@dealx/mcp-server

@dealx/mcp-server

Enables LLMs to search ads on the DealX platform through the Model Context Protocol.

Category
访问服务器

README

@dealx/mcp-server

This is a Model Context Protocol (MCP) server for the DealX platform. It allows LLMs to interact with the DealX platform, specifically to search for ads.

Table of Contents

Overview

The DealX MCP Server implements the Model Context Protocol to provide a standardized way for LLMs to interact with the DealX platform. Currently, it supports searching for ads, with plans to add more functionality in the future.

What is MCP?

The Model Context Protocol (MCP) is a standardized way for LLMs to interact with external systems. It provides a structured interface for LLMs to access data and perform actions in the real world. This server implements the MCP specification to allow LLMs to interact with the DealX platform.

Installation

Prerequisites

  • Node.js (v20 or later)
  • npm (v11 or later)

MCP Configuration

To use this server with an LLM like Claude, you need to add it to your LLM's MCP configuration:

  1. Open your LLM's MCP configuration file:

    • Claude Desktop App:
      • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
      • Windows: %APPDATA%\Claude\claude_desktop_config.json
      • Linux: ~/.config/Claude/claude_desktop_config.json
    • Cline (VS Code Extension):
      • ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
  2. Add the DealX MCP server to the mcpServers section:

    {
      "mcpServers": {
        "dealx": {
          "command": "npx",
          "args": ["-y", "@dealx/mcp-server"],
          "env": {
            "DEALX_API_URL": "https://dealx.com.ua"
          },
          "disabled": false,
          "autoApprove": []
        }
      }
    }
    

Installation via npm

The easiest way to install the DealX MCP Server is via npm:

npm install -g @dealx/mcp-server

Installation for Development

If you want to modify the server or contribute to its development:

  1. Clone the repository:

    git clone <repository-url>
    cd dealx/mcp
    
  2. Install dependencies:

    npm install
    
  3. Create a .env file based on the .env.example file:

    cp .env.example .env
    
  4. Edit the .env file to set the appropriate values:

    # DealX API URL
    DEALX_API_URL=http://localhost:3001
    
    # Optional: Specify the port for the MCP server
    MCP_SERVER_PORT=3100
    
    # Optional: Log level (debug, info, warn, error)
    LOG_LEVEL=info
    
  5. Build the server:

    npm run build
    

Usage

Starting the Server

You can run the server in several ways:

  1. If installed globally:

    node node_modules/@dealx/mcp-server/build/index.js
    
  2. Using npx without installation:

    npx -y @dealx/mcp-server
    
  3. With environment variables:

    DEALX_API_URL=https://dealx.com.ua npx -y @dealx/mcp-server
    
  4. For development:

    npm start
    

Using with an LLM

Once configured in your LLM's MCP settings, you can use natural language to interact with the DealX platform.

Example prompts:

  • "Search for ads on DealX with the query 'laptop'"
  • "Find the newest 5 ads for 'iPhone' on DealX"
  • "Search DealX for apartments in Kyiv"

Available Tools

search_ads

Search for ads on the DealX platform.

Parameters:

  • query (string, optional): Search query string
  • sort (string, optional): Sort order (e.g., "-created" for newest first)
  • offset (number, optional): Pagination offset (starts at 1, default: 1)
  • limit (number, optional): Number of results per page (max 100, default: 30)

Example Usage:

{
  "query": "laptop",
  "sort": "-created",
  "offset": 1,
  "limit": 10
}

Extending the Server

The server is designed to be easily extended with additional tools. Here's how to add a new tool:

  • Define the tool in the TOOLS object in src/index.ts:

    const TOOLS = {
      SEARCH_ADS: "search_ads",
      NEW_TOOL: "new_tool", // Add your new tool here
    };
    
  • Create a new file in the src/tools directory for your tool implementation:

    // src/tools/new-tool.ts
    import { ErrorCode, McpError } from "@modelcontextprotocol/sdk/types.js";
    
    interface NewToolParams {
      // Define your tool parameters here
    }
    
    export async function newTool(params: NewToolParams) {
      try {
        // Implement your tool logic here
    
        return {
          content: [
            {
              type: "text",
              text: JSON.stringify(result, null, 2),
            },
          ],
        };
      } catch (error) {
        // Handle errors
        // ...
      }
    }
    
  • Add the tool to the ListToolsRequestSchema handler in src/index.ts:

    this.server.setRequestHandler(ListToolsRequestSchema, async () => ({
      tools: [
        // Existing tools...
        {
          name: TOOLS.NEW_TOOL,
          description: "Description of your new tool",
          inputSchema: {
            type: "object",
            properties: {
              // Define your tool parameters here
            },
            required: [], // List required parameters
          },
        },
      ],
    }));
    
  • Add the tool to the CallToolRequestSchema handler in src/index.ts:

    this.server.setRequestHandler(CallToolRequestSchema, async (request) => {
      const { name, arguments: args } = request.params;
    
      switch (name) {
        // Existing cases...
        case TOOLS.NEW_TOOL:
          return await newTool(args);
        default:
          throw new McpError(ErrorCode.MethodNotFound, `Unknown tool: ${name}`);
      }
    });
    
  • Import your new tool in src/index.ts:

    import { newTool } from "./tools/new-tool.js";
    

Planned Future Tools

The following tools are planned for future implementation:

  • create_ad: Create a new ad on the DealX platform
  • edit_ad: Edit an existing ad
  • delete_ad: Delete an ad
  • get_threads: Get discussion threads for an ad
  • create_thread: Create a new discussion thread

Development

Project Structure

mcp/
├── build/              # Compiled JavaScript files
├── src/                # TypeScript source files
│   ├── tools/          # Tool implementations
│   │   └── search-ads.ts
│   └── index.ts        # Main server implementation
├── .env                # Environment variables (not in git)
├── .env.example        # Example environment variables
├── package.json        # Project dependencies and scripts
├── tsconfig.json       # TypeScript configuration
└── README.md           # This file

npm Scripts

  • npm run build - Compile TypeScript to JavaScript
  • npm start - Start the server using the compiled JavaScript
  • npm run dev - Start the server in development mode with hot reloading
  • npm run lint - Lint the code using ESLint
  • npm run format - Format the code using Prettier
  • npm test - Run tests

Troubleshooting

Common Issues

Server Not Starting

If the server fails to start, check the following:

  • Make sure you have the correct Node.js version installed
  • Check that all dependencies are installed
  • Verify that the .env file exists and has the correct values
  • Check the console output for error messages

Connection Issues

If the LLM can't connect to the server:

  • Make sure the server is running
  • Check that the MCP configuration in the LLM's settings is correct
  • Verify that the path to the server executable is correct
  • Check that the environment variables are set correctly

API Connection Issues

If the server can't connect to the DealX API:

  • Make sure the DealX API is running
  • Check that the DEALX_API_URL environment variable is set correctly
  • Verify that the API endpoint is accessible from the server

Getting Help

If you encounter issues not covered here, please open an issue against this GitHub repository.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选