n8n-nodes-fusion

v0.6.31

Published

10 days ago

n8n community node for Fusion AI (NeuroSwitch multi-provider orchestration)

Downloads

2,487

0High
0Medium
0Low

mcp4

n8n-community-node n8n fusion ai neuroswitch openai anthropic claude gemini orchestration langchain

Fusion AI Node for n8n

A production-ready n8n community node package that provides seamless integration with Fusion AI's NeuroSwitch multi-provider orchestration platform.

🚀 Features

Multi-Provider AI Access: Connect to OpenAI, Anthropic, Google, and other AI providers through a single unified interface
NeuroSwitch Auto-Routing: Intelligent automatic provider selection based on availability and performance
LangChain Integration: Full compatibility with n8n's AI Agent workflows and tool calling
Secure Credentials: API keys are stored securely with noData: true protection
Production Ready: Built with TypeScript, strict type checking, and comprehensive error handling

📦 Installation

From npm (Recommended)

npm install fusion-node

From Source

git clone https://github.com/Fusionaimcp4/n8n-nodes-fusion.git
cd n8n-nodes-fusion
npm install
npm run build

In n8n

Install the package in your n8n instance
Restart n8n
The Fusion AI nodes will appear in the node palette

🔧 Setup

1. Get Your Fusion API Key

Visit Fusion AI Platform
Sign up for an account
Generate your API key from the dashboard

2. Configure Credentials in n8n

Step-by-Step Credential Setup:

Open n8n: Navigate to your n8n instance
Go to Credentials: Click on "Credentials" in the left sidebar
Add New Credential: Click the "+" button or "Add Credential"
Search for Fusion: Type "Fusion API" in the search box
Select Fusion API: Click on "Fusion API" from the results
Enter Your Details:
- API Key: Paste your Fusion AI API key
- Base URL: Leave as default (https://api.mcp4.ai) or enter custom URL
Test Connection: Click "Test" to verify your credentials work
Save: Click "Save" to store your credentials
Name Your Credential: Give it a descriptive name like "Fusion AI Production"

Credential Fields Explained:

API Key (Required): Your Fusion AI API key for authentication
- Get this from your Fusion AI dashboard
- Keep this secure and never share it publicly
- The field is password-protected for security
Base URL (Optional): The base URL for the Fusion AI API
- Default: https://api.mcp4.ai
- Only change if using a custom Fusion AI instance
- Must include the protocol (https://)

Security Best Practices:

Environment Variables: In production, use environment variables for API keys
Credential Naming: Use descriptive names to identify different environments
Access Control: Limit API key permissions to necessary scopes only
Regular Rotation: Periodically rotate your API keys for enhanced security
Monitoring: Monitor API usage and costs through the Fusion AI dashboard

Troubleshooting Credentials:

"Invalid API Key" Error:

Verify the API key is correct and active
Check for extra spaces or characters
Ensure the API key hasn't expired

"Connection Failed" Error:

Verify your internet connection
Check if the Base URL is correct
Ensure your firewall allows HTTPS connections to api.mcp4.ai

"Test Connection Failed":

Double-check your API key
Verify the Base URL is accessible
Check n8n logs for detailed error messages

🎯 Usage

Fusion Chat Model Node (AI Agent Integration)

The primary node for AI Agent workflows:

Add Node: Drag "Fusion Chat Model" from the node palette
Select Model: Choose from available providers:
- NeuroSwitch (auto routing) - Recommended
- OpenAI: GPT-4, GPT-3.5-turbo
- Anthropic: Claude 3 Sonnet, Claude 3 Haiku
- Google: Gemini Pro, Gemini Pro Vision
Configure Options:
- Temperature: 0.0-1.0 (default: 0.3)
- Max Tokens: 1-4096 (default: 1024)
Connect to AI Agent: Use as a Language Model in AI Agent workflows

