広告掲載
MCP.so
ログイン

Swell MCP Server

@devkindhq

リポジトリ

基本情報

カテゴリ

その他

トランスポート

stdio

作者

devkindhq

投稿者

Ali Kazim

Swell MCP Server について

概要はまだありません

#ecommerce#swell#mcp#orders#products#customers

Swell MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "swell-mcp": {
      "command": "npx",
      "args": [
        "swell-mcp"
      ],
      "env": {
        "SWELL_STORE_ID": "",
        "SWELL_SECRET_KEY": ""
      }
    }
  }
}

Swell MCP Server のツール

14

List products with filtering and pagination

Get detailed product information

Search products with text queries and optional filters

Check current stock levels and stock status for a product

Update product metadata and attributes (name, description, SEO, tags, categories, attributes, active, sku, etc.)

Adjust stock levels or update stock tracking settings

Update product pricing (regular price, sale price, currency)

List orders with filtering options

Get detailed order information

Update the status of an order (with optional notes)

List customers with search and filtering options

Get detailed customer information (profile + optional order history)

Search customers using text queries (name, email, phone)

Update customer records (name, email, phone, tags, groups, marketing opt-ins, notes)

概要

What is Swell MCP?

Swell MCP is a Model Context Protocol server that integrates AI assistants with Swell's e-commerce platform. It provides comprehensive access to Swell stores for product management, order processing, and customer management through both CLI and MCP tool interfaces. It is built by Devkind, official Swell Partners.

How to use Swell MCP?

Install the server by running npx swell-mcp in any MCP client (Claude Desktop, Cursor, VS Code, Windsurf, Goose, LM Studio, Warp). Configure the environment variables SWELL_STORE_ID and SWELL_SECRET_KEY with your Swell credentials. Once installed, you can use the provided MCP tools (e.g., swell_list_products, swell_get_order) directly through your AI assistant.

Key features of Swell MCP

  • Complete Swell API access for products, orders, and customers
  • Dual transport support: STDIO and Streamable HTTP with SSE
  • Full TypeScript implementation with Zod schema validation
  • Structured error handling with Swell-specific error contexts
  • Debug mode for raw JSON responses
  • Production-ready tooling: ESLint, Prettier, semantic-release, MCP Inspector

Use cases of Swell MCP

  • List and search products with filtering and pagination
  • Check inventory levels for specific products
  • Process orders and update their status via natural language
  • Search customer profiles and retrieve order history
  • Integrate Swell store management into custom MCP clients

よくある質問

1

What is Swell MCP and what does it do?

Swell MCP is a Model Context Protocol server that connects AI assistants to Swell's e-commerce platform. It provides tools to manage products, orders, and customers through natural language commands.

2

What are the runtime requirements?

Node.js 18 or newer, a compatible MCP client (e.g., VS Code, Claude Desktop, Cursor), and Swell store credentials (Store ID and Secret Key).

3

How do I get Swell credentials for the server?

Log into your Swell dashboard at login.swell.store, go to Developer → API Keys, and copy your Store ID and Secret Key. Use the backend/admin key, not the public key.

4

What transport modes does Swell MCP support?

Swell MCP supports two transport modes: STDIO (JSON-RPC via stdin/stdout, used by local AI assistants) and Streamable HTTP (Server-Sent Events, configurable port, default 3000).

5

Where does my data live when using Swell MCP?

The server acts as a bridge between the AI assistant and your Swell store. It communicates directly with Swell's API; no data is stored by the server itself.

コメント

「その他」の他のコンテンツ

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Codelf

unbug

A search tool helps dev to solve the naming things problem.

14.2K

Hindsight

vectorize-io

Hindsight: Agent Memory That Learns

50.4K
N

Next Generation Movers: free moving quotes (remote MCP)

Next Generation Movers

Free moving quotes for AI agents from Next Generation Movers, a licensed interstate mover (USDOT 3764697). US long-distance nationwide and local DC/MD/VA. Indicative ballpark price and booking options; optional $0.01 x40

Glasswarp

Glasswarp

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

広告掲載