Medusa MCP

v1.0.0Business Applicationsstable

A Model Context Protocol server that provides a scalable backend solution for efficient interaction with Medusa's data models through the JavaScript SDK.

medusa-mcp-servermcpai-integration
Share:
60
Stars
0
Downloads
0
Weekly
0/5

What is Medusa MCP?

Medusa MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol server that provides a scalable backend solution for efficient interaction with medusa's data models through the javascript sdk.

A Model Context Protocol server that provides a scalable backend solution for efficient interaction with Medusa's data models through the JavaScript SDK.

This server falls under the Business Applications category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A Model Context Protocol server that provides a scalable bac

Use Cases

Interact with Medusa ecommerce backend through AI.
Manage products and orders using JavaScript SDK.
Access Medusa data models programmatically.
SGFGOV

Maintainer

LicenseMIT License
Languagetypescript
Versionv1.0.0
UpdatedMay 19, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx medusa-mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Medusa MCP

Medusa MCP Server is a TypeScript-based Model Context Protocol server that integrates with the Medusa.js e-commerce platform via the official Medusa JavaScript SDK. It provides AI assistants with a programmatic interface to Medusa's data models, enabling automation of commerce workflows such as inventory management, order processing, and pricing updates. Teams building on Medusa can use this server to orchestrate backend operations through natural-language prompts without writing custom API integrations.

Prerequisites

  • Node.js 18.x or higher
  • A running Medusa backend instance (v2.x recommended)
  • Medusa publishable API key and, for admin operations, admin credentials
  • npm or yarn for dependency management
  • An MCP-compatible client such as Claude Desktop
1

Clone the repository

Clone the medusa-mcp repository to your local machine.

git clone https://github.com/SGFGOV/medusa-mcp.git
cd medusa-mcp
2

Install dependencies

Install the required Node.js packages.

npm install
3

Build the project

Compile the TypeScript source to JavaScript in the dist/ directory.

npm run build
4

Configure environment variables

Set the required environment variables pointing to your Medusa backend. Create a .env file or pass them through the MCP client config.

MEDUSA_BACKEND_URL=http://localhost:9000
PUBLISHABLE_KEY=your_medusa_publishable_key
[email protected]
MEDUSA_PASSWORD=your_admin_password
5

Add to your MCP client configuration

Reference the compiled entry point in your claude_desktop_config.json. All environment variables can be passed inline.

{
  "mcpServers": {
    "medusa-mcp": {
      "command": "node",
      "args": ["/absolute/path/to/medusa-mcp/dist/index.js"],
      "env": {
        "MEDUSA_BACKEND_URL": "http://localhost:9000",
        "PUBLISHABLE_KEY": "your_medusa_publishable_key",
        "MEDUSA_USERNAME": "[email protected]",
        "MEDUSA_PASSWORD": "your_admin_password"
      }
    }
  }
}
6

Test with MCP Inspector

Before connecting to Claude, verify the server works correctly using the MCP Inspector tool.

npx @modelcontextprotocol/inspector ./dist/index.js

Medusa MCP Examples

Client configuration

claude_desktop_config.json entry that runs the compiled Medusa MCP server, passing in the backend URL and credentials as environment variables.

{
  "mcpServers": {
    "medusa-mcp": {
      "command": "node",
      "args": ["/Users/yourname/medusa-mcp/dist/index.js"],
      "env": {
        "MEDUSA_BACKEND_URL": "http://localhost:9000",
        "PUBLISHABLE_KEY": "pk_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
        "MEDUSA_USERNAME": "[email protected]",
        "MEDUSA_PASSWORD": "your-admin-password"
      }
    }
  }
}

Prompts to try

Use these prompts once the server is connected to interact with your Medusa store through Claude.

- "List all products in the Medusa store and show their prices."
- "Show me all pending orders that need fulfillment."
- "Update the inventory for product variant var_01 to 50 units."
- "Create a new product category called 'Summer Collection'."
- "What are the current shipping options available in the store?"

Troubleshooting Medusa MCP

Connection refused when the server tries to reach the Medusa backend

Ensure your Medusa backend is running and that MEDUSA_BACKEND_URL is correct. By default Medusa runs on http://localhost:9000. Check with: curl http://localhost:9000/health

Authentication fails with 401 Unauthorized on admin operations

Verify that MEDUSA_USERNAME and MEDUSA_PASSWORD match a valid Medusa admin user. You can test credentials directly via the Medusa admin dashboard or REST API.

'Cannot find module dist/index.js' error when starting the server

The TypeScript source must be compiled before running. Execute 'npm run build' inside the medusa-mcp directory to generate the dist/ folder.

Frequently Asked Questions about Medusa MCP

What is Medusa MCP?

Medusa MCP is a Model Context Protocol (MCP) server that model context protocol server that provides a scalable backend solution for efficient interaction with medusa's data models through the javascript sdk. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Medusa MCP?

Follow the installation instructions on the Medusa MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Medusa MCP?

Medusa MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Medusa MCP free to use?

Yes, Medusa MCP is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Medusa MCP Alternatives — Similar Business Applications Servers

Looking for alternatives to Medusa MCP? Here are other popular business applications servers you can use with Claude, Cursor, and VS Code.

n8n

189.1k

A comprehensive MCP server that provides full control over n8n automation workflows through natural language. It offers 43 tools for managing workflows, executions, credentials, and data tables, with safety features like write-mode protection and dou

LobeHub

77.5k

🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

Jeecgboot

46.4k

AI 低代码平台,「低代码 + 零代码」双模式驱动:低代码一键生成前后端代码,零代码 5 分钟搭建系统,AI Skills 一句话画流程、设计表单、生成整套系统。内置 AI聊天、知识库、流程编排、MCP插件等,兼容主流大模型。引领「AI 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式,消除 Java 项目 80% 的重复工作,提效而不失灵活。

CowAgent

44.7k

CowAgent (chatgpt-on-wechat) 是基于大模型的超级AI助理,能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、通过长期记忆和知识库不断成长,比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入,可选择DeepSeek/OpenAI/Claude/Gemini/ MiniMax/Qwen/GLM/LinkAI,能处理文本、语音、图片和文件,可快速搭建个人AI助理和企业数字员工。

Minds Platform

39.2k

Platform dedicated to building an open foundation for applied Artificial Intelligence, designed for people seeking production-ready AI systems they can truly control, extend and deploy anywhere.

Astrbot

32.8k

AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨

Browse More Business Applications MCP Servers

Explore all business applications servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

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

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Medusa MCP?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides