Products API MCP Server
An MCP server that retrieves product data from the DummyJSON API, supporting filtering by various parameters like ID, title, category, brand, price and rating.
README
My First MCP Project
This project demonstrates the use of MCP (Model Context Protocol) server that retrieves data from the DummyJSON API. Built using Cursor IDE with the default agent.
Table of Contents
Features
Products API Tools
- get_products
- Description: Get a list of products with optional filtering and pagination
- Parameters:
id(string, optional): Filter products by IDq(string, optional): Filter products by titlecategory(string, optional): Filter products by categorybrand(string, optional): Filter products by brandprice(number, optional): Filter products by pricerating(number, optional): Filter products by ratingskip(number, optional, default: 0): Number of products to skiplimit(number, optional, default: 10): Maximum number of products to return
- Returns: A list of products matching the specified criteria
- Data Source: DummyJSON API (https://dummyjson.com/products)
Installation and Usage
Prerequisites
- Node.js (version 23 or higher)
- Docker and Docker Compose
- WSL2 (if using Windows)
Using Docker (Recommended)
- Clone the repository:
git clone [repository-url]
cd my-first-mcp
- Install dependencies:
npm install
- Compile TypeScript:
npm run build
- Start containers using Docker Compose:
docker-compose up -d
⚠️ Important Notes
For WSL Users
If you're using WSL on Windows, you might encounter connection issues when using "localhost". Follow these steps:
- Find your WSL IP:
ip addr show eth0 | grep -oP '(?<=inet\s)\d+(\.\d+){3}'
- Use this IP instead of "localhost" in the PostgreSQL connection string
Cursor Configuration
To configure this MCP server with Cursor:
- Open Cursor
- Press:
- Windows/Linux:
Ctrl + Shift + P - macOS:
Cmd + Shift + P
- Windows/Linux:
- Type "Configure MCP Server" and select it
- Add the appropriate configuration based on your setup:
For Windows (without WSL) or Linux:
{
"mcpServers": {
"postgres": {
"command": "node",
"args": ["ABSOLUTE_PATH_TO_PROJECT/src/index.ts"]
}
}
}
For WSL Users:
{
"mcpServers": {
"postgres": {
"command": "wsl.exe",
"args": [
"-e",
"ABSOLUTE_PATH_TO_NODE/.nvm/versions/node/v23.11.0/bin/node",
"ABSOLUTE_PATH_TO_PROJECT/src/index.ts"
]
}
}
}
To find your Node.js path, run:
which node
License
This project is licensed under the MIT License.
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。