DEV Community: Arun Saragadam

Quick read to know what Model Context Protocol is ...

Arun Saragadam — Sat, 17 May 2025 12:23:30 +0000

Arun Saragadam for In One Minute

May 16 '25

What Is Model Context Protocol (MCP)?

#mcp #modelcontextprotocol #ai #llm

Comments

4 min read

What Is Model Context Protocol (MCP)?

Arun Saragadam — Fri, 16 May 2025 04:27:18 +0000

🧠 What Is Model Context Protocol (MCP)?

TL;DR: Model Context Protocol (MCP) proposes a shared standard like USB for AI that lets assistants access relevant context directly from your apps.

Remember that one friend who turns finding a lost item into a twenty -question interrogation?

AI assistants have become incredibly helpful -- but sometimes, they feel just like that friend, especially as our expectations keep growing.

You: When was my 1:1 with Priya moved to?

LLM: I don’t have access to your calendar or email. Could you:

    – Upload your calendar file?

    – Paste the reschedule email?

    – Tell me when it was originally scheduled?

You: I think it was last Thursday. Priya mentioned the change in Slack.

LLM: Can you paste that message here?

You:

What if your AI assistant could channel its inner Sherlock...

You: When was my 1:1 with Priya moved to?

LLM: Checking your connected tools...

    ✅ Found reschedule email from Priya in Gmail — moved from Thursday to Friday

    ✅ Confirmed new event in Google Calendar: Friday, 11:30 a.m.

    ✅ Cross-referenced Slack chat from Tuesday confirming the change

LLM: Your 1:1 with Priya was rescheduled to Friday at 11:30 a.m., confirmed by calendar, email, and Slack. Elementary!

Model Context Protocol (MCP) is one way to make this possible, though not the only one.

Imagine a world without USB.

Every PC manufacturer would have its own ports for connecting devices like keyboards and mice.

Peripheral makers would need to build multiple versions of the same device to support different ports. That’s exactly what happens with electrical plugs today as each country has its own socket type.

What is Model Context Protocol (MCP)?

Model Context Protocol (MCP), like any other protocol, is a set of rules, kind of like the USB standard for computers, that aims to help AI assistants connect to apps (email, todo / task apps etc) and data. Think of a protocol as a shared language that allows different things to understand each other.

To be fair in comparison, USB devices do need computers to work and vice-versa — it's a symbiotic relationship.

That's not the case with the apps as they can function independently.

Why does it matter?

Just like Apple or Android can’t build every app and Slack can’t build every bot, AI assistants can’t build every capability users need. They must rely on the wider developer community to extend their capabilities by adapting existing apps to work with AI assistants through the MCP architecture.

When should you use it?

It's still early days for MCP, like when USB was first introduced. Not all computers or devices used it right away. Similarly, for MCP to become really useful, both the companies that make AI assistants (like the "computer" in the USB analogy) and the companies that make apps (like the "keyboard" or "mouse") need to adopt it.

For end-users:

You can add more capabilities to your favorite AI assistant. These are referred to as MCP servers—a somewhat confusing name, as they function more like extensions to your AI assistant. MCP is still in limited beta and is aimed mainly at developers.

For developers:

Should you jump on the bandwagon of building an MCP Server—in other words, making your app’s capabilities available to be used in the AI assistant client?

That depends. Ask yourself: how long your product can stand out if users only access it through an AI assistant.

How does it work?

Here is a diagram from the MCP documentation.

As a developer, you build an extension to AI assistants aka MCP Server. The MCP Host / Client is your AI assistant, like Claude or ChatGPT. Here is a full list of supported clients.

💬 Your Turn — What Do You Think?

Do you see MCP as a useful standard or just another layer of complexity?
What’s one app you wish your AI assistant could “talk to” seamlessly?
Would you ever build (or use) an MCP Server?
Would you trust an assistant that automatically pulls info from your apps?

Comment below or DM me—I’d love to hear your take.

📚 Next Topic?

I’m on a mission to make tech as easy as ABC! Is there a topic — anything from ABC to AI — that you'd love simplified?

👉 Drop it in the comments, or send me a quick DM, and I’ll break it down in a future post!

