Server data from the Official MCP Registry
Model Context Protocol server for Swell e-commerce platform integration with AI assistants
Model Context Protocol server for Swell e-commerce platform integration with AI assistants
This is a well-architected MCP server for Swell e-commerce integration with strong code quality and proper security practices. The server correctly requires API credentials (store ID and secret key) via environment variables, implements comprehensive input validation using Zod, and follows a clean layered architecture. Permissions align well with the server's purpose (network access for Swell API, environment variable access for credentials). No critical vulnerabilities or malicious patterns were identified. Supply chain analysis found 4 known vulnerabilities in dependencies (0 critical, 3 high severity). Package verification found 1 issue.
4 files analyzed ยท 9 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Set these up before or after installing:
Environment variable: SWELL_STORE_ID
Environment variable: SWELL_SECRET_KEY
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-devkindhq-swell": {
"env": {
"SWELL_STORE_ID": "your-swell-store-id-here",
"SWELL_SECRET_KEY": "your-swell-secret-key-here"
},
"args": [
"-y",
"swell-mcp"
],
"command": "npx"
}
}
}From the project's GitHub README.
A Model Context Protocol server that integrates AI assistants with Swell's e-commerce platform. Built on a production-ready TypeScript foundation, it provides comprehensive access to Swell stores for product management, order processing, and customer management through both CLI and MCP tool interfaces.
Built by Devkind - Official Swell Partners serving businesses globally with cutting-edge e-commerce solutions.
This MCP server provides comprehensive integration with Swell's e-commerce platform:
MCP Tools:
swell_list_products - List products with filtering and paginationswell_get_product - Get detailed product informationswell_search_products - Search products with multiple criteriaswell_check_inventory - Check product inventory levelsswell_list_orders - List orders with filtering optionsswell_get_order - Get detailed order informationswell_update_order_status - Update order statusswell_list_customers - List customers with search capabilitiesswell_get_customer - Get detailed customer informationswell_search_customers - Search customers with multiple criteria# Required - Swell API credentials
SWELL_STORE_ID=your-store-id
SWELL_SECRET_KEY=your-secret-key
# Development
DEBUG=true # Enable detailed logging
TRANSPORT_MODE=http # Use HTTP transport
PORT=3001 # Custom port
This MCP server demonstrates the kind of sophisticated Swell integrations that power CheckoutJet - an enterprise-grade checkout solution for Swell stores built by Devkind.
CheckoutJet transforms your Swell checkout with:
Proven Results: Over โฌ500,000 processed for Swell merchants with 23% conversion rate improvements.
Ready to upgrade your Swell checkout? Book a 15-minute demo
Model Context Protocol (MCP) is an open standard for securely connecting AI systems to external tools and data sources. This server implements the MCP specification to provide AI assistants with comprehensive access to Swell's e-commerce platform, enabling intelligent store management and customer service automation.
First, install the Swell MCP server with your AI assistant or MCP client.
Standard config works in most MCP clients:
{
"mcpServers": {
"swell-mcp": {
"command": "npx",
"args": ["swell-mcp"],
"env": {
"DEBUG": "false",
"SWELL_STORE_ID": "your_store_id",
"SWELL_SECRET_KEY": "your_private_token"
},
"disabled": false
}
}
}
Follow the MCP install guide, use the standard config above.
Add to your claude_desktop_config.json:
{
"mcpServers": {
"swell-mcp": {
"command": "npx",
"args": ["swell-mcp"],
"env": {
"SWELL_STORE_ID": "your_store_id",
"SWELL_SECRET_KEY": "your_private_token"
}
}
}
}
Go to Cursor Settings -> MCP -> Add new MCP Server. Name it "Swell MCP", use command type with the command npx swell-mcp. Add your Swell credentials in the environment variables section.
Follow the MCP install guide, use the standard config above. You can also install the Swell MCP server using the VS Code CLI:
# For VS Code
code --add-mcp '{"name":"swell-mcp","command":"npx","args":["swell-mcp"],"env":{"SWELL_STORE_ID":"your_store_id","SWELL_SECRET_KEY":"your_private_token"}}'
After installation, the Swell MCP server will be available for use with your GitHub Copilot agent in VS Code.
Follow Windsurf MCP documentation. Use the standard config above.
Add to your MCP configuration:
{
"mcpServers": {
"swell-mcp": {
"command": "npx",
"args": ["swell-mcp"],
"env": {
"SWELL_STORE_ID": "your_store_id",
"SWELL_SECRET_KEY": "your_private_token"
}
}
}
}
Go to Advanced settings -> Extensions -> Add custom extension. Name it "Swell MCP", use type STDIO, and set the command to npx swell-mcp. Add your Swell credentials as environment variables. Click "Add Extension".
