Medusa.js Documentation MCP Server
Provides AI assistants with instant access to comprehensive Medusa.js v2 documentation, enabling smart search, precise section retrieval, and complete browsing through 2,105+ documentation sections.
README
š Medusa.js Documentation MCP Server
A powerful Model Context Protocol (MCP) server that gives your AI assistants instant access to comprehensive Medusa.js v2 documentation with smart search capabilities and real-time assistance for enhanced development workflow.
š Latest Documentation: September 2025 | š Coverage: 2,105+ sections | š¦ Size: 4.7MB
⨠Key Features
| šÆ Feature | š Description | š Benefits |
|---|---|---|
| š Smart Search | Fuzzy search through 2,105+ documentation sections | Find answers even with partial or inexact queries |
| š Precise Retrieval | Get exact sections by title or path | Access specific documentation instantly |
| š Complete Browsing | List all available sections with filtering | Discover new features and capabilities |
| ā” Lightning Fast | TypeScript-powered with optimized performance | Instant responses, no delays |
| š¦ Zero Setup | Documentation included, no external dependencies | Works out-of-the-box |
| š Real-time | Always up-to-date Medusa v2 documentation | Latest features and best practices |
š Prerequisites
- Node.js 18+
- npm or yarn
- AI Assistant with MCP support:
- Claude Code (CLI) ā Tested & Working
- Kilo Code ā Tested & Working
- Cursor
- Windsurf
- Or any MCP-compatible client
š Installation
1. Clone and Setup
# Clone the repository
git clone https://github.com/Alexcs24/Medusa.js-Documentation-MCP-Server
cd Medusa.js-Documentation-MCP-Server
# Install dependencies
npm install
# Build the TypeScript code
npm run build
2. Documentation Ready!
ā
No additional setup needed! The repository includes comprehensive Medusa.js v2 documentation (4.7MB, September 2025) located at ./docs/medusa-docs.txt.
Optional: Use your own documentation file:
# Replace with your own documentation if needed
export MEDUSA_DOCS_PATH="/absolute/path/to/your/custom-docs.txt"
3. Configure Your AI Assistant
š¢ Claude Code CLI ā Tested & Working
Global Configuration (recommended):
# Create or edit global config
nano ~/.claude/claude_code_config.json
Add this configuration:
{
"mcpServers": {
"medusa-docs": {
"command": "node",
"args": ["/absolute/path/to/Medusa.js-Documentation-MCP-Server/dist/index.js"],
"env": {
"MEDUSA_DOCS_PATH": "/absolute/path/to/Medusa.js-Documentation-MCP-Server/docs/medusa-docs.txt"
}
}
}
}
Project-specific Configuration:
# In your Medusa project root
mkdir -p .claude
cp claude_code_config.json .claude/mcp.json
# Edit paths to be relative to your project
Cursor IDE
Add to your Cursor settings (settings.json):
{
"mcp": {
"mcpServers": {
"medusa-docs": {
"command": "node",
"args": ["/absolute/path/to/Medusa.js-Documentation-MCP-Server/dist/index.js"],
"env": {
"MEDUSA_DOCS_PATH": "/absolute/path/to/docs/medusa-docs.txt"
}
}
}
}
}
Windsurf
Create or edit windsurf-mcp-config.json:
{
"mcpServers": {
"medusa-docs": {
"command": "node",
"args": ["/absolute/path/to/Medusa.js-Documentation-MCP-Server/dist/index.js"],
"env": {
"MEDUSA_DOCS_PATH": "/absolute/path/to/docs/medusa-docs.txt"
}
}
}
}
šÆ Usage & Natural Language Examples
After configuration, restart your AI assistant and interact using natural language:
š Smart Search Examples
š¬ "Search Medusa docs for payment providers"
š¬ "Find information about workflows in Medusa"
š¬ "Look up cart module documentation"
š¬ "How do I implement custom shipping methods?"
š¬ "Show me authentication examples"
š Specific Section Retrieval
š¬ "Get the section about API routes"
š¬ "Show me the modules documentation"
š¬ "Retrieve workflow examples"
š¬ "I need the admin customization guide"
š¬ "Display the product catalog setup"
š Browse Available Content
š¬ "List all available documentation sections"
š¬ "Show me categories in the docs"
š¬ "What documentation sections are available?"
š¬ "Browse workflow-related documentation"
š¬ "What payment integrations are documented?"
š Advanced Usage Patterns
š¬ "Compare different payment providers in Medusa"
š¬ "Walk me through setting up a complete e-commerce store"
š¬ "What's the difference between modules and plugins?"
