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

Overview

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

Note: This connector is for querying live data from running solutions (connects to TServer.exe). For AI-assisted solution configuration, see AI MCP for Designer Connector.

Key Capabilities

• Real-time Data Access

• — Query live tag values, historian data, and alarm states through AI

• Unified Namespace Browsing — Explore your tag structure and discover available data
• Historical Analysis — Query historian for trend analysis and past behavior investigation
• Alarm Monitoring — Check active alarms and query alarm history
• Custom Methods — Extend with your own solution-specific AI tools
• Platform Agnostic — Works with Claude, GitHub Copilot, and other MCP-compatible AI models

When to Use MCP for Runtime

Technical Specifications

Prerequisites

• FrameworX 10.1 or later
• .NET 8.0 runtime
• Claude Desktop or compatible MCP client
• Running FrameworX solution (TServer.exe)
• Network connectivity

Configuration

The

first step is to run the solution, which will automatically start the

MCP Server

. The second step is to configure the client LLM to perform the queries.

According to the claude documentation, there are three ways of connection to the MCP Server:

1. stdio
2. HTTP
3. SSE 

stdio

The following configuration uses stdio, which requires the MCP server to run on the same machine as the LLM. Therefore, if your solution is hosted on a remote machine, you must install the product in both environments: the local machine (where the LLM runs) and the remote machine (where the runtime is hosted).

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

starts automatically when your solution runs. You need to configure your AI client to connect to it.

Connection Methods

stdio Configuration

Use stdio when the AI client runs on the same machine as your solution.

Configure Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "YourSolution": {
      "command": "C:\\FrameworX\\fx-10\\net8.0\\TMCPServerStdio\\TMCPServerStdio.exe",
      "args": ["/host:127.0.0.1", "/port:3101"],
      "transport": "stdio"
    }
  }
}

Note: For

Windows-only solutions,

use the path <ProductPath>\

fx-10\

TMCPServerStdio\

TMCPServerStdio.exe

(without net8.0).

HTTP Configuration

Use HTTP when the AI client runs on a different machine than your solution.

MCP Server Settings (TMCPServerHttp.json

HTTP

This method was only tested with GitHub Copilot. Other LLMs should work as well, but have not been tested.

Program: TMCPServerHttp

Install Path: <ProductPath>\fx-10\net8.0\TMCPServerHttp\ (NET 8.0 Runtime required to execute TMCPServerHttp.dll)

LLM Setting 

Arguments in LLM Setting, example: .mcp.json (GitHub Copilot) or claude_desktop_config (ClaudeAI) (location may vary depending on the LLM)

1. Url:<url>: Endpoint containg Host:Port. Ex: http://localhost:3000, https://192.168.20.2:3000
   When using certificate HTTP/SSL, the url must include "https"

2. Headers: X_API_KEY (optional) used by authentication

MCP Server Setting

in C:\Users\Public\Documents\FrameworX\MachineSettings

)

Runtime section:

:

Multiple connections

To connect to several runtimes and/or listen several ports, call TMCPServerHttp with argument “/instance:<number>“.

1. Arguments in section “4” must include “instance”.

2. Example: TMCPServerHttp /instance:2 => X_API_KEY2, ListenPort2, Runtime2, etc…

{

  "

appSettings": {
    "

X_API_KEY": 

"",
    

"

CertFileName": "

",
    

"

CertPass": "

",
    

"

CertHash": 

"",

"ListenPort": "3000",
    

"Runtime": {
    

"Host": 

"localhost",
      "

Port": "3101",
      "

Username": "guest",
      "

Password": ""

}
  }
}

AI Client Settings (GitHub Copilot .mcp.json):

{
  "

servers": 

{
    "FrameworX Runtime": {
      "

type": "

http",
      "

url": "

http://localhost:3000",
      "

headers": 

{
        "

X-API-KEY": ""
      }
    }
  }

}

HTTP Settings Reference:

Multiple Connections: To connect to multiple runtimes, use /instance:<number> argument and matching numbered settings (e.g., X_API_KEY2, ListenPort2, Runtime2).

Verifying Connection

1. Click the LLM connector icon — you should see your solution name
2. Go to Settings → Developer and verify the connection shows "running"
3. Ask the AI a simple question like "What is the server uptime?"

Available Tools

AI MCP for Runtime provides these built-in tools:

Data Access

Historical Data

Alarms

Example Queries

Reading Values:

• "What is the current value of Tag.Temperature1?"
• "Get the value of Tag.Plant1/Line2/Pressure"
• "What is the Server.SystemMonitor.CPUUsage?"
• "How many active alarms are there?" (uses Alarm.TotalCount)

Browsing Data:

• "What tags are available under Tag.Plant1?"
• "Show me the members of Tag.Pump1" (for UserType tags)
• "What alarm groups exist?"
• "Find all tags containing 'Temperature'"

Historical Analysis:

• "Show me the temperature history for today"
• "Get the historian data for Tag.Pressure from 8am to noon"
• "What was the highest temperature value today and when did it occur?"

Alarm Investigation:

• "Are there any active alarms?"
• "Show me alarms from the last 24 hours"
• "How many alarms were acknowledged today?"
• "Query the alarm history for Tag.Temperature1"

Custom Methods

You can extend the MCP server with your own solution-specific tools by creating custom methods in Scripts.

Creating Custom Methods

SSE

SSE configuration was not tested.

How to verify if the setting was done correctly

1. Click in the LLM connector, you should see the <SolutionName> name.
2. Go in Settings > Developer, and check if your solution is in a good state (running). (depends on the LLM).

