Createve.AI Nexus MCP server

Createve.AI Nexus is an open-source implementation of the Model Context Protocol (MCP), designed to bridge AI agents with enterprise systems. It allows AI systems to securely access your organization's data and capabilities, making AI deployment simpler and more scalable across various business applications.

Installation Guide

Prerequisites

• Docker and Docker Compose
• Azure account (for enterprise deployments)
• Access to your organization's systems for integration

Basic Installation

You can quickly deploy Createve.AI Nexus using Docker:

# Pull the Docker image
docker pull createveai/nexus:latest

# Run the container
docker run -d -p 8000:8000 --name nexus createveai/nexus:latest

Configuration Setup

Create a configuration file config.yaml with your settings:

server:
  port: 8000
  host: 0.0.0.0

security:
  apiKey: your-api-key-here
  enableAuth: true

integrations:
  databases:
    enabled: true
    connections:
      - name: main-db
        type: postgres
        connectionString: ${DB_CONNECTION_STRING}
  
  systems:
    - name: crm
      endpoint: https://your-crm-system.com/api
      authType: oauth2

Azure Enterprise Deployment

For production deployments in Azure:

# Deploy using Azure CLI
az container create \
  --resource-group your-resource-group \
  --name nexus-server \
  --image createveai/nexus:latest \
  --dns-name-label nexus-server \
  --ports 8000 \
  --azure-file-volume-account-name your-storage-account \
  --azure-file-volume-account-key your-storage-key \
  --azure-file-volume-share-name your-file-share \
  --azure-file-volume-mount-path /app/config

Usage Guide

Connecting with Microsoft Copilot Studio

1. In Copilot Studio, navigate to the MCP integration settings
2. Add a new MCP connector with your Nexus server URL
3. Configure authentication using your API key
4. Test the connection to verify setup

Creating Custom Data Connectors

To expose your business data to AI agents:

// Example custom connector (save as myConnector.js)
module.exports = {
  name: "inventory",
  description: "Access inventory data",
  endpoints: [
    {
      path: "/products",
      method: "GET",
      handler: async (req, res) => {
        // Connect to your product database
        const products = await db.query("SELECT * FROM products");
        return res.json(products);
      }
    }
  ]
}

Add this connector to your configuration:

connectors:
  custom:
    - path: ./myConnector.js

Setting Up Database Access

Configure database connections to allow AI agents to query your data:

databases:
  - name: customerDb
    type: mssql
    connection: "Server=myserver;Database=customers;User Id=user;Password=pass;"
    tables:
      - name: customers
        description: "Customer information"
        readable: true
        columns:
          - name: customer_id
            description: "Unique customer identifier"
          - name: name
            description: "Customer's full name"

Integrating with Real-time Systems

For connecting to real-time data streams:

streams:
  - name: machineData
    type: mqtt
    topic: factory/machines/#
    broker: mqtt://broker.example.com
    description: "Real-time machine sensor data"

Securing Your Deployment

Set up security controls:

security:
  authentication:
    provider: azure-ad
    tenantId: your-tenant-id
    clientId: your-client-id
  
  authorization:
    roles:
      - name: reader
        permissions: ["read:data"]
      - name: admin
        permissions: ["read:data", "write:data"]

Troubleshooting

Common Issues

• Connection Failures: Verify network settings and firewall rules
• Authentication Errors: Check API keys and OAuth credentials
• Performance Issues: Monitor resource usage and optimize query patterns

Logging and Monitoring

Enable detailed logging for troubleshooting:

logging:
  level: debug
  output: file
  filePath: /var/log/nexus.log

Advanced Configuration

Scaling for Enterprise Use

For high-volume deployments:

performance:
  workers: 4
  maxConcurrent: 100
  timeoutSeconds: 30
  
  caching:
    enabled: true
    ttlSeconds: 300

Custom Processing Pipelines

Create data transformation pipelines:

pipelines:
  - name: documentProcessor
    steps:
      - type: extract
        format: pdf
      - type: transform
        action: summarize
      - type: store
        destination: knowledge-base

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "createveai-nexus" '{"command":"npx","args":["-y","createveai-nexus-server"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "createveai-nexus": {
            "command": "npx",
            "args": [
                "-y",
                "createveai-nexus-server"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your 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

2. Add this to your configuration file:

{
    "mcpServers": {
        "createveai-nexus": {
            "command": "npx",
            "args": [
                "-y",
                "createveai-nexus-server"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect