Agent2Agent and MCP: An End-to-End Tutorial for a complete Agentic Pipeline

Introduction

In the fast-moving world of agentic AI, two open protocols quietly solve the headaches that used to keep multi-agent projects from ever leaving the lab.

A few months ago, Anthropic introduced Model Context Protocol (MCP): A reliable access to the data and tools an agent needs once the conversation begins. Anthropic describes MCP as a USB-C port for language models—a single, well-defined connector that lets you plug the same model into GitHub, a Postgres database, or a custom knowledge base without rewriting the integration each time. By standardizing the way hosts, clients, and servers exchange "Tools," "resources," and "prompts," MCP turns context into something the model can count on rather than something developers keep stitching together ad hoc.  

Agent2Agent (A2A), a new protocol by Google, tackles another obstacle: getting autonomous agents—often built on different frameworks and hosted in different places—to understand one another. Instead of brittle, one-off bridges, A2A gives every agent a tiny "agent card" that advertises its skills and an HTTP interface that lets other agents negotiate tasks, stream intermediate results, and hand over artifacts. Google started the project to give agents a common language regardless of vendor, and the open-source spec already shows how discovery, task life-cycle updates, and secure push notifications can work out of the box. 

With A2A handling how agents talk to one another and MCP handling how they tap into the outside world, you end up with small, focused agents who can coordinate fluently and still see the bigger picture—an architecture that feels less like a collection of scripts and more like a cooperative workforce.

The Structure of this Tutorial

This tutorial will build a complete agentic pipeline using Agent2Agent and MCP. First, we will create and test a couple of simple MCP servers. Then, we will create a simple agent that uses MCP to get information. Finally, we will have a whole crew of agents that uses Agent2Agent to coordinate with each other while using MCP to get information.

For the sake of simplicity, we will use elementary agents that have access to single MCPs and MCPs that perform easy operations like fetching data from an API or searching the web.

We imagine we want to create a team of agents able to make simple reports about American Companies; in particular, we want to be able to ask questions such as "What is the price of the stocks of the top 10 companies in the S&P 500?" or "What are the top 5 producers of lumber in the US"?

Note on the Code

The code for this tutorial is available on GitHub. You should clone the repository, run the code locally, play around with it, and even modify it. This tutorial has been created by starting from two sources:

• Agent2Agent Tutorial
• MCP Tutorial

While the MCP documentation was terrific, the Google Agent2Agent repository had multiple issues and was not working as expected. As a consequence, I heavily modified the code provided.

How to run it

uv by Astral was used as a Python package and project manager. You can clone the repo, run uv sync, and then run whatever you need.

MCP Servers

Given our objective, we first define two services:

• A crawler able to search on Google and read web pages
• A stock retriever, able to get the price of a stock at a particular time and other helpful info

The Stock Retriever Service

We define a simple stock retriever service using FinHub APIs. The retriever will return a stock's current price, min, max opening, and closing price (IMPORTANT: if you use t

... View full README on GitHub