✏️ P.S.

I’m always tweaking these to make them better — was this one clear, helpful, or missing something?

Let me know in the comments or send me a quick DM!

Thanks for reading In 1 Min! Subscribe for free to receive new posts and support my work.

What Exactly is a Data Structure?

Arun Saragadam — Sat, 26 Apr 2025 05:29:00 +0000

TL;DR: A data structure is how your computer organizes and stores information efficiently—think of it like sorting your dishes or finding words in a dictionary.

Ever imagined how confusing a dictionary would be if all the words were randomly scattered throughout the book instead of neatly arranged alphabetically?

Now picture yourself cozily reading a book, and suddenly you stumble upon a word you don't know. No problem, right? Normally, you'd confidently reach for your dictionary—but imagine you have the chaotic dictionary described above. Finding your word could take forever!

Thankfully, dictionaries are neatly organized in alphabetical order, so you can quickly flip to the right section and find your word in seconds. This simple organization saves you a ton of time and hassle. That's exactly how data becomes structured.

A data structure is essentially a set of rules that determines how information is organized and used—whether it's arranging words in a dictionary, listing student names in a classroom register, managing how people line up to buy tickets, or even deciding which dinner plate gets used next (usually the top one in a stack).

Realizing you’ve been repeatedly using the same plate when stacking them on top of each other could make you reconsider your stacking habits—perhaps it’s time to queue the plates instead for a fairer rotation!

Now, let’s dive into the classic breakdown: What, Why, When, and How.

What?

A data structure is your computer’s way of keeping its sanity by neatly organizing information ("data"), making sure nothing gets lost or mixed up.

Why?

Without these clever systems, everyday tasks like finding your friend's contact in your phone, tracing back replies to a message, or even grabbing a book from a library would feel chaotic—like endlessly searching for something important in a messy room.

When?

Every time you store, access, or organize information—whether in code or real life—you’re instinctively using a data structure. Think: always placing your keys in the same spot or sorting clothes into different drawers.

How?

You already use data structures in daily life: storing each friend's birthday alongside their contact information in your phone, or neatly sorting clothes into specific shelves for easy access.

When you start coding, you’ll apply the same logic—by choosing popular, predefined data structures like arrays, linked lists, stacks, queues, or trees. You can even combine these structures to build new, efficient ways to organize and manage your data.

🎯 Your Turn!

Which of these best describes a data structure?

A) A random jumble of information
B) A system for organizing and storing data
C) A type of digital art
D) A way to scramble computer memory

(Type your answer—A, B, C, or D—in the comments!)

📚 Next Topic?

I'm on a mission to make tech as easy as ABC! Is there any topic—from ABC to AI—that you’d love to see simplified? 👉 Drop it in the comments, and I’ll break it down in a future post!

✏️ P.S. I'd love to hear your feedback—What did you think of this explanation? Was it clear, helpful, too detailed, or missing anything? Let me know in the comments—I’m always looking to make these even better for you!

Thanks for reading In 1 Min! Subscribe for free to receive new posts and support my work.

Bazel in 1 Min

Arun Saragadam — Mon, 14 Apr 2025 21:05:02 +0000

What is Bazel?

Bazel is a blazing-fast build and test tool originally developed at Google. It’s designed to handle projects of any size with speed and efficiency.

Why should you use Bazel?

✅ Supports multiple languages (Java, C++, Python, Go, etc.)
🌍 Works cross-platform
🧠 Only runs affected tests after code changes — saves time and compute
🧱 Built to scale with massive codebases
⚡ Parallel builds and tests for faster dev cycles

When does it make sense to adopt Bazel?

When you’re starting a new project
When your existing builds/tests are slow

⚠️ Disclaimer: This is a 1-min overview, not a full deep dive. If you've used Bazel in the real world, I'd love to hear your insights. What’s been great? What’s tricky?

📚 This post is part of in-1-min — dev concepts and tools explained in under a minute.

✍️ By Arun Saragadam • Follow for quick takes on dev tools, workflows, and productivity.

