Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
Akshay 🚀 Profile picture
@akshay_pachaar
Mar 13 • 11 tweets • 3 min read • Read on X
Scrolly
Model Context Protocol (MCP), clearly explained:
MCP is like a USB-C port for your AI applications.

Just as USB-C offers a standardized way to connect devices to various accessories, MCP standardizes how your AI apps connect to different data sources and tools.

Let's dive in! 🚀
At its core, MCP follows a client-server architecture where a host application can connect to multiple servers.

Key components include:

- Host
- Client
- Server

Here's an overview before we dig deep 👇
The Host and Client:

Host: An AI app (Claude desktop, Cursor) that provides an environment for AI interactions, accesses tools and data, and runs the MCP Client.

MCP Client: Operates within the host to enable communication with MCP servers.

Next up, MCP server...👇 Image
The Server

A server exposes specific capabilities and provides access to data.

3 key capabilities:

- Tools: Enable LLMs to perform actions through your server
- Resources: Expose data and content from your servers to LLMs
- Prompts: Create reusable prompt templates and workflowsImage
The Client-Server Communication

Understanding client-server communication is essential for building your own MCP client-server.

Let's begin with this illustration and then break it down step by step... 👇
1️⃣ & 2️⃣: capability exchange

client sends an initialize request to learn server capabilities.

server responds with its capability details.

e.g., a Weather API server provides available `tools` to call API endpoints, `prompts`, and API documentation as `resource`.
3️⃣ Notification

Client then acknowledgment the successful connection and further message exchange continues.

Before we wrap, one more key detail...👇
Unlike traditional APIs, the MCP client-server communication is two-way.

Sampling, if needed, allows servers to leverage clients' AI capabilities (LLM completions or generations) without requiring API keys.

While clients to maintain control over model access and permissions Image
I hope this clarifies what MCP does.

In the future, I'll explore creating custom MCP servers and building hands-on demos around them.

Over to you! What is your take on MCP and its future?
That's a wrap!

If you enjoyed this breakdown:

Follow me → @akshay_pachaar ✔️

Every day, I share insights and tutorials on LLMs, AI Agents, RAGs, and Machine Learning!

• • •

Missing some Tweet in this thread? You can try to force a refresh
　

Keep Current with Akshay 🚀

Akshay 🚀 Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @akshay_pachaar

Akshay 🚀 Profile picture
May 9
Traditional RAG vs. Agentic RAG, clearly explained (with visuals):
Traditional RAG has many issues:

- It retrieves once and generates once. If the context isn't enough, it cannot dynamically search for more info.

- It cannot reason through complex queries.

- The system can't modify its strategy based on the problem.
Agentic RAG attempts to solve this.

The following visual depicts how it differs from traditional RAG.

The core idea is to introduce agentic behaviors at each stage of RAG.
Read 7 tweets
Akshay 🚀 Profile picture
May 5
How LLMs work, clearly explained:
Before diving into LLMs, we must understand conditional probability.

Let's consider a population of 14 individuals:

- Some of them like Tennis 🎾
- Some like Football ⚽️
- A few like both 🎾 ⚽️
- And few like none

Here's how it looks 👇 Image
So what is Conditional probability ⁉️

It's a measure of the probability of an event given that another event has occurred.

If the events are A and B, we denote this as P(A|B).

This reads as "probability of A given B"

Check this illustration 👇 Image
Read 13 tweets
Akshay 🚀 Profile picture
May 4
5 amazing Jupyter Notebook tricks not known to many:
1️⃣ Retrieve a cell's output in Jupyter

If you often forget to assign the results of a Jupyter cell to a variable, you can use the `Out` dictionary to retrieve the output. Image
2️⃣ Enrich the default preview of a DataFrame

Simply printing a DataFrame reveals little about its contents.

Jupyter-DataTables enhances it with:

- sorting
- filtering
- exporting
- pagination
- column data types
- column distribution Image
Read 7 tweets
Akshay 🚀 Profile picture
Apr 30
Let's fine-tune DeepMind's latest Gemma 3 (100% locally):
Before we begin, here's what we'll be doing.

We'll fine-tune our private and locally running Gemma 3.

To do this, we'll use:
- @UnslothAI for efficient fine-tuning.
- @ollama to run it locally.

Let's begin! Image
1) Load the model

We start by loading the Gemma 3 model and its tokenizer using Unsloth: Image
Read 9 tweets
Akshay 🚀 Profile picture
Apr 26
Let's build an MCP-powered multi-agent deep researcher (100% local):
Before we dive in, here's a quick demo of what we're building!

Tech stack:

- @Linkup_platform for deep web research
- @crewAIInc for multi-agent orchestration
- @Ollama to locally server DeepSeek
- @cursor_ai as MCP host

Let's go! 🚀
System overview:

- User submits a query
- Web search agent runs deep web search via Linkup
- Research analyst verifies and deduplicates results
- Technical writer crafts a coherent response with citations

Now, let's dive into the code!
Read 16 tweets
Akshay 🚀 Profile picture
Apr 21
Transformer vs. Mixture of Experts in LLMs, clearly explained (with visuals):
Mixture of Experts (MoE) is a popular architecture that uses different "experts" to improve Transformer models.

The visual below explains how they differ from Transformers.

Let's dive in to learn more about MoE!
Transformer and MoE differ in the decoder block:

- Transformer uses a feed-forward network.
- MoE uses experts, which are feed-forward networks but smaller compared to that in Transformer.

During inference, a subset of experts are selected. This makes inference faster in MoE.
Read 10 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

Send Email!

:(