Example AI Agent Workflow

{
  "nodes": [
    {
      "name": "Fusion Chat Model",
      "type": "fusionChatModel",
      "parameters": {
        "model": "neuroswitch",
        "options": {
          "temperature": 0.3,
          "maxTokens": 1024
        }
      }
    },
    {
      "name": "AI Agent",
      "type": "aiAgent",
      "parameters": {
        "languageModel": "={{ $('Fusion Chat Model').item.json.response }}"
      }
    }
  ]
}

🔒 Security

Credential Protection

API Keys: Stored securely with noData: true protection
No Data Persistence: Credentials are not logged or stored in plain text
Secure Transmission: All API calls use HTTPS encryption

Best Practices

Environment Variables: Use environment variables for API keys in production
Access Control: Limit API key permissions to necessary scopes
Monitoring: Monitor API usage and costs through Fusion AI dashboard
Rotation: Regularly rotate API keys for enhanced security

Reporting Security Issues

If you discover a security vulnerability, please do not open a public GitHub issue. Instead:

Email: [email protected]
Response Time: We aim to respond within 24-48 hours
See: SECURITY.md for detailed reporting guidelines

🛠️ Development

Prerequisites

Node.js >= 18.0.0
npm or yarn
TypeScript knowledge

Building from Source

# Clone repository
git clone https://github.com/Fusionaimcp4/n8n-nodes-fusion.git
cd n8n-nodes-fusion

# Install dependencies
npm install

# Build the project
npm run build

# Run linting
npm run lint

# Format code
npm run format

Project Structure

├── dist/                    # Built files (production)
├── nodes/Fusion/           # Source TypeScript files
│   ├── FusionChatModel.node.ts    # Main AI Agent node
│   ├── FusionApi.credentials.ts   # Credential configuration
│   └── fusion.svg                # Node icon
├── package.json           # Package configuration
├── tsconfig.json         # TypeScript configuration
└── README.md             # This file

📊 Supported Models

OpenAI

GPT-4
GPT-4 Turbo
GPT-3.5-turbo
GPT-3.5-turbo-16k

Anthropic

Claude 3 Sonnet
Claude 3 Haiku
Claude 3 Opus

Google

Gemini Pro
Gemini Pro Vision

Auto-Routing (NeuroSwitch)

Automatically selects the best available provider
Handles failover and load balancing
Optimizes for cost and performance

🐛 Troubleshooting

Common Issues

"Invalid model ID" Error

Ensure the model string format is correct: provider:model_id
Check that the model is active in your Fusion AI account

"Could not resolve parameter dependencies" Error

This has been fixed in the latest version
Update to the latest package version

Connection Timeout

Verify your API key is correct
Check your internet connection
Ensure the base URL is accessible

Debug Mode

Enable debug logging in n8n to see detailed error messages:

N8N_LOG_LEVEL=debug npm start

📈 Performance

Optimization Tips

Use NeuroSwitch: Automatic routing optimizes for speed and cost
Batch Requests: Process multiple items in a single workflow execution
Cache Results: Store frequently used responses
Monitor Usage: Track token consumption and costs

Rate Limits

Fusion AI handles rate limiting automatically
NeuroSwitch provides intelligent queuing
Respect individual provider rate limits

🤝 Contributing

We welcome contributions! Please see our Contributing Guidelines for details.

Development Setup

Fork the repository
Create a feature branch
Make your changes
Add tests if applicable
Submit a pull request

📄 License

This project is licensed under the MIT License - see the LICENSE.txt file for details.

🆘 Support

Documentation: Fusion AI API Docs
Issues: GitHub Issues
Discussions: GitHub Discussions
Email: [email protected]

🔄 Changelog

v0.1.4

Initial release
Fusion Chat Model node for AI Agent integration
Multi-provider support (OpenAI, Anthropic, Google)
NeuroSwitch auto-routing
Secure credential handling
Production-ready build system

Made with ❤️ by the Fusion AI team