🏠 Explore more posts at dev.to/in-1-min

This article breaks down the fastest way to build web & Android apps using Flutter and Docker. Check it out! 🚀 Have any insights or improvements? Share your thoughts in the comments and contribute to the discussion! 💡🔥 #Flutter #Docker #DevCommunity

Arun Saragadam — Fri, 07 Mar 2025 12:44:17 +0000

Flutter + Docker: The Fastest Way to Build Web & Android Apps

Arun Saragadam ・ Mar 7

#flutter #docker #web #android

Flutter + Docker: The Fastest Way to Build Web & Android Apps

Arun Saragadam — Fri, 07 Mar 2025 01:58:50 +0000

Flutter + Docker: The Fastest Way to Build Web & Android Apps

Whether you're setting up a CI/CD pipeline or onboarding to a new project, reducing complexity is always a win. The Flutter-Docker repository provides a simple way to build and test web (and Android) applications without the hassle of setting up dependencies manually.

Use Case 1: Quickly Onboard to a New Project

When joining a new project, the first thing you want to do is see what it looks like. But setting up the right environment, installing dependencies, and configuring tools can take time. In many cases, you might just need to ask your teammate what software version they are using, and that’s all you need to explore the project. If luck favors you, the latest version might even work out of the box.

Fastest Way to Run a New Project

With this Docker setup, you don’t need to install anything on your system. In just two commands, you can preview the web version of any project. You might just have to ask your teammate what Flutter version they are using, and that’s all you need to explore the project. If luck favors you, the latest Flutter version might even work for you.

Pull the Docker image:

   docker pull ghcr.io/iarunsaragadam/flutter-web-builder:latest

Build the project in a container:

   docker run --rm -v "$PWD":/app -w /app ghcr.io/iarunsaragadam/flutter-web-builder:latest

Serve the built web application using Nginx:

   docker run --rm -v "$PWD"/build/web:/usr/share/nginx/html -p 8080:80 nginx

Now, simply open http://localhost:8080, and you’re instantly running the built web project—without installing any dependencies!

Use Case 2: Streamline Your CI/CD Pipeline

One of the biggest challenges in software deployment is ensuring consistent build environments. Software versions, dependencies, and local configurations can all introduce inconsistencies in the CI/CD process.

How Docker Helps

Reduce Setup Time: No need to manually install dependencies on CI/CD machines.
Ensure Consistency: The Docker image guarantees that the build runs the same way across different environments.
Simplify Commands: With a single Docker command, you can automate the build process.

How to Integrate in CI/CD

To build a web application within a CI/CD pipeline, simply use:

docker run --rm -v "$PWD":/app -w /app ghcr.io/iarunsaragadam/flutter-web-builder:latest flutter build web

For Android builds:

docker run --rm -v "$PWD":/app -w /app ghcr.io/iarunsaragadam/flutter-android-builder:latest flutter build apk

These commands clean the project, fetch dependencies using flutter pub get, and then proceed with the build—ensuring a fully automated and reproducible pipeline.

Sample CI/CD Pipelines (Not Tested)

GitHub Actions Pipeline

name: Flutter Docker Build

on: [push, pull_request]

jobs:
  build:
    runs-on: ubuntu-latest

    steps:
      - name: Checkout code
        uses: actions/checkout@v3

      - name: Build Flutter Web with Docker
        run: |
          docker run --rm -v "$PWD":/app -w /app ghcr.io/iarunsaragadam/flutter-web-builder:latest flutter build web

      - name: Serve Build with Nginx
        run: |
          docker run --rm -v "$PWD"/build/web:/usr/share/nginx/html -p 8080:80 nginx

Azure DevOps Pipeline

trigger:
  - main

pool:
  vmImage: 'ubuntu-latest'

steps:
  - checkout: self

  - script: |
      docker run --rm -v "$(Build.SourcesDirectory)":/app -w /app ghcr.io/iarunsaragadam/flutter-web-builder:latest flutter build web
    displayName: 'Build Flutter Web with Docker'

  - script: |
      docker run --rm -v "$(Build.SourcesDirectory)/build/web":/usr/share/nginx/html -p 8080:80 nginx
    displayName: 'Serve Build with Nginx'

Disclaimer: These pipeline configurations are provided as a starting point and have not been tested. Please modify them as needed for your specific project.

What About iOS?

