Skip to main content
Glama
jordnlvr

OneTech MCP Server

by jordnlvr
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

OneTech MCP Server

NPM Version License: MIT

Extract and document Mendix Studio Pro modules via Model Context Protocol (MCP)

OneTech MCP Server enables AI assistants like GitHub Copilot to interrogate local Mendix .mpr files and extract comprehensive module documentation including domain models, pages, microflows, and enumerations.

🚀 Quick Start

Install Globally (Recommended)

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

Or Use with NPX (No Install)

npx @jordnlvr/onetech-mcp-server

Configure in VS Code

Add to your VS Code settings.json:

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

Or use global install:

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

📚 Usage

Once configured, use GitHub Copilot to extract module documentation:

You: "Extract the RequestHub module from D:\Projects\OneTech.mpr"

Copilot: [Uses onetech_extract_module tool]
✅ Successfully extracted 4 files from module 'RequestHub':
  - DomainModel.json (57KB)
  - Pages.json (42KB)
  - Microflows.json (0KB)
  - Enumerations.json (4KB)

🛠️ Available Tools

onetech_extract_module

Extracts domain model, pages, microflows, and enumerations from a Mendix module using mx.exe.

Parameters:

  • mprPath (required): Absolute path to the .mpr file

  • moduleName (required): Name of the module to extract

  • outputPath (required): Absolute path to output directory for JSON files

  • mxPath (optional): Path to mx.exe (default: D:\Program Files\Mendix\11.3.0.80734\modeler\mx.exe)

Returns:

  • JSON files containing complete module structure

  • File sizes and extraction status

  • Success/error messages

📋 Requirements

  • Node.js: >= 18.0.0

  • Mendix Studio Pro: Version 11.3.0 or compatible

  • mx.exe: Command-line tool (included with Studio Pro)

🔒 Privacy & Security

  • 100% Local: All processing happens on your machine

  • No Cloud: Your .mpr files never leave your computer

  • No Tracking: No telemetry, analytics, or data collection

  • Open Source: Full transparency, audit the code yourself

🎯 Use Cases

  • Documentation Generation: Extract module structure for AI-powered docs

  • Code Review: Analyze domain models and microflows

  • Migration Planning: Understand module dependencies

  • Teaching: Demonstrate Mendix architecture to students

  • Onboarding: Help new developers understand existing apps

📦 What Gets Extracted

For each module, the tool generates 4 JSON files:

  1. DomainModel.json: Entities, attributes, associations, validation rules

  2. Pages.json: Page layouts, widgets, data sources

  3. Microflows.json: Logic flows, actions, parameters

  4. Enumerations.json: Enumeration types and values

🏗️ Architecture

Your Machine
├── VS Code + GitHub Copilot
├── OneTech MCP Server (this package)
│   └── Calls mx.exe with your .mpr file
├── mx.exe (Mendix CLI)
└── Your .mpr files (local, never uploaded)

🤝 Contributing

Built by the OneTech Team for the Mendix developer community.

Found a bug? Open an issue on GitHub.
Have a feature request? Let us know!

📄 License

MIT License - See LICENSE file for details

🔗 Links

Version: 0.1.0
Status: MVP Release
First Mendix MCP Server 🎉

Available Tools

1 tool
onetech_extract_moduleA

Extract domain model, pages, microflows, and enumerations from a Mendix module using mx.exe. Returns JSON files with complete module structure.

ParametersJSON Schema
NameRequiredDescriptionDefault
mprPathYesAbsolute path to the .mpr file (e.g., D:\Projects\OneTech.mpr)
moduleNameYesName of the module to extract (e.g., RequestHub)
outputPathYesAbsolute path to output directory for JSON files
mxPathNoOptional: Path to mx.exe (default: D:\Program Files\Mendix\11.3.0.80734\modeler\mx.exe)

TDQS

A3.5/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the tool uses 'mx.exe' and returns JSON files, but it lacks details on permissions, side effects, error handling, or performance aspects. For a tool with no annotations, this leaves significant gaps in understanding its behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that efficiently conveys the tool's purpose, method, and output. It is front-loaded with key information and avoids unnecessary details, making it highly concise and effective for quick comprehension.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of annotations and output schema, the description provides basic context but is incomplete. It covers the tool's action and output format but misses behavioral details and return value specifics. For a tool with 4 parameters and no structured output, more information would improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 100%, so the input schema already documents all parameters thoroughly. The description does not add any additional meaning or context beyond what the schema provides, such as usage examples or constraints. This meets the baseline for high schema coverage but does not enhance parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Extract'), the target resources ('domain model, pages, microflows, and enumerations'), and the tool used ('mx.exe'). It specifies the scope ('from a Mendix module') and the output format ('JSON files with complete module structure'), making the purpose specific and comprehensive without relying on sibling tools for differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for extracting module components in Mendix projects, but it does not provide explicit guidance on when to use this tool versus alternatives, prerequisites, or exclusions. With no sibling tools, the context is straightforward, but the lack of detailed guidelines limits its effectiveness for complex decision-making.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool update
    • First observedonetech_extract_module
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.5/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool has a clear, distinct purpose focused on extracting module structure from Mendix.

Naming Consistency5/5

The naming follows a consistent verb_noun pattern (onetech_extract_module), and with only one tool, there is no inconsistency to evaluate. The name clearly describes the action and target.

Tool Count2/5

A single tool is too few for most server purposes, as it severely limits functionality and suggests an incomplete or overly narrow scope. While the tool itself might be useful, the set lacks breadth for typical MCP server operations.

Completeness2/5

The server appears to target Mendix module extraction, but with only one tool, there are significant gaps. There is no coverage for creating, updating, deleting, or querying modules, making the surface incomplete for any robust workflow in this domain.

Resources

Related MCP Connectors