AI MCP Tool Connector

Enable AI-powered industrial automation through Model Context Protocol integration.

Overview

The MCP (Model Context Protocol) Tool Connector bridges FrameworX solutions with AI language models, enabling intelligent automation assistance while maintaining industrial-grade safety and determinism. This connector exposes your solution's data and functionality as structured tools that AI models can invoke with parameters, not just generate text responses.

Key Capabilities

• Structured AI Integration - Expose specific methods and functions to AI models with type-safe parameters
• Real-time Data Access - Query live tag values, historian data, and alarm states through AI
• Bi-directional Communication - AI can both read from and write to your industrial systems (with appropriate safeguards)
• Platform Agnostic - Works with Claude, GPT, and other MCP-compatible AI models

Integration Architecture

AI Model (Claude/GPT) ←→ MCP Protocol ←→ FrameworX Solution
                              ↓
                     [Structured Methods]
                     [Tag Data Access]
                     [Historian Queries]
                     [Alarm Monitoring]

Technical Specifications

Prerequisites

• FrameworX 10.1 or later
• .NET 8.0 runtime
• Claude Desktop or compatible MCP client
• Network connectivity for TCP transport

Implementation Components

1. MCP Script Classes

Create specialized script classes that expose methods to AI models. These classes use decorator attributes to define AI-accessible functions.

Learn more: Scripts Classes Reference

2. AI-Ready Architecture

FrameworX's consistent object model and event-driven architecture provide the foundation for reliable AI integration.

Learn more: AI-Ready by Design

3. Solution Examples

Pre-built examples demonstrate MCP integration for real industrial scenarios.

Learn more: SolarPanels MCP Demo

Configuration Workflow

Step 1: Create MCP Script Class

1. Navigate to Scripts → Classes
2. Create new class, select MCP Tool type
3. Define methods with MCP decorators:

csharp

[McpServerTool, Description("Get current tank level")]
public string GetTankLevel(
    [Description("Tank identifier")] string tankId)
{
    return @Tag[$"Tank_{tankId}_Level"].ToString();
}

Step 2: Configure AI Client

Configure your AI client (e.g., Claude Desktop) to connect to the MCP server:

json

{
  "mcpServers": {
    "YourSolution": {
      "command": "C:\\FrameworX\\fx-10\\net8.0\\TMCPServerStdio\\TMCPServerStdio.exe",
      "args": ["/host:127.0.0.1", "/port:5000"],
      "transport": "stdio"
    }
  }
}

Step 3: Query Through AI

Once configured, the AI can access your solution data:

• "What is the current production rate?"
• "Show me active alarms for Line 1"
• "Get historian data for temperature over the last hour"

Deployment Patterns

Green Light: Safe for Autonomous Use

• Historical data analysis
• Pattern recognition
• Report generation
• Read-only monitoring

Yellow Light: Requires Oversight

• Optimization suggestions
• Predictive maintenance scheduling
• Quality predictions
• Automated troubleshooting

Red Light: Not Suitable

• Direct safety system control
• Emergency response decisions
• Critical process changes
• Unvalidated write operations

Getting Started

Quick Start Tutorial

Build your first MCP Tool and connect it to Claude AI:

How to Build an MCP Tool - Step-by-step guide for creating and deploying MCP Tools

Example Implementation

Explore a complete working example with MQTT integration:

SolarPanels MCP Demo - Full solution demonstrating MCP Tools with solar panel monitoring

Database Integration

Connect MCP Tools with external databases:

PostgreSQL Connector - Example of integrating MCP with PostgreSQL for historian data

Best Practices

Security Considerations

• Authentication - Implement proper authentication for MCP endpoints
• Authorization - Define clear permission levels for AI operations
• Validation - Always validate AI-generated parameters before execution
• Audit Trail - Log all AI-initiated actions for compliance

Performance Optimization

• Cache frequently accessed data
• Implement rate limiting for AI queries
• Use asynchronous methods for long-running operations
• Monitor resource usage of MCP server process

Error Handling

csharp

[McpServerTool, Description("Safe data retrieval")]
public string GetData(string tagName)
{
    try
    {
        if (!@Tag.Exists(tagName))
            return $"Error: Tag {tagName} not found";
        
        return @Tag[tagName].ToString();
    }
    catch (Exception ex)
    {
        @Info.Trace($"MCP Error: {ex.Message}");
        return "Error: Unable to retrieve data";
    }
}

Advanced Features

Multi-Model Support

The MCP Tool Connector supports multiple AI models simultaneously:

• Different models can access different method sets
• Model-specific permissions and rate limits
• Unified logging across all AI interactions

Custom Tool Definitions

Beyond standard methods, create specialized tools for:

• Complex workflow orchestration
• Multi-step industrial processes
• Cross-system data aggregation
• Custom business logic exposure

Troubleshooting

MCP Server not starting

• Verify .NET 8.0 runtime installation
• Check firewall settings for configured port
• Confirm TMCPServerStdio.exe path is correct

AI cannot access methods

• Ensure MCP decorators are properly applied
• Verify solution is running (Runtime → Startup)
• Check AI client configuration matches server settings

Data not updating

• Confirm tags are properly configured
• Verify real-time database connectivity
• Check MCP method error handling

Related Documentation

• AI-Ready by DAI-Ready by Designesign - Platform architecture for AI integration
• Scripts Module Reference - Complete scripting documentation
• MCP Tool Tutorial - Step-by-step tutorial on how to create a MCP tool
• SolarPanels MCP Demo - Working example solution

In this section...