Go to Program in the right sidebar -> Install -> Edit mcp.json. Use the standard config above with your Swell credentials.
Go to Settings -> AI -> Manage MCP Servers -> + Add to add an MCP Server. Use the standard config above.
Alternatively, use the slash command /add-mcp in the Warp prompt and paste the standard config from above.
SWELL_STORE_ID)SWELL_SECRET_KEY - use the backend/admin key, not the public key)SWELL_STORE_ID: Your Swell store identifier (required)SWELL_SECRET_KEY: Your Swell secret/private key (required)DEBUG: Set to "true" to enable debug mode with raw JSON responses (optional){
"mcpServers": {
"swell-mcp": {
"command": "npx",
"args": ["swell-mcp"],
"env": {
"DEBUG": "false",
"SWELL_STORE_ID": "my-awesome-store",
"SWELL_SECRET_KEY": "sk_live_abc123def456..."
},
"disabled": false
}
}
}
Once installed in your MCP client (see Getting Started above), you can use the Swell MCP tools directly through your AI assistant:
"List my active products"
โ Uses swell_list_products with active=true
"Show me pending orders from this week"
โ Uses swell_list_orders with status=pending and date filtering
"Update customer John Doe's email to john@example.com"
โ Uses swell_update_customer to modify customer information
"Check inventory for product ID abc123"
โ Uses swell_check_inventory for stock levels
Enable debug mode to see raw JSON responses instead of formatted output:
{
"env": {
"DEBUG": "true",
"SWELL_STORE_ID": "your_store_id",
"SWELL_SECRET_KEY": "your_private_token"
}
}
TRANSPORT_MODE=stdio node dist/index.jsPORT env var)http://localhost:3000/mcphttp://localhost:3000/ โ Returns server versionTRANSPORT_MODE=http node dist/index.jssrc/
โโโ cli/ # Command-line interfaces
โ โโโ index.ts # CLI entry point with Commander setup
โโโ controllers/ # Business logic orchestration
โ โโโ swell.products.controller.ts # Product management logic
โ โโโ swell.products.formatter.ts # Product response formatting
โ โโโ swell.orders.controller.ts # Order management logic
โ โโโ swell.orders.formatter.ts # Order response formatting
โ โโโ swell.customers.controller.ts # Customer management logic
โ โโโ swell.customers.formatter.ts # Customer response formatting
โโโ services/ # External API interactions
โ โโโ swell.products.service.ts # Swell products API service
โ โโโ swell.products.types.ts # Product type definitions
โ โโโ swell.orders.service.ts # Swell orders API service
โ โโโ swell.orders.types.ts # Order type definitions
โ โโโ swell.customers.service.ts # Swell customers API service
โ โโโ swell.customers.types.ts # Customer type definitions
โโโ tools/ # MCP tool definitions (AI interface)
โ โโโ swell.products.tool.ts # Product management tools
โ โโโ swell.orders.tool.ts # Order management tools
โ โโโ swell.customers.tool.ts # Customer management tools
โโโ types/ # Global type definitions
โ โโโ common.types.ts # Shared interfaces (ControllerResponse, etc.)
โโโ utils/ # Shared utilities
โ โโโ logger.util.ts # Contextual logging system
โ โโโ error.util.ts # MCP-specific error formatting
โ โโโ error-handler.util.ts # Error handling utilities
โ โโโ config.util.ts # Environment configuration
โ โโโ constants.util.ts # Version and package constants
โ โโโ formatter.util.ts # Markdown formatting
โ โโโ swell-client.util.ts # Swell SDK client wrapper
โ โโโ transport.util.ts # HTTP transport utilities
โโโ index.ts # Server entry point (dual transport)
The server follows a clean, layered architecture that promotes maintainability and clear separation of concerns:
src/cli/)list-products --active --category electronicssrc/tools/)swell_list_products tool with filtering and pagination optionssrc/resources/)swell://products/123 resource providing product detailssrc/controllers/)src/services/)src/utils/)logger.util.ts: Contextual logging (file:method context)error.util.ts: MCP-specific error formattingtransport.util.ts: HTTP/API utilities with retry logicconfig.util.ts: Environment configuration managementFor developers who want to contribute or modify the server:
# Clone the repository
git clone https://github.com/devkindhq/swell-mcp.git
cd swell-mcp
# Install dependencies
npm install
# Configure your Swell credentials
cp .env.example .env
# Edit .env and add your SWELL_STORE_ID and SWELL_SECRET_KEY
# Build the project
npm run build
# Run in different modes:
# 1. STDIO Transport - For AI assistant integration (Claude Desktop, Cursor)
npm run mcp:stdio
# 2. HTTP Transport - For web-based integrations
npm run mcp:http
# 3. Development with MCP Inspector
npm run mcp:inspect # Auto-opens browser with debugging UI
# Build and Clean
npm run build # Build TypeScript to dist/
npm run clean # Remove dist/ and coverage/
