Public-Sharing Labels and Verbatim Field Egress in an MCP-to-A2A Agent Configuration: A Controlled Multi-Model Study

Abstract

Safety properties assessed separately for Model Context Protocol (MCP) tool use and Agent2Agent (A2A) delegation need not describe behavior when one agent uses both. We measure one such behavior in a single controlled MCP-to-A2A configuration: a testbed drives a real-model host across a local MCP and a local A2A leg into an ordered event trace scored by exact deterministic rules (no LLM judge), one restricted decision per trial. In a pre-specified, frozen three-arm design, each of 10 record scen

Categories

Framework mappings

Suggested from the entry's categories.

@misc{mahapatra2026publicsharing,
  title = {{Public-Sharing Labels and Verbatim Field Egress in an MCP-to-A2A Agent Configuration: A Controlled Multi-Model Study}},
  author = {Arpan Kumar Mahapatra},
  year = {2026},
  month = sep,
  eprint = {2609.01693},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.01693}
}