OpenAI Gemini Llama Example
Createdphilschmid
Demonstrates building an AI agent using the Model Context Protocol (MCP) with open LLMs like Meta Llama 3, OpenAI, or Google Gemini, and a SQLite database.
About
This repository provides a basic example of constructing an AI agent leveraging the Model Context Protocol (MCP) in conjunction with open LLMs, specifically Meta Llama 3, OpenAI, and Google Gemini, along with a SQLite database. It serves as a straightforward, educational illustration focused on connecting to an MCP server, loading and utilizing tools and resources, transforming tools into LLM-compatible function calls, and interacting with an LLM via the `openai` or `google-genai` SDK. The code sets up a simple CLI agent to interact with a SQLite database through an MCP server.
Key Features
- Connects to an MCP server
- Loads and uses tools and resources from the MCP server
- Converts tools into LLM-compatible function calls
- Interacts with an LLM using the `openai` SDK or `google-genai` SDK
- Includes examples for Llama 3 and Gemini models
- 145 GitHub stars
Use Cases
- Building AI agents that interact with databases
- Demonstrating the use of MCP with various LLMs
- Educational purposes for understanding MCP implementation