Beginner's Guide to MCP with LangChain and Gemini

MCP (Model Context Protocol) is a standard way for language models to interact with external tools — like web search, calculators, and databases — in a structured, clean manner. It acts like a bridge between the model and its tools, making communication modular and manageable.

Why Use MCP in Agents?

Separates model logic from tool logic
Allows the AI agent to decide how and when to use tools
Keeps your system modular, scalable, and easier to maintain
Works great with agent frameworks like LangChain

In short, MCP makes your AI agent smarter and more capable by letting it access external knowledge and functionalities on demand.

Understanding MCP Through a Project

To see MCP in action, let's look at a practical example: the mcp_langchain_examples GitHub project.

Project Structure

mcp_langchain_examples/
├── server.py      # MCP server with DuckDuckGo search tool
├── client.py      # MCP client that connects to the server
├── prompt.py      # System prompts to guide the AI
├── main.py        # Agent logic with Gemini + MCP tools
└── requirements.txt

Installation & Setup

Prerequisites

Python 3.8+
Google API key for Gemini model

Method 1: Using uv (recommended)

# Install uv
curl -LsSf https://astral.sh/uv/install.sh | sh
 
# Create env & install
uv venv
uv sync

Method 2: Using pip

# Create and activate virtual environment
python -m venv .venv
source .venv/bin/activate  # Windows: .venv\Scripts\activate
 
# Install requirements
pip install -r requirements.txt

Then create a .env file in the root and add your Gemini API key:

GOOGLE_API_KEY=your_api_key_here

How It Works

User Question
     ↓
LangChain Agent (Gemini model)
     ↓
Decides to use MCP tool
     ↓
MCP Client → MCP Server
     ↓
DuckDuckGo Search
     ↓
Results returned to agent
     ↓
Formatted response to user

Example Interaction

Question: Who is the current CEO of OpenAI?
Answer: Based on the latest search, the CEO of OpenAI is Sam Altman.

Conclusion

MCP brings a structured, scalable way to empower your AI agents. By combining LangChain with a capable model like Gemini, you can build smart, flexible, tool-using agents easily. Try out the project and start building your own powerful AI workflows!

Project GitHub Repo · LangChain Docs · Gemini API