Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Bookstore MCP Server search for books by Brandon Sanderson"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Full-stack bookstore API with dual exposure: REST endpoints for web clients and MCP (Model Context Protocol) tools for LLM agents. One service layer powers both.
REST API for inventory, orders, and members
Six MCP tools (search_books, get_book, check_stock, etc.)
React admin UI with Tool Explorer to invoke MCP tools over HTTP
Shared service/repository layer — no duplicated business logic
Related MCP server: bookstore-mcp-server
Layer | Tech |
Backend | Node.js, Express, MCP SDK, Zod |
Frontend | React, TypeScript, Vite |
Data | Local JSON catalog |
npm run install:all
npm run dev:backend # http://localhost:8003
npm run dev:frontend # http://localhost:5176Docker
docker compose up --buildTool | Purpose |
| Search by title, author, genre |
| Book details by ID |
| Availability check |
| Order lookup |
| Member profile |
| Genre-based recommendations |
curl -X POST http://localhost:8003/api/v1/tools/call \
-H "Content-Type: application/json" \
-d '{"tool":"search_books","arguments":{"query":"design"}}'MIT
This server cannot be deployed
Hosted MCP for e-commerce: live product catalog, stock, and pricing for AI agents.
API-first CRM for LLMs - contacts, companies, deals and activities over a native MCP server.
LLM Orchestration Agent (Mcp)
Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.
