MCP 服务器

Fake Store API MCP Server

Provides seamless access to the Fake Store API for AI assistants with 18 CRUD tools for managing e-commerce data including products, carts, and users. Perfect for e-commerce demos, testing, and learning MCP development with zero configuration required.

README

Fake Store API MCP Server

A Model Context Protocol (MCP) server that provides seamless access to the Fake Store API for AI assistants. Perfect for e-commerce demos, testing, and learning MCP development.

Features

🛍️ Complete E-commerce Data Access: Products, carts, and users
🔧 18 MCP Tools: Full CRUD operations for all resources
📦 Easy Integration: Works with Claude Desktop, Plugged.in, and other MCP clients
🚀 Zero Configuration: Works out of the box with Fake Store API
📝 TypeScript: Fully typed for better development experience
✅ Input Validation: Comprehensive parameter validation

Installation

NPX (Recommended)

npx -y mcp-server-fakestore

From Source

git clone https://github.com/yourusername/mcp-server-fakestore.git
cd mcp-server-fakestore
npm install
npm run build

Configuration

Claude Desktop

Add this to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "fakestore": {
      "command": "npx",
      "args": ["-y", "mcp-server-fakestore"]
    }
  }
}

Plugged.in

Add this server configuration in Plugged.in MCP settings:

{
  "name": "fakestore",
  "command": "npx",
  "args": ["-y", "mcp-server-fakestore"]
}

Available Tools

Products (7 tools)

fakestore_get_products - Get all products with optional limit and sorting
fakestore_get_product - Get a single product by ID
fakestore_get_categories - Get all product categories
fakestore_get_products_by_category - Get products in a specific category
fakestore_add_product - Add a new product (simulation)
fakestore_update_product - Update an existing product (simulation)
fakestore_delete_product - Delete a product (simulation)

Carts (6 tools)

fakestore_get_carts - Get all carts with optional limit and sorting
fakestore_get_cart - Get a single cart by ID
fakestore_get_user_carts - Get all carts for a specific user
fakestore_add_cart - Add a new cart (simulation)
fakestore_update_cart - Update an existing cart (simulation)
fakestore_delete_cart - Delete a cart (simulation)

Users (5 tools)

fakestore_get_users - Get all users with optional limit and sorting
fakestore_get_user - Get a single user by ID
fakestore_add_user - Add a new user (simulation)
fakestore_update_user - Update an existing user (simulation)
fakestore_delete_user - Delete a user (simulation)

Usage Examples

With Claude Desktop

Get all products:

Show me all products from the fake store

Search by category:

Show me electronics from the fake store

Get user's cart:

What's in user ID 1's shopping cart?

Product analysis:

Find the 5 most expensive products in the store

Programmatic Usage

import { Server } from '@modelcontextprotocol/sdk/server/index.js';

// The server runs on stdio transport
// Connect your MCP client to interact with the tools

Data Structure

Product

{
  id: number;
  title: string;
  price: number;
  description: string;
  category: string;
  image: string;
  rating: {
    rate: number;
    count: number;
  };
}

Cart

{
  id: number;
  userId: number;
  date: string;
  products: Array<{
    productId: number;
    quantity: number;
  }>;
}

User

{
  id: number;
  email: string;
  username: string;
  password: string;
  name: {
    firstname: string;
    lastname: string;
  };
  address: {
    city: string;
    street: string;
    number: number;
    zipcode: string;
    geolocation: {
      lat: string;
      long: string;
    };
  };
  phone: string;
}

Development

# Install dependencies
npm install

# Build the project
npm run build

# Watch mode for development
npm run watch

# Run tests
npm test

Important Notes

Simulation: The Fake Store API is read-only. POST, PUT, and DELETE operations return simulated responses but don't persist data.
Rate Limits: The public API has no strict rate limits, but please be respectful.
Data: All data is fake and for testing purposes only.