Standards and AI Agents: an Overview of MCP, A2A, ADK and More
summary
Overview of IA agent standards and frameworks: explains protocols MCP, A2A, ACP and frameworks ADK, Arc, Quarkus, LangChain4j. Shows how to build an agent first without protocols, then add MCP interactions, and finally create a multi-agent, multi-technology system using A2A with ADK, Quarkus and LangChain4j, including live demos and explanations of why and how the protocols work.
AI-written summary · about
chapters (11)
- 0:00Conference intro
- 1:05AI agents defined
- 22:50MCP and A2A protocols
- 33:10MCP details
- 1:00:00MCP demo
- 1:22:50MCP security
- 1:39:29A2A overview
- 2:08:02A2A lifecycle
- 2:33:09A2A demo
- 2:50:04MCP vs A2A
- 2:58:00Q&A
related talks
26mOverview of AI Agent Protocols
46mMCP and A2A Revolutionizing Interconnection and Collaboration of AI Agents
41mPatterns & Practices for building Multi-Agent Systems
27mA2A in 25 Minutes: Building AI agents that communicate
32mFrom Monolith to AI Agent Modernizing Java Systems with MCP
39mA2A in 45 Minutes: Building Interoperable AI Agents
43mA2A in 50 Minutes: Building Interoperable AI Agents
29mBuilding Interoperable Agents: When A2A meets MCP