How to build an MCP (Model Context Protocol) Tool that exposes production KPIs and historical data to AI models, enabling intelligent analysis of industrial processes.
Navigate to Scripts → Classes
Click in the create a New Class button
In Create new Code, select MCPTool
Click OK
In the Script code, you can have multiple methods and they follow this format:
[McpServerTool, Description("<This is the question>")] public string <MethodName> ( [Description("<Description of the parameter>")] <Parameters>) { <Logic> <Return> }
Example:
[McpServerTool, Description("Performs concatenation of two input text values.")] public string Concat( [Description("The first text value to be used in the operation.")] string parameter1, [Description("The second text value to be used in the operation, concatenated after the first.")] string parameter2) { return parameter1 + parameter2; }
The logic can process the data and return it as a string, so the AI will receive it.
Have Claude AI Desktop downloaded
Go in Settings → Developer → Edit Config and select the ”claude_desktop_config.json”
This .json should have the following content:
{ "mcpServers": { "<SolutionName>": { "command": "<ProductPath>\\fx-10\\net8.0\\TMCPServerStdio\\TMCPServerStdio.exe", "args": [ "/host:127.0.0.1", "/port:<port>" ], "transport": "stdio" } } }
In the Developer setting it shoud show “running” and when you open a new chat in “Search and Tools” you will see the name of your solution there.
You can query any method in a Claude chat. e.g: “What is the tag value?” and it returns the value requested.
Besides the method you created in the script, you can ask general information about the solution, like:
Get tag historian
Get alarm online
Get value
These tutorials provide simple, practical starting points for both MCP Tools focusing on real industrial scenarios while keeping complexity minimal for learning purposes.