{"id":"timothywarner-org-context-engineering","name":"context-engineering","af_score":46.5,"security_score":20.2,"reliability_score":22.5,"what_it_does":"A training/repository (Python) showing how to build semantic long-term memory for AI assistants using Model Context Protocol (MCP) with FastAPI/FastMCP and a hybrid RAG architecture (vector + graph + scratchpad), including example labs (e.g., a hello MCP lab) and a flagship teaching app (WARNERCO Schematica).","best_when":"You want a learning-focused scaffold or baseline implementation for MCP tool servers and hybrid retrieval/memory pipelines in Python.","avoid_when":"You need a clearly documented, versioned, production SaaS interface with stable guarantees, explicit SLAs, and formal security/compliance statements from the package maintainers.","last_evaluated":"2026-03-30T15:36:03.136169+00:00","has_mcp":true,"has_api":true,"auth_methods":["Local run of MCP stdio server (no auth described in README)","Local FastAPI server (no auth described in README)"],"has_free_tier":false,"known_gotchas":["Repository appears educational; production-grade behaviors (structured errors, retries, idempotency, rate limits, and auth) are not evidenced in the provided README.","If MCP tools are stateful (scratchpad/session memory), agents may need to manage session identifiers/contexts carefully (details not provided in README).","Hybrid memory configuration may vary (vector/graph/Azure); misconfiguration could lead to partial retrieval or inconsistent behavior."],"error_quality":0.0}