This device is not compatible.

Build a Multi Agent System with MCP and A2A

PROJECT

Build a Multi Agent System with MCP and A2A

In this project, we’ll build a multi-agent system that collects news, weather, finance, and media data, then uses an LLM to generate a daily brief, delivered via a Streamlit app with real-world API integration.

You will learn to:

Build MCP servers to expose tools over HTTP.

Orchestrate multiple agents using FastMCP and message passing.

Integrate multiple external APIs with secure environment variables.

Generate structured content using an LLM prompt and response parsing.

Build a Streamlit UI that triggers agents and displays results.

Validate and normalize API outputs for reliable downstream usage.

Skills

Generative AI

Python 3

Large Language Models (LLMs)

Prerequisites

Basic Python programming

Familiarity with REST APIs

Basic understanding of LLMs and prompts

Understanding of async programming in Python

Basic knowledge of Streamlit

Technologies

Python

Project Description

In this project, we’ll build a small AI-driven news brief generator that fetches real-time data from multiple APIs, aggregates the data using an agent-based orchestration model, and generates a formatted article using a large language model. The system implements MCP servers for weather, news, finance, and media data sources, and defines scout and publisher agents that communicate through explicit message passing to assemble a context-aware daily brief.

The final output is rendered in a Streamlit interface that supports generating, viewing, and saving reports. Along the way, the project demonstrates how to design agent contracts, validate data schemas, and integrate third-party APIs using secure environment variables. This project targets developers building production-grade AI systems using tools such as FastMCP, OpenAI, and Streamlit, with an emphasis on modular architecture and agent coordination.

Project Tasks

Introduction

Task 0: Get Started

Task 1: Get API Keys

MCP Infrastructure

Task 2: Implement World Data MCP Server

Task 3: Implement Weather MCP Tool and Run the Server

Task 4: Implement Finance MCP Server

Task 5: Implement Media Engine MCP Server

Agent-to-Agent Orchestration

Task 6: Set Up Agent Messaging Protocol

Task 7: Build Contextualist Agent to Fetch Contextual Data

Task 8: Build Scout Agent to Aggregate Signals

Task 9: Build Publisher Agent to Generate Articles

User Interface

Task 10: Build Streamlit Interface to Trigger Agents

Task 11: Improve Article Readability in the UI

Congratulations!

Subscribe to project updates

Hear what others have to say

Join 1.4 million developers working at companies like

"Another great hands on project to apply your knowledge learned. Thank you Educative ❤️"

Atabek BEKENOV

Senior Software Engineer

"Super excited to learn E-commerce website for my own startup venture. Thanks for your great learning platform."

Pradip Pariyar

Senior Software Engineer

"This was an excellent lesson. I learned a lot working through the process. I enjoyed it so much that I rebuilt it my AWS account to see how hard it would be to deploy to a production environment."

Renzo Scriber

Senior Software Engineer

"It was my first proper data engineering project and it was amazing."

Vasiliki Nikolaidi

Senior Software Engineer

"It's a fantastic way to do hands-on practice; I enjoy this way of learning."

Juan Carlos Valerio Arrieta

Senior Software Engineer

Relevant Courses

Use the following content to review prerequisites or explore specific concepts in detail.