š¬ "Show me step-by-step workflow implementation"
š§ Available MCP Tools
The MCP server provides 3 powerful tools to access Medusa.js documentation:
š 1. search_docs - Smart Documentation Search
What it does: Intelligently searches through 2,105+ documentation sections using fuzzy matching Perfect for: Finding relevant information when you don't know the exact section name
Parameters:
query(string, required): Your search querylimit(number, optional): Maximum results to return (default: 5)
⨠Example Usage:
{
"name": "search_docs",
"arguments": {
"query": "workflow payment providers",
"limit": 3
}
}
Returns: Workflow Engine Module, timeout configurations, and In-Memory workflow setup
š 2. get_section - Precise Section Retrieval
What it does: Fetches exact documentation sections by title or path Perfect for: Getting detailed information about a specific topic you know exists
Parameters:
identifier(string, required): Exact section title or path
⨠Example Usage:
{
"name": "get_section",
"arguments": {
"identifier": "Debug Workflows"
}
}
Returns: Complete section content with debugging approaches and techniques
š 3. list_sections - Browse All Available Content
What it does: Lists all 2,105+ available documentation sections Perfect for: Discovering what documentation is available or browsing by category
Parameters:
category(string, optional): Filter sections by specific category
⨠Example Usage:
{
"name": "list_sections",
"arguments": {
"category": "workflows"
}
}
Returns: Complete list of workflow-related documentation sections
š Real-World Usage Examples
Scenario 1: "How do I set up payments in Medusa?"
- Use
search_docswith query"payment setup" - Get relevant sections about payment modules and providers
- Use
get_sectionto dive deep into specific payment provider setup
Scenario 2: "What workflow features are available?"
- Use
list_sectionswith category"workflows" - Browse available workflow documentation
- Use
get_sectionto read specific workflow implementation guides
Scenario 3: "I need help with cart functionality"
- Use
search_docswith query"cart module" - Find cart-related sections and APIs
- Access detailed cart implementation examples
š§ Development
Scripts
# Development server with hot reload
npm run dev
# Watch mode (auto-restart on changes)
npm run watch
# Build TypeScript
npm run build
# Start production server
npm run start
Testing
Test the MCP server manually:
# Start the server
node dist/index.js
# In another terminal, send MCP requests
echo '{"jsonrpc":"2.0","method":"tools/list","id":1}' | node dist/index.js
Debug Mode
# Enable debug logging
DEBUG=1 node dist/index.js
# Or with environment variables
MEDUSA_DOCS_PATH="/path/to/docs.txt" DEBUG=1 node dist/index.js
š Project Structure
Medusa.js-Documentation-MCP-Server/
āāā src/
ā āāā index.ts # Main MCP server implementation
āāā dist/ # Compiled JavaScript (auto-generated)
āāā docs/
ā āāā medusa-docs.txt # Complete Medusa v2 docs (4.7MB, Sep 2025)
āāā config.json # Server configuration settings
āāā example-docs.txt # Example documentation format
āāā claude_code_config.json # Example Claude Code config
āāā package.json # Node.js dependencies
āāā tsconfig.json # TypeScript configuration
āāā .gitignore # Git ignore rules
āāā LICENSE # MIT License
āāā README.md # This file
āļø Configuration
All server settings can be customized in config.json:
{
"searchDefaults": {
"maxResults": 5, // Default number of search results
"threshold": 0.4, // Search sensitivity (0-1, lower = more strict)
"minMatchCharLength": 3 // Minimum characters for search matching
},
"listDefaults": {
"maxSections": 50 // Maximum sections shown in list_sections
},
"server": {
"name": "medusa-docs-mcp",
"version": "1.0.0"
},
"documentation": {
"previewLength": 500, // Length of content preview in search results
"fallbackPaths": [ // Paths to search for documentation file
"docs/medusa-docs.txt",
"llms-full.txt",
"../llms-full.txt",
"../../llms-full.txt",
"/home/claude/llms-full.txt"
]
}
}
š§ Customize Your Settings
- More search results: Increase
searchDefaults.maxResults - Stricter search: Lower
searchDefaults.threshold(0.2 = very strict, 0.8 = very loose) - Longer previews: Increase
documentation.previewLength - More list items: Increase
listDefaults.maxSections
š Environment Variables
MEDUSA_DOCS_PATH: Absolute path to your documentation fileDEBUG: Enable debug logging (set to1ortrue)
š Troubleshooting
Server not found
- Restart your AI assistant after configuration changes
- Check that file paths are absolute, not relative
- Verify the
dist/index.jsfile exists (runnpm run build)
Documentation not loading
- Verify
MEDUSA_DOCS_PATHpoints to the correct file - Check file permissions (should be readable)
- Ensure the file exists and is not empty
Permission errors
# Fix file permissions
chmod 644 /path/to/docs/medusa-docs.txt
chmod +x /path/to/Medusa.js-Documentation-MCP-Server/dist/index.js
Debug connection issues
# Test MCP server manually
echo '{"jsonrpc":"2.0","method":"tools/list","id":1}' | MEDUSA_DOCS_PATH="/path/to/docs.txt" node dist/index.js
Check your AI assistant's MCP logs:
- Claude Code CLI: View ā Output ā MCP logs
- Cursor IDE: Developer Tools ā Console
- Windsurf: Check extension logs in developer tools
š¤ Contributing
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature) - Make your changes
- Update configuration in
config.jsonif needed - Build and test (
npm run build) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
š License
This project is licensed under the MIT License - see the LICENSE file for details.
š Acknowledgments
- Model Context Protocol by Anthropic
- Medusa.js commerce platform
- Fuse.js for fuzzy search functionality
š Support
- š Issues: GitHub Issues
- š¬ Discussions: GitHub Discussions
- š§ Email: Contact through GitHub
ā Star this repo if it helps your Medusa development workflow!
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.