DealX
About
DealX is a Model Context Protocol (MCP) server for the DealX platform that allows LLMs to search for ads. It implements the MCP specification to provide a standardized interface for LLMs to interact with the DealX platform.
Details
- Author
- dealexpress
- GitHub stars
- 2
- Downloads
- 188
- Categories
- Developer Tools, Other
- Tags
- #ecommerce, #marketplace, #business-operations
Jump to
- Provides a search_ads tool for querying ads.
- Supports pagination with offset and limit parameters.
- Allows sorting results (e.g., newest first).
- Designed to be easily extended with additional tools.
- Hosted deployment available on Fronteir AI.
- Works with any MCP-compatible LLM client.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
DealXCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install via npm (npm install -g @dealx/mcp-server) or run with npx (npx -y @dealx/mcp-server). Configure the server in your LLM’s MCP settings (e.g., Claude Desktop or Cline) by adding a dealx entry under mcpServers with the command npx, args ["-y", "@dealx/mcp-server"], and environment variable DEALX_API_URL set to https://dealx.com.ua. Then use natural language prompts like “Search for ads on DealX with the query 'laptop'”.
search_ads
Search for ads on the DealX platform
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"dealx": {
"dealx": {
"command": "npx",
"args": [
"-y",
"@dealx/mcp-server"
],
"env": {
"DEALX_API_URL": "https://dealx.com.ua"
},
"disabled": false,
"autoApprove": []
}
}
}
}McpServers
{
"dealx": {
"command": "npx",
"args": [
"-y",
"@dealx/mcp-server"
],
"env": {
"DEALX_API_URL": "https://dealx.com.ua"
},
"disabled": false,
"autoApprove": []
}
}This is a Model Context Protocol (MCP) server for theDealX platform. It allows LLMs to interact with the DealX platform, specifically to search for ads.
- Overview
- Installation
- Usage
- Available Tools
- Extending the Server
- Development
- Troubleshooting
A hosted deployment is available onFronteir AI.
The DealX MCP Server implements theModel Context Protocolto provide a standardized way for LLMs to interact with theDealX platform. Currently, it supports searching for ads, with plans to add more functionality in the future.
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.
- Node.js (v20 or later)
- npm (v11 or later)
To use this server with an LLM like Claude, you need to add it to your LLM's MCP configuration:
-
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
- ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
Add the DealX MCP server to themcpServerssection:
{ "mcpServers": { "dealx": { "command": "npx", "args": ["-y", "@dealx/mcp-server"], "env": { "DEALX_API_URL": "https://dealx.com.ua" }, "disabled": false, "autoApprove": [] } } }
The easiest way to install the DealX MCP Server is via npm:
If you want to modify the server or contribute to its development:
git clone <repository-url> cd dealx/mcp
Create a.envfile based on the.env.examplefile:
Edit the.envfile 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
node node_modules/@dealx/mcp-server/build/index.js
DEALX_API_URL=https://dealx.com.ua npx -y @dealx/mcp-server
Once configured in your LLM's MCP settings, you can use natural language to interact with the DealX platform.
- "Search for ads on DealX with the query 'laptop'"
- "Find the newest 5 ads for 'iPhone' on DealX"
- "Search DealX for apartments in Kyiv"
- 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)
{ "query": "laptop", "sort": "-created", "offset": 1, "limit": 10 }
The server is designed to be easily extended with additional tools. Here's how to add a new tool:
-
Define the tool in theTOOLSobject insrc/index.ts:
const TOOLS = { SEARCH_ADS: "search_ads", NEW_TOOL: "new_tool", // Add your new tool here };
Create a new file in thesrc/toolsdirectory 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 theListToolsRequestSchemahandler insrc/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 theCallToolRequestSchemahandler insrc/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 { newTool } from "./tools/new-tool.js";
The following tools are planned for future implementation:
- create_ad: Create a new ad on theDealX 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
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 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
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.envfile exists and has the correct values
- Check the console output for error messages
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
If the server can't connect to the DealX API:
- Make sure the DealX API is running
- Check that theDEALX_API_URLenvironment variable is set correctly
- Verify that the API endpoint is accessible from the server
If you encounter issues not covered here, please open an issue against this GitHub repository.
Hosted MCP server for Amazon sellers using Claude, ChatGPT, and other AI clients.
D2C eCommerce fulfillment platform: manage orders, inventory, shipments, campaigns, and billing via AI agents
MCP server for Billy — Danish online accounting. Invoices, contacts, daybook transactions, accounts, and products.
Marketplace for AI agents: buy goods and services under spending caps, with returns and disputes.
Real-time product search across Southeast Asia with 3.8M+ items — the first SEA e-commerce MCP server
Real-time pricing, ratings, and feature comparisons for 508+ SaaS, AI, and security products across 45 categories. Zero dependencies, no auth required.
Living economy for AI agents - Conway physics, energy currency, marketplace, reputation.
Agent-first industrial marketplace: search and broker industrial assets (ASIC repair, mining, energy, equipment) and livestock medianería partnerships — anonymous read tier, every write needs human approval.
Agent-first marketplace for real-world assets — agro and energy first; humans approve every write.
A TypeScript-based MCP server for interacting with the Etsy API, featuring a simple notes system.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
