AI/ML Model Cards in Edge AI Cyberinfrastructure: towards Agentic AI

TL;DR

This paper explores dynamic AI/ML model cards embedded in edge AI systems, evaluating the Model Context Protocol's benefits, tradeoffs, and impact on active session management for ongoing model assessment.

Contribution

It introduces the use of Patra Model Cards as dynamic objects within edge AI infrastructure and assesses the MCP interface's effectiveness and overhead.

Findings

MCP enables active sessions for model cards.

Overhead of MCP is comparable to REST interfaces.

Active session management improves model lifecycle tracking.

Abstract

AI/ML model cards can contain a benchmarked evaluation of an AI/ML model against intended use but a one time assessment during model training does not get at how and where a model is actually used over its lifetime. Through Patra Model Cards embedded in the ICICLE AI Institute software ecosystem we study model cards as dynamic objects. The study reported here assesses the benefits and tradeoffs of adopting the Model Context Protocol (MCP) as an interface to the Patra Model Card server. Quantitative assessment shows the overhead of MCP as compared to a REST interface. The core question however is of active sessions enabled by MCP; this is a qualitative question of fit and use in the context of dynamic model cards that we address as well.