MCP Client
by dev-mahfuj80
This project demonstrates a simple client-server implementation using the Model Context Protocol (MCP). It showcases how to connect large language models with tools and data in a standardized way.
Last updated: N/A
What is MCP Client?
This is an example client-server implementation using the Model Context Protocol (MCP). It demonstrates how to create an MCP server with custom tools and connect to it using an MCP client, enabling interaction between large language models and external resources.
How to use MCP Client?
To use this client, you need Python 3.9+ and uv. Install the dependencies using uv install -e . and then run the client script uv run src/client/mcp_client.py. The client connects to the server, lists available tools, and calls the BMI calculator and weather tool with sample data.
Key features of MCP Client
MCP Implementation
Custom Tool Integration
Client-Server Communication
BMI Calculator Tool
Weather Data Retrieval Tool
Use cases of MCP Client
Connecting LLMs to external APIs
Creating custom tools for LLMs
Standardized interaction with LLMs
Demonstrating MCP usage
Testing LLM tool interactions
FAQ from MCP Client
What is MCP?
What is MCP?
MCP stands for Model Context Protocol, a standardized way to connect large language models with tools and data.
What are the prerequisites for running this example?
What are the prerequisites for running this example?
You need Python 3.9+ and uv (Python package manager).
How do I install the dependencies?
How do I install the dependencies?
Run uv install -e . in the project directory.
How do I start the client?
How do I start the client?
Run uv run src/client/mcp_client.py to start the client, which will automatically start the server.
What tools are available on the server?
What tools are available on the server?
The server exposes two tools: calculate_bmi and fetch_weather.