Steps

1 Setup an API key for Google Maps in Argolis

2 Clone the gitlab repo

3 Setup the virtual env

cd talk-building-your-own-mcp-server
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

4 Create a .env file within each of the agent subdirectories

The .env file should have the following entries -

GOOGLE_GENAI_USE_VERTEXAI=TRUE GOOGLE_CLOUD_PROJECT=<Your Project Name> GOOGLE_CLOUD_LOCATION=us-central1

5 Create a .env file within each of the mcp subdirectories

The .env file should have the following entries -

GOOGLE_MAPS_API_KEY=<Your API Key>

4 Running the agent

Make sure to auth with gcloud auth application-default login
Run cd agent
Run adk web

5 Running the MCP Server

Change path cd mcpserver
Run python google_maps_server.py

6 Run the MCP Inspector

Make sure you have node installed - [https://nodejs.org/en/download/]
Run npx @modelcontextprotocol/inspector
Connect to your MCP Server over 'HTTP' using the MCP Serer URL - which is usually :/mcp

This server cannot be installed

-

security - not tested

F

license - not found

-

quality - not tested

How are these scores calculated?

Enables interaction with Google Maps services through the Model Context Protocol. Provides location-based functionality and mapping capabilities for AI agents.

Google Maps MCP Server