients/products and inventory operations. Supports product creation, updates, search, and stock adjustments through natural language commands.
README
MCP Inflow Ingredients
An MCP (Model Context Protocol) server that enables AI assistants to interact with Inflow Inventory API, allowing them to manage ingredients/products and inventory programmatically.
Features
Product/Ingredient Management
- List Ingredients: Search and filter products with smart search
- Get Ingredient Details: Retrieve full information about specific products
- Get Inventory Summary: View quantities (on hand, available, reserved, etc.)
- Search Ingredients: Full-text search across name, description, SKU, barcode
- Create Ingredient: Add new products to inventory
- Update Ingredient: Modify existing product information
Inventory Management
- Create Stock Adjustment: Adjust inventory quantities for products
- List Stock Adjustments: View adjustment history
- Get Stock Adjustment: Retrieve details of specific adjustments
Setup
Prerequisites
- Node.js 18+ installed
- Inflow Inventory account with API access
- Inflow API key and Company ID
Installation
- Navigate to the project directory:
cd ~/mcp-inflow-ingredients
- Install dependencies:
npm install
- Configure environment variables:
cp .env.example .env
# Edit .env with your Inflow API credentials
Required environment variables:
INFLOW_API_KEY: Your Inflow API keyINFLOW_COMPANY_ID: Your Inflow company IDINFLOW_API_URL: API base URL (default: https://cloudapi.inflowinventory.com)INFLOW_API_VERSION: API version (default: 2025-06-24)
Test Connection
Verify your Inflow API connection:
npm run test:connection
This will test basic API connectivity and list products.
MCP Server Usage
Running the Server
Start the MCP server:
npm start
For development with auto-reload:
npm run dev
Available Tools
Product/Ingredient Tools
list_ingredients
- List all products with optional filters
- Parameters: name, description, isActive, barcode, smart, include, limit
get_ingredient
- Get detailed information about a specific product
- Parameters: productId (required), include
get_inventory_summary
- Get inventory summary with quantities
- Parameters: productId (required)
search_ingredients
- Search products using full-text search
- Parameters: query (required), limit, include
create_ingredient
- Create a new product
- Parameters: productId (UUID, required), name (required), sku, description, isActive, additionalFields
update_ingredient
- Update an existing product
- Parameters: productId (required), name, sku, description, isActive, additionalFields
Inventory Tools
create_stock_adjustment
- Create a stock adjustment to modify inventory
- Parameters: stockAdjustmentId (UUID, required), locationId (required), lines (array, required), adjustmentReasonId, notes, adjustmentDate
list_stock_adjustments
- List stock adjustments
- Parameters: adjustmentNumber, include, limit
get_stock_adjustment
- Get details of a specific adjustment
- Parameters: stockAdjustmentId (required), include
Project Structure
mcp-inflow-ingredients/
├── index.js # Main MCP server entry point
├── types.ts # TypeScript definitions for JSDoc
├── package.json # Node.js dependencies and scripts
├── .env # Environment variables (not in git)
├── .env.example # Environment template
├── .mcp.json # MCP server configuration
├── src/
│ ├── inflow-client.js # Inflow API client
│ └── handlers/
│ ├── product-handlers.js # Product operations
│ └── inventory-handlers.js # Inventory operations
├── tests/
│ └── test-connection.js # API connection test
└── docs/
└── swagger.json # Inflow API documentation
Development
Type Safety
This project uses JSDoc with TypeScript type definitions for type safety without a build step. Types are defined in types.ts and imported via JSDoc comments.
Testing
Run the connection test:
npm run test:connection
Scripts
npm start- Start the MCP servernpm run dev- Development mode with auto-reloadnpm run test:connection- Test Inflow API connection
Inflow API Resources
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。