://img.shields.io/badge/CometML-Opik-FF6F00?logo=comet&logoColor=white" alt="Opik / CometML">

This project demonstrates the creation of an AI Agent using the Google Agent Development Kit (ADK), OpenAI's GPT-4o model, the Google Maps MCP Server, and Opik for observability with Comet.ml. The primary goal of this project is to deepen my understanding of Agent Development principles, the application of the Model Context Protocol in practice, and how to integrate its tools and services into an AI Agent for enhanced abilities beyond the training data. This project is largely inspired by Santiago Valdarrama's tutorial on YouTube: * **Video:** [Building AI Agents with Google's Agent Development Kit (ADK)](https://www.youtube.com/watch?v=lstUnckxfs0) * **Repo:** [svpino/google-adk-sample](https://github.com/svpino/google-adk-sample) ## Table of Contents - [Key Technologies](#key-technologies) * [Google Agent Development Kit (ADK)](#google-agent-development-kit-adk) * [Opik & CometML](#opik--cometml) * [Model Context Protocol (MCP)](#model-context-protocol-mcp) * [Google Maps MCP Server](#google-maps-mcp-server) - [Project Structure](#project-structure) - [Project Setup and Installation](#project-setup-and-installation) * [Prerequisites](#prerequisites) * [Installation Steps](#installation-steps) * [Environment Variables](#environment-variables) * [Running the Agent](#running-the-agent) - [Screenshots & Usage](#screenshots--usage) * [ADK Web UI](#adk-web-ui) * [Agent Using Tools (Directions)](#agent-using-tools) * [Conversation Events & Tool Graph](#conversation-events--tool-invocation) * [Opik (CometML) Tracing](#opik-cometml-tracing) - [Code Deep Dive (`agent.py`)](#code-deep-dive-agentpy) * [Imports and Setup](#imports-and-setup) * [Agent Definition](#agent-definition) * [MCP Toolset Configuration](#mcp-toolset-configuration) * [Opik Tracing Callbacks](#opik-tracing-callbacks) - [Video Demonstration](#video-demonstration) - [Author](#author) - [License](#license) ## Key Technologies ### Google Agent Development Kit (ADK) ![ADK logo](assets/screenshots/adk.png) The [Google Agent Development Kit (ADK)](https://google.github.io/adk-docs/) is a Python framework designed to simplify the development of AI Agents powered by LLMs. It provides access to tools, memory, agent orchestration and LLMs from providers like OpenAI, Anthropic, Cohere and many others through integration with the `LiteLlm` library. The ADK also includes a web UI for interacting with and debugging agents. ### Opik & CometML [Opik](https://github.com/comet-ml/opik) is an open-source observability solution for LLM applications, built by Comet. It allows you to trace, visualize, and debug the interactions within your AI Agents, including LLM calls, tool usage, and other operations. In this project, Opik is configured to send traces to [CometML](https://www.comet.com/), providing a rich UI to inspect agent behavior. ### Model Context Protocol (MCP) ![MCP](assets/screenshots/mcp.png) The [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction) is an open protocol that standardizes how applications provide context to LLMs and connect them to different data sources and tools. It defines a schema for tool descriptions, invocations, and responses. This allows for interoperability between different LLM systems and tool providers. ### Google Maps MCP Server The [Google Maps MCP Server](https://apidog.com/blog/google-maps-mcp-server/) is a Node.js application that exposes Google Maps Platform APIs as MCP tools. This allows an ADK Agent to easily leverage Google Maps features to deliver more relevant, context-aware responses. *

#google-maps-api

MCP AI Agent with Google ADK, Google Maps, and Opik