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

Name: MCP AI Agent with Google ADK, Google Maps, and Opik
Author: luuisotorres

@luuisotorres

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

AI Agent built with Google ADK that leverages Google Maps MCP Server to answer real-world location questions with tool usage and traceable execution via Opik.

#python #mcp #artificial-intelligence #openai #google-maps-api #ai-agents #opik #comet-ml #ai-agent #llm-agent #llm-tools #gpt-4o #model-context-protocol #mcp-server #model-context-protocol-servers #adk-python

基本信息

分类

AI 与智能体

许可证

MIT

运行时

python

传输方式

stdio

发布者

luuisotorres

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "mcp-ai-agent": {
      "command": "uv",
      "args": [
        "venv",
        "#",
        "Create",
        "a",
        "virtual",
        "environment",
        "(e.g.,",
        ".venv)"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is MCP AI Agent with Google ADK, Google Maps, and Opik?

This project demonstrates how to build 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 CometML. It is designed for developers who want to learn agent development principles and see the Model Context Protocol (MCP) applied in practice.

How to use MCP AI Agent with Google ADK, Google Maps, and Opik?

Clone the repository, create a virtual environment with uv, install dependencies, and copy .env.example to .env with your API keys. Then run uv run adk web to start the ADK web UI at http://127.0.0.1:8000, where you can interact with the agent. The Google Maps MCP Server is started automatically via npx when needed.

Key features of MCP AI Agent with Google ADK, Google Maps, and Opik

Built with Google Agent Development Kit (ADK)
Uses OpenAI’s GPT‑4o model via LiteLLM
Integrates Google Maps MCP Server for location tools
Exposes seven Google Maps tools (directions, geocode, etc.)
Traces all agent interactions with Opik in CometML
Provides a web UI for debugging and conversation inspection

Use cases of MCP AI Agent with Google ADK, Google Maps, and Opik

Get turn‑by‑turn driving, walking, or cycling directions
Convert addresses to geographic coordinates and vice versa
Retrieve elevation data for given coordinates
Search for places (restaurants, landmarks) and get details
Calculate travel time and distance between multiple points

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

What are the prerequisites to run this project?

Python 3.11, uv (Python package manager), Node.js and npm/npx (to run the Google Maps MCP Server), and API keys for Google Maps Platform, OpenAI, and CometML.

How does the Google Maps MCP server start?

The ADK’s MCPToolset is configured to automatically start the server via npx when the agent needs to use its tools, so no manual startup is required.

Which Google Maps tools are available to the agent?

The agent can use: maps_directions, maps_geocode, maps_reverse_geocode, maps_elevation, maps_search_places, maps_place_details, and maps_distance_matrix.

Where are agent traces stored?

Traces are sent to CometML using the Opik observability library, which provides a rich UI to inspect LLM calls, tool usage, and overall agent behavior.

What AI model does the agent use?

The agent uses OpenAI’s GPT‑4o model, accessed through the LiteLLM integration within the Google ADK.

AI 与智能体分类下的更多 MCP 服务器

Gemini MCP Server

aliargun

MCP server implementation for Google's Gemini API

259

Model Context Protocol for Unreal Engine

chongdashu

Enable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).

2.0K