bianca-sanchez-fattmerchant/Partner-MCP-Server
If you are the rightful owner of Partner-MCP-Server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.
Stax Partner MCP Server is a production-grade Model Context Protocol server designed to support Stax payment processing partners with efficient access to merchant data and transaction management.
Stax Partner MCP Server
A production-grade Model Context Protocol (MCP) server for Stax payment processing partner support. This server provides token-optimized, fast-response tools for common support tasks, helping partner support representatives efficiently access merchant data, transaction information, and manage portfolios.
🚀 Quick Start
Prerequisites
- Node.js 18+
- Stax API key with partner permissions
- MCP-compatible client (Claude Desktop, etc.)
Installation
# 1. Clone and install
git clone https://github.com/your-org/stax-partner-mcp-server.git
cd stax-partner-mcp-server
npm install && npm run build
# 2. Configure API key
cp config.json.template config.json
# Edit config.json and add your Stax API key
# 3. Verify setup
npm run health-check
# 4. Setup Claude Desktop (auto-configures)
npm run setup-claude
That's it! Restart Claude Desktop and you're ready to go.
📖 Need detailed setup? See for platform-specific instructions.
✨ Features
- 6 Essential Tools for partner support workflows
- Token-Optimized Responses (typically <500 tokens)
- Smart Caching with 70%+ hit rate for common queries
- Production-Grade Error Handling with helpful messages
- Request Batching and deduplication for performance
- Secure Authentication with Stax API keys
- TypeScript for type safety and better development experience
- Flexible Configuration via config file or environment variables
🛠️ Available Tools
The server provides 6 essential tools for partner support:
1. Merchant Management
get_merchant- Basic info and health statusget_application_status- Underwriting progress and blockerslist_portfolio_merchants- Portfolio overview with filtering
2. Transaction Analysis
list_recent_transactions- Recent transaction history with filtering
3. Financial Tools
fee_statement_analysis- Comprehensive fee breakdown and volume analysis
4. Dispute Management
list_active_disputes- Active disputes with urgency tracking
Each tool returns token-optimized responses with essential data first and details on demand.
📋 Configuration
Simple Setup (Recommended)
{
"stax_api_key": "your-stax-api-key-here"
}
Advanced Configuration
{
"stax_api_key": "your-api-key",
"api_settings": {
"timeout": 8000,
"max_retries": 2
},
"caching": {
"enabled": true,
"ttl_seconds": 180
},
"logging": {
"level": "info"
}
}
Environment Variables: You can also use
STAX_API_KEYenvironment variable instead of config.json
🔗 Claude Desktop Integration
Add to your claude_desktop_config.json:
{
"mcpServers": {
"stax-partner": {
"command": "node",
"args": ["/path/to/stax-partner-mcp-server/dist/index.js"]
}
}
}
Config file locations:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
🧪 Development
npm run dev # Development with auto-reload
npm run build # Build TypeScript
npm run test # Run test suite
npm run lint # Check code style
npm run health-check # Verify setup
📚 Documentation
- 🛠️ - Platform-specific setup details
- 📖 - Usage examples and configurations
- 🏗️ API Documentation - Complete tool reference
🤝 Contributing
- Fork the repository
- Create a feature branch
- Make your changes with tests
- Submit a pull request
📄 License
MIT License - see LICENSE file for details.
