OneTech

You can extract and document Mendix Studio Pro modules locally by running a dedicated MCP server. It analyzes your Mendix .mpr files and produces ready-to-use JSON documentation for domain models, pages, microflows, and enumerations, which you can feed into AI-assisted tooling or internal docs.

How to use

Set up a local MCP server and connect your MCP-enabled client (for example an AI assistant) to it. You can run the server from your machine and point your client to the local process or to a locally installed binary. Once connected, request module documentation by specifying the path to your Mendix module file and the module name. The server will generate structured JSON files for DomainModel, Pages, Microflows, and Enumerations that your tooling can consume.

How to install

Prerequisites: ensure you have Node.js version 18.0.0 or newer installed on your system.

Install the MCP server globally so you can run it from any directory.

Install globally using npm:

npm install -g @jordnlvr/onetech-mcp-server

Additional setup and configuration

You can also run the server on demand without a global install by using npx. This keeps the tool lightweight and avoids permanent global changes.

Run with npx:

npx @jordnlvr/onetech-mcp-server

VS Code configuration for Copilot integration

Enable MCP support in your Copilot chat and point Copilot to your MCP server. Add the following configuration to your VS Code user settings.

{
	"github.copilot.chat.mcp.enabled": true,
	"github.copilot.chat.mcp.servers": {
		"onetech": {
			"command": "npx",
			"args": ["@jordnlvr/onetech-mcp-server"]
		}
	}
}

Alternative global install configuration

If you prefer using a globally installed binary, you can configure Copilot to call the binary directly.

{
	"github.copilot.chat.mcp.enabled": true,
	"github.copilot.chat.mcp.servers": {
		"onetech": {
			"command": "onetech-mcp-server"
		}
	}
}

Available tools

onetech_extract_module

Extracts domain model, pages, microflows, and enumerations from a Mendix module by invoking the MCP server with the specified module file path and module name. Returns JSON files containing DomainModel.json, Pages.json, Microflows.json, and Enumerations.json with their sizes and statuses.