M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
M

Medusa MCP Server

Community
MCP server for the Medusa JS SDK
How to install ↓ Compare GitHub source repository ↗
Category
Dev Tools #327 of 438
Stars
★ 71 Popular
Transport
stdio (local process)
Runtime
Node.js · Python
Credentials
Optional API key
License
MIT
Last commit
⚠
43FMRS · D

A community MCP server for the Medusa JS SDK focused on extensibility and AI automation, supporting OpenAPI-based customization and conversion into a Claude Skill. Best suited to developers with Medusa and Node.js experience, but it lacks official backing and detailed tool documentation, so security and functionality should be assessed before use.

Strongest · Setup experience 10/20 Weakest · Reliability 6/20

Reliability
6/20
Security and permissions
7/20
Maintenance
10/20
Documentation
10/20
Setup experience
10/20
Why each score
Reliability 6/20
The README only shows npm install / npm run build / npm start plus manual testing via the MCP Inspector; there is no evidence of automated tests, CI workflows, or documented error handling. Since the server manifest was not cached, the declared tool list cannot be verified against actual behavior. Per the static calibration rule, reliability is capped at 12 absent verifiable CI+test evidence, so a low-to-mid score is warranted.
Security and permissions 7/20
Credentials (MEDUSA_USERNAME/MEDUSA_PASSWORD, PUBLISHABLE_KEY) are passed via environment variables, a reasonable practice, and no hardcoded secrets or exfiltration behavior is evident. However, the README does not describe least-privilege scoping, does not mention confirmation gates for dangerous operations (orders, refunds, product deletion via Medusa admin endpoints), and discloses no data-flow or network boundaries. Risks are visible but mitigations are incomplete — not a red line, but not full marks either.
Maintenance 10/20
The project is MIT licensed, not archived, has 68 stars and only 1 open issue, and includes a CONTRIBUTING.md indicating some governance. However, the README provides no release history, versioning policy, security-response channel, or dependency-update process, making sustained maintenance activity unverifiable — a middling score.
Documentation 10/20
Documentation covers install, build, start, an environment-variable table, an architecture diagram, and customization via OAS files, showing some layering. It lacks specific tool/parameter documentation, usage limits, cost information, and troubleshooting beyond 'restart Inspector after rebuild', leaving hidden assumptions — a middling score.
Setup experience 10/20
Setup steps are simple (clone, npm install, npm run build, npm start) with an environment-variable table provided. However, no concrete client configuration example (e.g., for Claude Desktop or another mainstream MCP client) is given, and platform compatibility is not addressed, leaving the process manual and unverified. Per the static calibration rule, setup is capped at 15 absent verifiable execution evidence, so a middling score applies.

Static review · not runListed 2026-09-07

Read the FMRS scoring method →

Fit and risk

What it can accessUses the network

Best for

  • Developers building e-commerce on Medusa JS who want AI-agent automation
  • Teams integrating a Medusa backend with LLM toolchains
  • Engineers comfortable customizing OpenAPI definitions for fine-grained tool control

Not for

  • Projects not using Medusa
  • Users seeking official Medusa support or hosted solutions
  • Non-technical users unable to deploy a Node.js service and manage credential environment variables

Required permissions

  • Network access to a Medusa backend URL
  • A Medusa publishable API key (PUBLISHABLE_KEY)
  • Medusa admin username and password for admin operations

Risks and side effects

  • Admin credentials stored as environment variables carry leak risk
  • AI agents can trigger real commerce operations (order fulfillment, pricing updates); mistakes may affect production data
  • Server defaults to localhost:3000; exposing it to a network requires your own security measures
  • No tool list is documented, so actual capabilities must be verified by reviewing the source

Setup

Before you start

Runtime：Node.js · Python

MEDUSA_BACKEND_URL required URL of your Medusa backend, from your own Medusa deployment.
PUBLISHABLE_KEY optionalsecret Medusa publishable API key, generated in your Medusa admin dashboard.
MEDUSA_PASSWORD optionalsecret Medusa admin password, used for admin operations.
Other optional settings (1)
MEDUSA_USERNAME optional Medusa admin username, used for admin operations.
  1. Clone https://github.com/SGFGOV/medusa-mcp and run npm install
  2. Build with npm run build
  3. Configure environment variables: MEDUSA_BACKEND_URL (Medusa backend URL), PUBLISHABLE_KEY (publishable API key), MEDUSA_USERNAME and MEDUSA_PASSWORD (admin credentials)
  4. Start the server with npm start
  5. Optionally test with npx @modelcontextprotocol/inspector ./dist/index.js (restart the Inspector and browser after each rebuild).

Check that it works

Run npx @modelcontextprotocol/inspector ./dist/index.js and confirm the server starts and exposes Medusa-related tools; the server runs at http://localhost:3000.

Troubleshooting

  1. Restart the MCP Inspector and browser after every rebuild
  2. Verify MEDUSA_BACKEND_URL and PUBLISHABLE_KEY are set correctly
  3. If admin tools fail, confirm MEDUSA_USERNAME and MEDUSA_PASSWORD are provided
  4. On build errors, run npm install first to ensure dependencies are complete
  5. For customization, check that oas/admin. and oas/store. contain up-to-date OAS definitions

Things to try

Once connected, you can ask your AI assistant things like:

  • List the products in my Medusa store
  • Lower the price of a product by 10%
  • Show the status of my recent orders

Use cases

Automating commerce workflows such as inventory or pricing adjustments
Letting AI agents access product and order data from a Medusa backend
Customizing admin and store tools via OpenAPI definitions (oas/admin., oas/store.)
Converting the server into a Claude Skill using the included mcp-to-skill.py script

Overview

medusa-mcp is a Model Context Protocol (MCP) server designed for integration with the Medusa JavaScript SDK. It provides a scalable backend layer for managing and interacting with Medusa's data models, enabling automation, orchestration, and intelligent service extensions. It can automate workflows such as inventory or pricing adjustments, connect external tools like email and analytics, and let AI agents analyze trends and trigger actions. It is an MIT-licensed community project, not maintained by Medusa officially.

Similar servers

Context7 80 · B

Upstash's official server providing up-to-date third-party library docs for AI coding assistants

★ 63.3k · Tools 2 Compare with this →
Compare with other MCP servers

Source revision d1ce4896b456 Data synced 2026-10-19 Read the FMRS scoring method