Integrum – Reflection based MCP Server from any Python module or library

Developer Nemanja Milosevic open sourced Integrum, an MIT-licensed library that generates MCP servers from existing Python modules, libraries, or plain classes, under the AlphaDeep project. Integrum uses an in-memory object store with word-based keys for state management and relies on FastMCP context for multi-user isolation in HTTP/SSE sessions. In a test, Gemma 4 (26B A4B) used Integrum to access scikit-learn's Random Forest Classifier on the Iris dataset and reached 100% validation accuracy without hyperparameter tuning.

Integrum - Reflection based MCP Server from any Python module or library https://nmilosev.svbtle.com/integrum-reflection-based-mcp-server-from-any-python-module-or-library Yesterday I open sourced Integrum https://github.com/alphadeepai/integrum , a library that is a part of AlphaDeep https://alphadeep.ai world. It allows you to quickly create MCP server s from existing Python libraries or modules or even plain classes . It is released with MIT license and I hope somebody else also finds it useful for a more formal approach to giving agents additional capabilities compared to just letting them writing arbitrary code with or without a sandbox . Couple of interesting things about it: State Management state-management 3 Obviously not all Python code is functional, so some state management is required. I opted for a simple in memory object store pattern with keys being “model-friendly” - they are words to save tokens. Also there is tuple unpacking, array access and other simple needed things to get started. Multi-user isolation multiuser-isolation 3 LLM sessions are stateless by design so I thought it would be hard to keep track of which object belongs to which user. Luckily after inspecting FastMCP implementation it seems like context is present for HTTP/SSE anyway so that didn’t turn out to be that difficult in the end. Gemma experiment recursive self-improvement? : gemma-experiment-recursive-selfimprovement 2 To test Integrum out I gave Gemma 4 26B A4B access to scikit-learn Random Forest Classifier and a toy dataset Iris . Without much trouble Gemma was able to build and evaluate a small model https://github.com/alphadeepai/integrum/blob/main/examples/gemma sklearn session.md . It didn’t experiment with hyperparameter tuning but since it got 100% validation accuracy it didn’t have the opportunity. It would be interesting to see what it would do with a “hard” problem. It would also be interesing if we gave it tools to update its own weights to improve performance on some benchmark. :