Context Engineering with MCP

Example Use Cases

• 1

  Persistent semantic memory across sessions.

• 2

  Hybrid retrieval-augmented generation pipelines combining vector, graph, and session memory.

• 3

  Production-ready MCP implementations with Python and FastAPI.

Description

This repository provides a comprehensive training and production-ready implementation of the Model Context Protocol (MCP) to enable AI assistants to remember and manage context effectively. It features a flagship teaching app, WARNERCO Schematica, which demonstrates a hybrid retrieval-augmented generation (RAG) pipeline integrating vector, graph, and session memory stores. The system supports semantic search, relationship queries, and session memory to enhance AI assistant capabilities in real-world applications.