Unfortunately, iOS builds cannot be done using this Docker-based approach. Apple requires iOS applications to be built and signed on macOS using Xcode. This means that to build iOS applications, you'll need access to a macOS machine or a macOS-based CI/CD service like GitHub Actions (macOS runners) or Codemagic.

Why This Matters

Saves Time: Skip dependency setup and run a new project instantly.
Reduces Errors: Avoid environment-related issues by running builds in a consistent Docker container.
Improves CI/CD Pipelines: Automate and streamline web and Android builds with minimal effort.

Conclusion

Whether you’re automating builds in a CI/CD pipeline or quickly previewing a new project without installing anything, Flutter-Docker is a powerful tool to simplify your workflow. With just a few Docker commands, you can avoid setup headaches and focus on what really matters—building great applications.

How to dockerize an angular application?

Arun Saragadam — Thu, 03 Oct 2024 16:51:08 +0000

Dockerizing your Angular app is simpler than you think. With just a few steps, your application will be up and running inside a Docker container. Let’s walk through the process step by step.

Prerequisites

Before we begin, make sure you have the following:

A basic understanding of how to build and run an Angular application.
Node.js and npm installed on your machine.
Docker installed and running.

Steps to Dockerize Angular

Write a Dockerfile.
Test the Dockerfile.
Celebrate your success!

1. Write a Dockerfile

First things first, let's write a Dockerfile to containerize your Angular app.

Where to place the Dockerfile?

Create a Dockerfile in the root of your Angular project, right where your package.json is located. This ensures that the Docker build process has access to all necessary files in the project.

What to put in the Dockerfile?

Here’s a simple, efficient Dockerfile that builds your Angular app using Node.js and serves it with Nginx:

# Arguments to avoid too many pulls from Docker Hub
ARG NODE_URI
ARG NGINX_URI

# Stage 1: Build Angular App
FROM ${NODE_URI:-node}:lts-alpine3.15 AS builder
WORKDIR /app

# Install Angular CLI globally
RUN npm install -g @angular/cli

# Copy package.json and install dependencies
COPY package.json /app
RUN npm install --legacy-peer-deps

# Copy the entire project and build the Angular app
COPY . /app
RUN npm run build --prod

# Stage 2: Serve Angular App with Nginx
FROM ${NGINX_URI:-nginx}:stable-alpine AS deployer
COPY --from=builder /app/dist/amp /usr/share/nginx/html

# Optionally configure Nginx
COPY nginx.conf /etc/nginx/nginx.conf

Why this Dockerfile?

This Dockerfile uses a multi-stage build approach:

Stage 1 (builder): Uses a Node.js image to install dependencies and build the Angular app.
Stage 2 (deployer): Uses an Nginx image to serve the built app.

2. Test the Dockerfile

Now that you’ve created the Dockerfile, let’s build and run your Docker container.

Step 1: Build the Docker Image

In the root of your Angular project (where the Dockerfile is located), run the following command to build your Docker image:

docker build -t nginx-angular-app .

This command builds the image and tags it as nginx-angular-app.

Step 2: Run the Docker Container

Once the image is built, use this command to run your Angular application in a container:

docker run -d -it -p 80:80/tcp --name angular-app nginx-angular-app:latest

This command does the following:

Runs the container in detached mode (-d) with an interactive terminal (-it).
Maps port 80 on your local machine to port 80 in the container (-p 80:80).
Names the container angular-app.

Step 3: Access Your Application

Open your browser and navigate to http://localhost to see your Angular app up and running in the container!

3. Pat Yourself on the Back 🎉

Congratulations! You just Dockerized an Angular application like a pro.
Grab a coffee or take a short break—you’ve earned it! ☕
If you run into issues, don’t panic. Docker makes debugging easier, and with time, you’ll master it.

Next Steps

Now that you've successfully Dockerized your Angular app, here are a few things you can explore:

Automating the build and deployment process with CI/CD pipelines.
Customizing the Nginx configuration to optimize your app's performance.
Using Docker Compose to manage multi-container applications.

By following these steps, you'll not only learn how to containerize your Angular application but also gain a better understanding of Docker's powerful capabilities. Happy coding!