Query Through AI

Once configured, the AI can access your solution data:

General questions

• What is the Server.SystemMonitor.Uptime of BottlingLine MCP Demo?
• Get value of Tag.Machine1.Temperature1

Alarm

• Is there any active alarm, or has there been one recently? Any acknowledged?
• Retrieve the alarms again, and check how many acknowledged alarms do we have? and how many are not?

Historian

• Retrieve the historical Brewery/BrewHouse/Temperature values from today.
• Show a trend visualization (only the trend) with the historical values of Brewery/BrewHouse/Temperature from today in JSX format
• Get all the historical value from today and return the highest and the time that hapenned

Custom Methods (methods you created)

• Get the last anomalies from the Bottling Line

Available Methods

When MCP server is running, by default you have three methods:

1. Get Value
2. Get Historian
3. Get Alarms

1. Navigate to Scripts → Classes
2. Create a new class

, select

1. with type MCP Tool

type

2. Define methods using MCP decorators

, where:

Description is the question you will ask the LLM.

MethodName is what the LLM will call. Each capital letter will appear as a space in the LLM interface.

Example

1. :

GetTankLevel will appear as "Get Tank Level".

ParametersDescription explains what is expected for each parameter.

Parameters define the inputs.

Content defines the behavior or response of the method.

Result is what the LLM will receive in order to generate the answer, which it will then convert into a more human-readable response.

Code Block

language	c#

[McpServerTool, Description("

<Description>

Get current tank level for a specific tank")]
public string 

<MethodName>

get_tank_level(
    [Description("

<ParametersDescription>

Tank identifier (1-4)")]

<Parameters>

 string tank_id = "1")
{

<Content>

    return 

<Result>

@Tag[$"Tank{tank_id}_Level"].ToString();
}

Example:

Code Block

Method Structure:

Element	Purpose
[McpServerTool]	Marks method as MCP tool
[Description("...")]	Explains what the tool does (shown to AI)
Method name	Tool name (use snake_case)
Parameter descriptions	Explains expected input to AI
Return value	Result sent to AI

Custom Method Examples

Simple Value Retrieval:

[McpServerTool, Description("Get 

production count 

for 

today")]
public string 

get_production_count()
{
    return @Tag.

Production.TodayCount.ToString();
}

Error Handling

Within the custom methods, you can also add safeguards to help identify potential errors, as shown below:

With Error Handling:

[McpServerTool, Description("

Get data 

for a specific tag with validation")]
public string 

get_tag_data(
    [Description("Full tag path")] string tag_name)
{
    try
    {
        if (!@Tag.Exists(

tag_name))
            return $"Error: Tag '{

tag_name}' not found";
        
        return @Tag[

tag_name].ToString();
    }
    catch (Exception ex)
    {
        @Info.Trace($"MCP Error: {ex.Message}");
        return "Error: Unable to retrieve data";
    }
}

Aggregated Data:

[McpServerTool, Description("Get summary of all tank levels")]
public string get_all_tank_levels()
{
    var result = new StringBuilder();
    for (int i = 1; i <= 4; i++)
    {
        var level = @Tag[$"Tank{i}_Level"].Value;
        result.AppendLine($"Tank {i}: {level}%");
    }
    return result.ToString();
}

Important: After creating or modifying custom methods, fully restart the AI client (close from Task Manager, not just the window).

Best Practices

For AI Queries

• Be specific about tag paths when asking for values
• Use "active alarms" for current state, "alarm history" for past events
• Specify time ranges clearly for historical queries
• Ask the AI to browse the namespace if you're unsure of tag names

For Custom Methods

• Use descriptive names and descriptions — the AI relies on these
• Include parameter validation and error handling
• Return clear error messages that help the AI understand what went wrong
• Follow snake_case naming convention for consistency
• Keep methods focused on single tasks

Security Considerations

• Use X_API_KEY authentication for HTTP connections
• Configure appropriate runtime user permissions
• Be cautious with write operations — consider read-only access for AI
• Review custom methods for security implications

Troubleshooting

MCP Server not starting

• Verify .NET 8.0 runtime

• is installed
• Check firewall settings for the configured port
• Confirm TMCPServerStdio.exe path is correct in AI client config

AI cannot access methods

• Ensure

• solution is running (

• TServer.exe active)

• Verify AI client configuration matches server settings

• Restart

• AI client completely (close

• via Task Manager)
• Check that MCP decorators are properly applied to custom methods

Data not updating

• Confirm tags are properly configured in the solution
• Verify real-time database connectivity
• Check

• custom method error handling for exceptions

Custom methods not appearing

• Verify class type is set to "MCP Tool"
• Check for syntax errors in method code
• Restart AI client completely after changes

HTTP connection failing

• Verify ListenPort is not blocked by firewall
• Check X_API_KEY matches between server and client
• For HTTPS, verify certificate is properly configured
• Test with http://localhost:3000 first before remote access

Related Documentation

Quick Start Tutorial

Build your first MCP

connection step by step:

• AI MCP for Runtime Tutorial

• — Creating and deploying MCP Tools

Example Implementation

Explore a complete working example

:

• SolarPanels MCP Demo

• — Full solution demonstrating MCP Tools with solar panel monitoring

Technology Information

• AI-Ready by Design

• — Platform architecture for AI integration

Reference Information

• Scripts Module Reference

• — Complete scripting documentation

AI MCP for Designer

For AI-assisted solution configuration (creating tags, displays, alarms):

• AI MCP for Designer Connector — Enable AI to configure solutions
• AI MCP for Designer Tutorial — Step-by-step guide for AI-assisted configuration

In this section...