Token Optimization Strategy
Response Design
- Concise summaries: 30-50 tokens
- Essential data first: Core info in 100-200 tokens
- Details on demand: Use
include_detailsflags - Smart truncation: Limit lists, show "and X more"
Caching Strategy
- Merchant info: 5-minute cache (infrequent changes)
- Transactions: 1-minute cache (frequent changes)
- Deposits: 3-minute cache (daily settlement)
- Portfolio: 2-minute cache (overview queries)
Performance Features
- Request batching: Identical requests share responses
- Parallel fetching: Multiple API calls when needed
- Compression: Large responses are compressed
- Rate limiting: Prevents API quota exhaustion
Error Handling
The server provides helpful, actionable error messages:
- Merchant not found: Shows ID format help and suggests portfolio listing
- Authentication failed: Explains credential setup and permissions
- Rate limited: Suggests wait time and optimization tips
- Invalid parameters: Shows valid ranges and examples
- API errors: Provides troubleshooting guidance
Development
Project Structure
src/
├── config.ts # Configuration management
├── index.ts # Entry point
├── server.ts # Main MCP server
├── services/ # Core services
│ ├── authManager.ts # Authentication handling
│ ├── apiClient.ts # Optimized Stax API client
│ ├── cache.ts # Token-aware caching
│ └── toolRegistry.ts # Tool registration & execution
├── tools/ # Tool implementations
│ ├── merchantTools.ts # Merchant information tools
│ ├── transactionTools.ts # Transaction tools
│ ├── financialTools.ts # Financial tools
│ └── disputeTools.ts # Dispute & portfolio tools
├── types/ # TypeScript type definitions
│ ├── config.ts # Configuration types
│ ├── merchant.ts # Merchant-related types
│ ├── transactions.ts # Transaction types
│ ├── financial.ts # Financial types
│ ├── disputes.ts # Dispute types
│ └── index.ts # Type exports
└── utils/ # Utility classes
├── errorHandler.ts # Production error handling
├── formatter.ts # Token-optimized formatting
└── logger.ts # Structured logging
Scripts
npm run build # Build TypeScript
npm run start # Start production server
npm run dev # Development with auto-reload
npm run test # Run test suite
npm run lint # Check code style
npm run lint:fix # Fix linting issues
npm run type-check # TypeScript type checking
Testing
# Run all tests
npm test
# Run with coverage
npm run test -- --coverage
# Watch mode for development
npm run test -- --watch
Performance Metrics
Target performance indicators:
- Token Efficiency: <500 tokens per typical response
- Response Time: <2s cached, <5s API calls
- Cache Hit Rate: >70% for merchant/portfolio queries
- Error Rate: <1% for valid requests
- API Rate Limit: 120 RPM (2 req/second) with burst allowance
Security
- API Key Security: Credentials stored in environment variables
- Request Validation: All inputs validated and sanitized
- Error Sanitization: No sensitive data in error messages
- Rate Limiting: Prevents abuse and quota exhaustion
- Logging: Structured logs without sensitive information
Production Deployment
Docker Support
Create a Dockerfile:
FROM node:18-alpine
WORKDIR /app
COPY package*.json ./
RUN npm ci --only=production
COPY dist ./dist
EXPOSE 3000
USER node
CMD ["node", "dist/index.js"]
Environment Setup
# Production configuration
export NODE_ENV="production"
export LOG_LEVEL="info"
export ENABLE_METRICS="true"
# Stax API credentials (secure)
export STAX_API_KEY="$(cat /run/secrets/stax_api_key)"
# Performance tuning
export CACHE_MAX_ENTRIES="2000"
export PARTNER_RATE_LIMIT_RPM="200"
MCP Client Configuration
Add to your MCP client configuration:
{
"mcpServers": {
"stax-partner": {
"command": "node",
"args": ["/path/to/stax-partner-mcp-server/dist/index.js"],
"env": {
"STAX_API_KEY": "your-api-key"
}
}
}
}
Contributing
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature) - Make your changes with tests
- Ensure code passes linting and tests
- Commit changes (
git commit -m 'Add amazing feature') - Push to branch (
git push origin feature/amazing-feature) - Open a Pull Request
Support
- Issues: Report bugs and feature requests via GitHub Issues
- Documentation: Check the
/docsfolder for detailed guides - API Reference: See the Stax API documentation
- MCP Protocol: Visit the Model Context Protocol specification
License
MIT License - see LICENSE file for details.
Changelog
v1.0.0
- Initial release with 8 essential tools
- Token-optimized response formatting
- Production-grade error handling
- Smart caching and request batching
- Comprehensive test suite