Market Price Finder
Enables querying and comparing product prices across different marketplaces with real-time updates. Deployable on Cloudflare Workers with tools for searching products, comparing prices, and retrieving price history.
README
Market Price Finder MCP Server written in TypeScript (Cloudflare Workers Deployment)
This project is a Model Context Protocol (MCP) server built on Cloudflare Workers that helps find and compare market prices for products. It provides tools for querying and analyzing product prices across different marketplaces.
An MCP server is a specialized server that implements the Model Context Protocol, allowing AI models to interact with external tools and services. In this case, our server provides tools for market price analysis.
Features
- Query product prices from various marketplaces
- Compare prices across different vendors
- Real-time price updates
- No authentication required for basic usage
- Deployable on Cloudflare Workers platform
Getting Started
Option 1: Quick Deploy
Click the button below to deploy directly to Cloudflare Workers:
After deployment, your server will be available at: remote-mcp-server-authless.<your-account>.workers.dev/sse
Option 2: Local Development
To set up the project locally, follow these steps:
- Create a new project using the template:
npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless
- Install dependencies:
cd my-mcp-server
npm install
- Start the development server:
npm run dev
Customizing the Server
Adding New Tools
You can extend the server's functionality by adding your own tools:
- Open
src/index.ts - Locate the
init()method - Add new tools using
this.server.tool(...)
For more information about creating tools, check the MCP tools documentation.
Using the Server
Method 1: Cloudflare AI Playground
The easiest way to interact with your MCP server is through the Cloudflare AI Playground:
- Visit Cloudflare AI Playground
- In the connection settings, enter your server URL:
- For deployed server:
remote-mcp-server-authless.<your-account>.workers.dev/sse - For local development:
http://localhost:8787/sse
- For deployed server:
- Start using the market price finder tools through the playground interface
Method 2: Claude Desktop Integration
You can also use the server with Claude Desktop:
- Install the MCP remote proxy:
npm install -g mcp-remote
- Configure Claude Desktop:
- Open Claude Desktop
- Go to Settings > Developer > Edit Config
- Update the configuration:
{
"mcpServers": {
"market-finder": {
"command": "npx",
"args": [
"mcp-remote",
"http://localhost:8787/sse" // Use your deployed URL for production
]
}
}
}
- Restart Claude Desktop to apply changes
API Documentation
Our MCP server provides the following tools:
searchProduct: Search for product pricescomparePrice: Compare prices across marketplacesgetPriceHistory: Get historical price data (if available)
For detailed API documentation and examples, check the source code comments in src/index.ts.
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。