MCP Llama3 Flight Search Client

A client for the MCP Flight Search service using Ollama and Llama 3.2 to provide a user-friendly flight search interface with Model Context Protocol tools.

Description

This client application provides a user-friendly interface to interact with the Model Context Protocol (MCP) flight search service. It allows users to search for flights between airports with specified dates.

About

A client for the MCP Flight Search service using Ollama and Llama 3.2 to provide a user-friendly flight search interface with Model Context Protocol tools

github.com/arjunprabhulal/mcp-llama3-client

Files

mcp_flight_client.py: Main client implementation for interacting with the MCP Flight Search service
prompt_templates.py: Contains prompt templates for generating flight search queries

Installation

Install the required packages for this client:

pip install -r requirements.txt

Required packages:

llama-index
llama-index-llms-ollama
llama-index-tools-mcp
langchain-community

Installing Ollama

This client uses Ollama to run Llama 3.2 locally. To install Ollama:

ollama pull llama3.2

Prerequisites

You need to have the MCP Flight Search service running.

Installing the MCP Flight Search Package

# Install from PyPI
pip install mcp-flight-search

Starting the MCP Server

You can start the MCP server using one of the following methods:

Starting the MCP Server

# Using the command-line entry point
mcp-flight-search --connection_type http

# Or using the Python module approach
python -m mcp_flight_search.server --connection_type http

Usage

python mcp_flight_client.py

Architecture

+------------------------------+      HTTP      +------------------------------+
|                              | <------------> |                              |
|  MCP Llama3 Flight Search    |                |  MCP Flight Search Server    |
|  Client (This Repository)    |                |  (Backend Service)           |
|                              |                |                              |
|  - mcp_flight_client.py      |                |  - search_flights_tool       |
|  - prompt_templates.py       |                |  - server_status             |
|                              |                |                              |
|  Uses:                       |                |  Uses:                       |
|  - llama-index               |                |  - Model Context Protocol    |
|  - llama-index-llms-ollama   |                |  - SerpAPI for Google        |
|    (with Llama 3.2)          |                |    Flights data              |
|  - llama-index-tools-mcp     |                |                              |
|  - langchain-community       |                |                              |
+------------------------------+                +------------------------------+
              |                                               |
              |                                               |
              v                                               v
+------------------------------+                +------------------------------+
|                              |                |                              |
|  Ollama (Local LLM)          |                |  Flight Search               |
|  Running Llama 3.2           |                |  APIs                        |
|                              |                |                              |
+------------------------------+                +------------------------------+
              |
              |
              v
+------------------------------+
|                              |
|  User Interface              |
|                              |
+------------------------------+

This architecture shows how the MCP Llama3 Flight Search Client connects to the MCP Flight Search Server over HTTP. The client uses various libraries to interact with the server, which in turn uses the Model Context Protocol (MCP) to provide flight search functionality through tools like search_flights_tool.

The client leverages Ollama to run Llama 3.2 locally, providing powerful language model capabilities while maintaining privacy and reducing dependency on cloud services.

Author

For more articles on AI/ML and Generative AI, follow me on Medium: https://medium.com/@arjun-prabhulal

License

This project is licensed under the MIT License

Categories

Current Category: llama-index

mcp-flight-search-client

mcp-llama3-client