Thread by @akshay_pachaar

Let's build an MCP server (100% local):

Before diving in, here's what we'll be doing today:

- Understand MCP with a simple analogy.
- Build a 100% local and secure MCP client using @mcpuse
- Integrate the client with @Stagehanddev MCP sever
- Use this setup for control and automate browser

Let's go! 🚀

First, let's understand MCP using a translation analogy.

Imagine you only know English. To get info from a person who only knows:

- French, you must learn French.
- German, you must learn German.
- and so on.

Learning even 5 languages will be a nightmare for you!

But what if you find a translator?

- You talk to the translator.
- It infers the info you want.
- It picks the person to talk to.
- It gets you a response.

The translator is like an MCP!

It lets you (Agents) talk to other people (tools) through a single interface.

The client-server architecture:

Host (Agent/IDE) runs the MCP Client to communicate with MCP Servers.

Servers expose tools that can perform various actions.

This architecture enables secure and standardized AI tool integration.

Check this out👇

With this understanding in mind, let's start building our own MCP servers and clients...👇

1️⃣ Build a simple MCP server

First, we create a simple MCP server using FastMCP with a tool that adds two numbers.

Then create a configuration file that tells any client how to connect to this server.

Create these files as shown below👇

2️⃣ Create MCP Client

Next, we build a client using mcp-use, powered by locally running LLMs.

It's completely secure and can run on your machine.

Afterward, we'll wrap up this client in a user-friendly Streamlit UI for ease of use.

Check this out 👇

Let's integrate the MCP client and server we just created.

Here's the Streamlit UI I mentioned earlier.

For didactic purposes, we're starting with a very simple server.

Check this out👇

Now, let's make this more practical. We're going to build a browser automation MCP server using Stagehand.

With this, we can navigate websites, click buttons, fill out forms, and extract data using natural language commands.

Check this out👇

Next, let's interact with Stagehand MCP server.

When asked to find the cheapest flight from one city to another:
- It navigated to Google.
- Typed in the query.
- Scraped the relevant information.
- Returned the results to the agent to generate a response.

See this video👇

Why mcp-use?

You can connect any LLMs to MCP servers & create local MCP clients easily with mcp-use.

- Compatible with Ollama & LangChain
- Stream Agent output async
- Built-in debugging mode, etc

Repo:

(don't forget to star ⭐)github.com/mcp-use/mcp-use

To summarise here's what we covered:

- What is MCP
- How to build your own MCP Server
- How to build a 100% local MCP Client
- Fully automate and control a browser

I'll leave you with this great website to explore more MCP servers...👇

That's a wrap!

If you found it insightful, reshare with your network.

Find me → @akshay_pachaar ✔️
For more insights and tutorials on LLMs, AI Agents, and Machine Learning!

https://twitter.com/703601972/status/1958875808430530738