---
format: "aidr-story-markdown/v1"
id: "5d193cc1f396c8e39b220f8d1dbe6e508d25f4e743cec875d7aba3418f269cc6"
canonical_url: "https://aidr.today/5d193cc1?lang=en"
title: "The Cost of Saying Hello: An Empirical Study of Handshake Overhead in AI Agent Communication Protocols"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-23T04:00:00.000Z"
category: "Frameworks"
topics: ["agent","framework"]
source_urls: ["https://arxiv.org/abs/2610.30151"]
summary: "A new empirical benchmark measures handshake overhead in three major AI agent communication protocols—MCP, A2A, and ACP—across cold-start, warm-repeat, capability-mismatch, and degraded-metadata scenarios, finding that round-trip count dominates handshake cost and that a legacy MCP handshake takes three round trips and 230 ms at 50 ms RTT while A2A needs one round trip and 61.0 ms."
---

# The Cost of Saying Hello: An Empirical Study of Handshake Overhead in AI Agent Communication Protocols

> [Open the canonical story](<https://aidr.today/5d193cc1?lang=en>)

**Published:** 2026-10-23T04:00:00.000Z
**Category:** Frameworks
**Topics:** agent, framework

## Summary

A new empirical benchmark measures handshake overhead in three major AI agent communication protocols—MCP, A2A, and ACP—across cold\-start, warm\-repeat, capability\-mismatch, and degraded\-metadata scenarios, finding that round\-trip count dominates handshake cost and that a legacy MCP handshake takes three round trips and 230 ms at 50 ms RTT while A2A needs one round trip and 61\.0 ms\.

## Sources

- [Story source](<https://arxiv.org/abs/2610.30151>)