Provides tools for querying Git history and commit changes for Mendix .mxunit files, including semantic diffs that distinguish logic changes from layout moves. Enables questions about who changed a microflow, when, and what exactly changed.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mendix-mapper what uses MyModule.Customer and what breaks if I change it?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server that makes a Mendix app queryable by Claude — entities, microflows, pages, references, and semantic diffs of .mxunit across git history, without opening Studio Pro.
A Mendix project is binary. git diff tells you nothing, text search finds nothing, and figuring out the impact of a change means opening Studio Pro and clicking around.
This server fixes both ends of that:
it extracts the model from the .mpr and exposes it as queryable data;
it decodes .mxunit files (BSON) so commits can actually be diffed — including telling apart logic changes from things that merely moved on the canvas.
Related MCP server: contextflow-mcp
Once the server is connected, questions like these become answerable without leaving the conversation:
What uses MyModule.MyEntity? What breaks if I change it?
Which microflows write to this attribute?
Who changed this microflow, and when? What did they change?
Which entities are reachable from the client, and what access rules do they have?
Which pages and nanoflows can trigger this microflow?
See GETTING_STARTED.md — clone, virtual environment, one config file, and registering the server. About ten minutes.
Requirements:
Python 3.10+
Mendix Studio Pro installed (the server shells out to mx.exe to dump the .mpr; Studio Pro never needs to be running)
Windows (paths and mx.exe are Windows-oriented today)
Early. The code is being extracted from a private working version and lands here after a cleanup pass — the API is expected to change until the first tagged release.
Planned next: fieldbooks — a per-project package of business rules and project-specific tools, so the server can answer what the model itself cannot express.
This server cannot be deployed
Connect Claude to your Platform7n workspaces — chat, links, and tasks. One-click OAuth.
Give your AI agent persistent, governed memory for every project. At task start it recalls the approved decisions, conventions, risks and architecture (semantic search, ranked by importance); at close it proposes what was learned as typed memories that you review and approve — governance, not a notes dump. Agents propose, humans govern: edits go back to pending and deletion is human-only by design. Connect Claude Code, Cursor, Claude Desktop or any MCP client in two minutes with just your API key — hosted (nothing to install) or locally via `uvx solucortex-mcp`. Built by SoluAI and dogfooded daily: SoluCortex is developed using its own living memory.
Persistent memory for Claude Code and Cursor. Stop re-explaining your project every session.
AI Agent with Architectural Memory. Impact analysis (free), tests and code from the graph (pro).
