This device is not compatible.

Build an Agentic Workflow with CrewAI and GitHub MCP Server Tools

PROJECT

Build an Agentic Workflow with CrewAI and GitHub MCP Server Tools

In this project, we’ll learn to build a CrewAI agentic workflow using GitHub MCP Server tools. We’ll fetch and summarize issues, PRs, and branches and convert Markdown into polished HTML reports.

You will learn to:

Run and validate GitHub MCP Server commands locally to fetch the repo data.

Use LangChain to turn MCP commands into reusable tools.

Build and manage a multi-agent Crew workflow.

Integrate CrewAI with a Django application.

Skills

Generative AI

Large Language Models (LLMs)

Web Development

Prerequisites

Experience with Python programming

Working knowledge of Django

Intermediate understanding of large language models (LLMs) and prompt-based workflows

Familiarity with CrewAI concepts (agents, tasks, and crews)

Understanding of REST APIs

Technologies

OpenAI

Django

Python

LangChain

Project Description

Understanding repository health, tracking open issues, reviewing pull requests, and monitoring branches are essential tasks for development teams managing complex codebases. Manually gathering this information across multiple GitHub repositories is time-consuming and prone to inconsistency. Agentic workflows powered by multi-agent systems can automate repository analysis by orchestrating specialized agents that each focus on specific aspects of the codebase, then synthesize findings into comprehensive reports.

In this project, we'll build a Django web application that integrates CrewAI with the GitHub MCP Server to create an intelligent repository analysis system. Users can input any public GitHub repository URL, triggering a multi-agent workflow where specialized CrewAI agents retrieve and summarize repository structure, open issues, recent pull requests, and active branches. We'll use LangChain tools to interact with the MCP Server for GitHub API data extraction, then configure each agent with specific tasks for analyzing different repository aspects. The agents work collaboratively, with each generating Markdown documentation that gets combined into a unified HTML report rendered in Django.

We'll start by setting up the GitHub MCP Server integration and building the Django UI for user input and report display. Next, we'll create the CrewAI project structure with custom tools for repository analysis, define specialized agents (repository structure analyzer, issue lister, pull request analyzer, branch tracker), and assemble them into a coordinated agentic workflow. By the end, you'll have a production-ready AI-powered documentation system demonstrating CrewAI multi-agent orchestration, MCP Server integration, LangChain tooling, Django web development, and automated report generation applicable to any developer tools or code intelligence platform.

Project Tasks

Introduction

Task 0: Get Started

Integrate GitHub MCP Server

Task 1: Build mcpcurl

Task 2: Explore the GitHub MCP Server

Build and Run Django Application

Task 3: Build the User Interface

Task 4: Render the Documentation Interface

Task 5: Run the Django Application

Build the GitHub MCP Server Crew

Task 6: Set Up the CrewAI Project Structure

Task 7: Create a Custom Tool to Analyze a Repository’s Structure

Task 8: Create the CrewAI Agent to Analyze Repository Structure

Task 9: Set Up the CrewAI Task to Summarize Repository Structure

Task 10: Assemble the CrewAI Workflow

Task 11: Integrate Your Crew into the Django Workflow

Task 12: Run the Application

Task 13: Build an Issue Analyzer Agent

Task 14: Add the Issue Lister Task to the Crew

Task 15: Build the Pull Request Lister Agent

Task 16: Add the Pull Request Task to the Crew

Task 17: Build the Branch Lister Agent

Task 18: Add the Branch Listing Task to the Crew

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.