AI Agent protocols: MCP, A2A

A2A vs MCP 🤜💥🤛 - YouTube by Max S. 

Making Sense of Google's A2A Protocol

Making sense of Google's A2A Protocol (and how A2A relates to MCP) - YouTube by Max S.

What's Google's A2A all about? #aiagent #aigents #google #ai - YouTube by Max S. from Udemy

Introducing the Model Context Protocol \ Anthropic

The Model Context Protocol is an open standard that enables developers to build secure, two-way connections between their data sources and AI-powered tools. The architecture is straightforward: developers can either expose their data through MCP servers or build AI applications (MCP clients) that connect to these servers.

• Model Context Protocol specification and SDKs
• Local MCP server support in the Claude Desktop apps
• An open-source repository of MCP servers

Model Context Protocol (MCP) - Anthropic

Introduction - Model Context Protocol

At its core, MCP follows a client-server architecture where a host application can connect to multiple servers:

Google: A2A protocol

• MCP (Model Context Protocol) for tools and resources
  • Connect agents to tools, APIs, and resources with structured inputs/outputs.
  • Google ADK supports MCP tools. Enabling wide range of MCP servers to be used with agents.
• A2A (Agent2Agent Protocol) for agent-agent collaboration
• Dynamic, multimodal communication between different agents without sharing memory, resources, and tools
• Open standard driven by community.
• Samples available using Google ADK, LangGraph, Crew.AI

Build A Claude MCP Agent That Does Everything! - YouTube

Model Context Protocol (MCP): The Key To Agentic AI - YouTube