npm run prepare # Build + ensure executable permissions (for npm publish)
# CLI Testing (coming soon)
# npm run cli -- list-products --active # List active products
# npm run cli -- get-product <product-id> # Get product details
# npm run cli -- list-orders --status pending # List pending orders
# MCP Server Modes
npm run mcp:stdio # STDIO transport for AI assistants
npm run mcp:http # HTTP transport on port 3000
npm run mcp:inspect # HTTP + auto-open MCP Inspector
# Development with Debugging
npm run dev:stdio # STDIO with MCP Inspector integration
npm run dev:http # HTTP with debug logging enabled
# Testing
npm test # Run all tests (Jest)
npm run test:coverage # Generate coverage report
npm run test:cli # Run CLI-specific tests
# Code Quality
npm run lint # ESLint with TypeScript rules
npm run format # Prettier formatting
npm run update:deps # Update dependencies
TRANSPORT_MODE: Transport mode (stdio | http, default: stdio)PORT: HTTP server port (default: 3000)DEBUG: Enable debug logging (true | false, default: false)SWELL_STORE_ID: Your Swell store ID (required)SWELL_SECRET_KEY: Your Swell secret key (required).env File# Basic configuration
TRANSPORT_MODE=http
PORT=3001
DEBUG=true
# Swell API credentials (required)
SWELL_STORE_ID=your-store-id
SWELL_SECRET_KEY=your-secret-key
MCP Inspector: Visual tool for testing your MCP tools
npm run mcp:inspectDebug Logging: Enable with DEBUG=true environment variable
Create ~/.mcp/configs.json:
{
"swell-mcp": {
"environments": {
"DEBUG": "true",
"TRANSPORT_MODE": "http",
"PORT": "3000",
"SWELL_STORE_ID": "your-store-id",
"SWELL_SECRET_KEY": "your-secret-key"
}
}
}
The Swell MCP server provides comprehensive e-commerce management tools for AI assistants. The list below matches the tool names and parameter schemas implemented under src/tools/.
swell_list_products
page, limit, active, category, tags, sort, expandswell_get_product
productId, expandswell_search_products
query, page, limit, active, category, tags, sort, expandswell_check_stock
productId, includeVariants (default: true)swell_update_product
productId plus any editable product fieldsswell_update_product_stock
productId, quantity, reason, reasonMessage, variantId, orderIdswell_update_product_pricing
productId, price, salePrice, currencyswell_list_orders
page, limit, status, customerId, dateFrom, dateTo, sort, expandswell_get_order
orderId, expandswell_update_order_status
orderId, status, notesswell_list_customers
page, limit, search, email, dateFrom, dateTo, sort, expandswell_get_customer
customerId, expand, includeOrderHistoryswell_search_customers
query, page, limit, dateFrom, dateTo, sort, expandswell_update_customer
customerId plus editable customer fieldsThis server is built with a modular architecture that makes it easy to add new Swell API integrations or custom business logic. The existing Swell tools (products, orders, customers) serve as examples for implementing additional functionality.
For detailed implementation patterns, see the existing controllers, services, and tools in the codebase.
If you want to run the server independently (not through an MCP client):
npm install -g swell-mcp
# Set your credentials
export SWELL_STORE_ID=your-store-id
export SWELL_SECRET_KEY=your-secret-key
# Run the server
swell-mcp
# Run with HTTP transport on port 3000
TRANSPORT_MODE=http swell-mcp
# Custom port
PORT=8080 TRANSPORT_MODE=http swell-mcp
Impressed by this MCP server's capabilities? This is just a glimpse of what's possible with expert Swell development.
Transform your Swell store with our battle-tested checkout solution:
Ready to transform your e-commerce business?
The server includes comprehensive testing infrastructure:
tests/ # Not present - tests are in src/
src/
โโโ **/*.test.ts # Co-located with source files
โโโ utils/ # Utility function tests
โโโ controllers/ # Business logic tests
โโโ services/ # API integration tests
โโโ cli/ # CLI command tests
*.util.test.ts)npm test # Run all tests
npm run test:coverage # Generate coverage report
npm run test:cli # CLI-specific tests only
Looking for expert Swell development? Devkind is an official Swell partner serving businesses globally with our remote team, specializing in:
Get Started: See CheckoutJet Demo | Book FREE consultation | Email: hello@devkind.com.au | Global Remote Team
Be the first to review this server!
by Modelcontextprotocol ยท Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno ยท Developer Tools
Toleno Network MCP Server โ Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace ยท Developer Tools
Create, build, and publish Python MCP servers to PyPI โ conversationally.