Free account
Read this concept with a free account
Read this concept at no cost by signing in with Google.
no card needed
Core
MCP and A2A: The Protocols Connecting Agents to Tools and to Each Other
The Model Context Protocol (MCP) standardises how AI applications connect to tools and data sources; the Agent2Agent protocol (A2A) standardises how agents from different systems communicate. This guide explains each, the product decisions they create, and their security implications.
CONCEPT / THE AGENT LIFECYCLE
RELATED CONCEPTS
PRACTISE THIS CONCEPT
Agentic ProductsWhat is MCP, and why should a product manager care about it?→Agentic ProductsWe could build our travel agent on airline APIs, or use a browser agent that clicks through websites like a person. Which?→Agentic ProductsShould we build our agents on a model provider's hosted agent platform, or own the orchestration ourselves?→Agentic ProductsOur workplace agent now connects to forty tools and keeps calling the wrong one. What do you change?→Live Prototyping & AI-Native WorkflowPrototype an MCP server in a day so our product works from ChatGPT and Claude. Which tools do you expose first?→Agentic ProductsYour team wants to build an AI agent to onboard new suppliers. Should it be an agent, or something simpler?→