Position: Let’s Build a Trustworthy Model Context Protocol!
Arjhun Swaminathan, Anika Hannemann
Abstract
The Model Context Protocol (MCP) standardizes AI agent-tool interaction, accelerating agentic AI adoption through interoperability. This presents an opportunity to embed trustworthiness: As a standard and an interface between agents and tools, MCP becomes a natural enforcement point; any improvements to it automatically propagate to all systems using it. Analyzing MCP through EU Commission’s Ethics guidelines for trustworthy AI, we identify three things: fundamental shifts in how trustworthiness works, critical challenges these shifts create, and strategic intervention points where protocol-level mechanisms can achieve ecosystem-wide impact. We argue how MCP’s architecture provides a foundation for trustworthiness and propose practical improvements to strengthen it. This position paper posits that building trustworthy MCP enables responsible agentic AI deployments.
BibTeX
@inproceedings{icml2026_positionletsbuil,
title = {Position: Let’s Build a Trustworthy Model Context Protocol!},
author = {Arjhun Swaminathan and Anika Hannemann},
booktitle = {ICML 2026},
year = {2026}
}