
ERPNext MCP Server
A production-ready server that enables AI assistants like Claude Desktop to seamlessly integrate with ERPNext for document operations, reporting, and custom workflows through natural language interaction.
README
ERPNext MCP Server
A production-ready Model Context Protocol (MCP) server for seamless ERPNext integration with AI assistants like Claude Desktop.
🚀 Features
- Complete ERPNext Integration: Full CRUD operations for documents, DocTypes, reports, and dashboards
- Production-Ready Security: OAuth 2.1, API key authentication, rate limiting, and comprehensive audit logging
- High Performance: Redis caching, connection pooling, and optimized API calls
- Enterprise Features: Multi-tenancy support, horizontal scaling, and high availability
- Comprehensive Monitoring: Health checks, metrics, and detailed logging
- Docker Support: Multi-stage builds for minimal attack surface
- TypeScript: Full type safety and modern JavaScript features
📋 Prerequisites
- Ubuntu 20.04/22.04/24.04 LTS
- Node.js 18+
- Redis 6+
- ERPNext instance with API access
- Digital Ocean droplet (minimum 2GB RAM)
🛠️ Quick Installation
Option 1: Automated Installation (Recommended)
# Download and run the installation script
wget https://raw.githubusercontent.com/YOUR_USERNAME/erpnext-mcp-server/main/scripts/install.sh
chmod +x install.sh
sudo ./install.sh
Option 2: Manual Installation
# Clone the repository
git clone https://github.com/sivabhogela88/erpnext-mcp-server.git
cd erpnext-mcp-server
# Install dependencies
npm ci
# Copy and configure environment variables
cp .env.example .env
nano .env # Edit with your ERPNext credentials
# Build the project
npm run build
# Start the server
npm start
Option 3: Docker Installation
# Build the Docker image
docker build -t erpnext-mcp-server .
# Run with Docker Compose
docker-compose up -d
⚙️ Configuration
Environment Variables
Create a .env
file with the following configuration:
# ERPNext Configuration
ERPNEXT_URL=https://your-erpnext-instance.com
ERPNEXT_API_KEY=your_api_key_here
ERPNEXT_API_SECRET=your_api_secret_here
# OAuth Configuration (optional)
OAUTH_ENABLED=false
OAUTH_CLIENT_ID=your_oauth_client_id
OAUTH_CLIENT_SECRET=your_oauth_client_secret
OAUTH_REDIRECT_URI=http://localhost:3000/callback
# Server Configuration
NODE_ENV=production
PORT=3000
LOG_LEVEL=info
# Security Configuration
ENABLE_AUTH=true
JWT_SECRET=your_jwt_secret_here
ENCRYPTION_KEY=your_encryption_key_here
ALLOWED_ORIGINS=http://localhost,https://your-domain.com
# Redis Configuration
REDIS_URL=redis://localhost:6379
REDIS_PASSWORD=your_redis_password
# Rate Limiting
RATE_LIMIT_ENABLED=true
RATE_LIMIT_MAX_REQUESTS=100
RATE_LIMIT_WINDOW_MS=60000
Claude Desktop Configuration
Add the following to your Claude Desktop configuration file:
MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"erpnext": {
"command": "node",
"args": ["/opt/erpnext-mcp-server/dist/index.js"],
"env": {
"ERPNEXT_URL": "https://your-erpnext-instance.com",
"ERPNEXT_API_KEY": "your_api_key",
"ERPNEXT_API_SECRET": "your_api_secret"
}
}
}
}
🔧 Available Tools
Document Operations
create_document
- Create new ERPNext documentsread_document
- Retrieve document detailsupdate_document
- Update existing documentsdelete_document
- Delete documentslist_documents
- List documents with filters
Schema Operations
get_doctype
- Get DocType schema and field definitionslist_doctypes
- List all available DocTypes
Reporting & Analytics
get_report
- Execute and retrieve report datacreate_dashboard
- Create custom dashboards
Advanced Operations
execute_method
- Execute custom ERPNext methods
🔒 Security Features
- Authentication: OAuth 2.1 with PKCE or API key/secret
- Encryption: TLS 1.3 for all communications
- Rate Limiting: Configurable per-endpoint limits
- Input Validation: Zod schemas for all inputs
- Audit Logging: Comprehensive activity logs
- CORS Protection: Configurable allowed origins
- Container Security: Non-root user, read-only filesystem
📊 Monitoring & Logging
Health Check Endpoint
curl http://localhost:3000/health
Logs Location
- Application logs:
/opt/erpnext-mcp-server/logs/app.log
- Error logs:
/opt/erpnext-mcp-server/logs/error.log
- Access logs:
/opt/erpnext-mcp-server/logs/access.log
Monitoring with Systemd
# Check service status
sudo systemctl status erpnext-mcp
# View logs
sudo journalctl -u erpnext-mcp -f
# Restart service
sudo systemctl restart erpnext-mcp
🚀 Production Deployment
Digital Ocean Recommended Specs
Basic Setup (up to 50 concurrent users):
- 2 vCPUs
- 4GB RAM
- 50GB SSD
- $24/month
Production Setup (up to 200 concurrent users):
- 4 vCPUs
- 8GB RAM
- 100GB SSD
- $48/month
Enterprise Setup (200+ concurrent users):
- 8+ vCPUs
- 16GB+ RAM
- 200GB+ SSD
- Load balancer recommended
Security Hardening Checklist
- [ ] Configure firewall (UFW) rules
- [ ] Enable fail2ban for brute force protection
- [ ] Set up SSL/TLS with Let's Encrypt
- [ ] Configure log rotation
- [ ] Enable automatic security updates
- [ ] Set up monitoring alerts
- [ ] Regular security audits
- [ ] Implement backup strategy
🧪 Testing
# Run all tests
npm test
# Run tests with coverage
npm run test:coverage
# Run security tests
npm run test:security
# Run linting
npm run lint
🐛 Troubleshooting
Common Issues
-
Connection refused errors
- Check ERPNext URL and credentials
- Verify firewall rules
- Check Redis connection
-
Authentication failures
- Verify API key/secret
- Check token expiration
- Review audit logs
-
Performance issues
- Monitor Redis cache hit rate
- Check ERPNext server load
- Review rate limiting settings
Debug Mode
Enable debug logging:
LOG_LEVEL=debug npm start
📈 Performance Optimization
- Caching: Redis caching with 5-minute TTL
- Connection Pooling: Reuse HTTP connections
- Batch Operations: Support for bulk document operations
- Compression: Gzip compression for API responses
- CDN: Optional CloudFlare integration
🤝 Contributing
We welcome contributions! Please see our Contributing Guidelines for details.
- Fork the repository
- Create your feature branch (
git checkout -b feature/AmazingFeature
) - Commit your changes (
git commit -m 'Add some AmazingFeature'
) - Push to the branch (
git push origin feature/AmazingFeature
) - Open a Pull Request
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🙏 Acknowledgments
- Anthropic for the Model Context Protocol
- Frappe/ERPNext team for the amazing ERP platform
- Community contributors and testers
📞 Support
- Documentation: Full documentation
- Issues: GitHub Issues
- Discussions: GitHub Discussions
- Security: security@your-domain.com
Built with ❤️ for the ERPNext community
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.