Arham Jewellers MCP Server
Enables searching products, browsing categories, checking gold rates, tracking orders, placing orders, and getting store info for Arham Jewellers through natural language.
README
Arham Jewellers MCP Server
MCP (Model Context Protocol) server for the Arham Jewellers customer AI assistant. Exposes tools for searching products, browsing categories, checking gold rates, tracking orders, placing orders, and getting store info.
Prerequisites
- Node.js 18+ (uses built-in
fetch) - A running Arham Jewellers backend API
Setup
# Install dependencies
npm install
# Configure environment
cp .env.example .env
# Edit .env with your API_BASE_URL
# Build
npm run build
Configuration
Create a .env file — only the API base URL is needed (token is passed per request):
API_BASE_URL=https://arham-jewellers-backend.onrender.com
Running
npm start
Get a Token
# Admin login (phone must include +91 prefix)
LOGIN_PHONE=+919879879870 LOGIN_PASSWORD=Admin@1234 npm run get-token
# User login
LOGIN_PHONE=+919879879870 LOGIN_PASSWORD=yourpass npm run get-token
Available Tools (11)
All tools require a token parameter (JWT) passed by the MCP client with each request.
| Tool | Description |
|---|---|
search_products |
Search products by name, karat, or category |
get_product_details |
Get full details of a specific product |
get_product_by_barcode |
Find a product by barcode number |
get_categories |
Get the hierarchical category tree (Level 1=Karat, 2=Collection, 3=Style) |
get_category_products |
List products in a Level 3 category |
get_current_gold_rate |
Get today's gold rate per gram |
get_gold_rate_history |
Get historical gold rates |
get_user_orders |
Get order history |
get_order_details |
Get details of a specific order |
place_order |
Place an order (requires user confirmation) |
get_store_info |
Get store info (About, Contact, Terms, etc.) |
Important Notes
- Category levels: Only Level 3 (Style) category IDs return products. Use
get_categories(level=3)to find valid IDs. - Order placement:
place_orderuses a two-step confirm flow — the AI must ask the user before settingconfirm=true. - Gold rate: The
/api/v1/gold-rate/currentendpoint may not be available on all backend versions.
Connect to MCP Clients
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"arham-jewellers": {
"command": "node",
"args": [
"--env-file=/absolute/path/to/arham-mcp-server/.env",
"/absolute/path/to/arham-mcp-server/build/index.js"
]
}
}
}
Cursor
Add to .cursor/mcp.json:
{
"mcpServers": {
"arham-jewellers": {
"command": "node",
"args": [
"--env-file=/absolute/path/to/arham-mcp-server/.env",
"/absolute/path/to/arham-mcp-server/build/index.js"
]
}
}
}
Project Structure
src/
├── index.ts # Entry point (MCP server + STDIO transport)
├── config.ts # Environment variable loader
├── api-client.ts # HTTP client for backend API (token passed per call)
├── types.ts # TypeScript interfaces
└── tools/
├── index.ts # Tool registry
├── products.ts # search_products, get_product_details, get_product_by_barcode
├── categories.ts # get_categories, get_category_products
├── gold-rate.ts # get_current_gold_rate, get_gold_rate_history
├── orders.ts # get_user_orders, get_order_details, place_order
└── store.ts # get_store_info
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.