mcpField
G
Google ADK Development Environment

Google ADK Development Environment

Local
github.com/linus-mcmanameyDeveloper Tools0Updated 73w ago

About Google ADK Development Environment

Google ADK Development Environment is a VS Code Dev Container setup for developing Google Agent Development Kit applications with Python. It bundles development tools, Google Cloud SDK, and Python packages, with commands for testing and code checks.

Key features

  1. 01VS Code Dev Container setup
  2. 02Python 3.13 environment
  3. 03Google Cloud SDK included
  4. 04Auto-formatting and pytest setup
  5. 05Commands for linting and checks

Use cases

  1. 01Set up a Google ADK development workspace
  2. 02Run tests and code-quality checks
  3. 03Develop with included Google Cloud libraries

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Google ADK Development Environment

This project is set up with a development container optimized for Google Agent Development Kit (ADK) development using Python 3.13.

🚀 Quick Start

  1. Prerequisites: Make sure you have VS Code with the Dev Containers extension installed
  2. Open in Dev Container: Open this folder in VS Code and click "Reopen in Container" when prompted
  3. Wait for Setup: The container will build and install all dependencies automatically
  4. Start Developing: You're ready to build Google ADK applications!

📦 What's Included

Development Environment
  • Python 3.13 - Latest Python version
  • VS Code Extensions - Python, Pylint, Black, Jupyter, Google Cloud Code, and more
  • Google Cloud SDK - Pre-installed and ready to use
  • Git & GitHub CLI - Version control tools
Python Packages
  • Google Cloud Libraries - Storage, BigQuery, AI Platform, Speech, Vision, etc.
  • Machine Learning - TensorFlow, PyTorch, Transformers, LangChain
  • Web Frameworks - FastAPI, Flask, with async support
  • Development Tools - pytest, ruff, black, mypy, pre-commit
  • Data Processing - pandas, numpy, matplotlib, plotly
Features
  • Port Forwarding - Common development ports (3000, 5000, 8000, 8080, 9000)
  • Custom Aliases - Helpful shortcuts for ADK development
  • Auto-formatting - Code formatting on save
  • Testing Setup - pytest configuration
  • Jupyter Support - For interactive development

🔧 Configuration

Google Cloud Setup
  1. Copy .env.example to .env and configure your settings
  2. Run adk-setup to authenticate with Google Cloud
  3. Set your project ID: gcloud config set project YOUR_PROJECT_ID
Useful Commands
  • adk-setup - Setup Google Cloud authentication
  • adk-test - Run tests
  • adk-format - Format code with black and fix with ruff
  • adk-lint - Run ruff linter
  • adk-check - Run full code quality check (ruff + mypy + pytest)

📁 Project Structure

.devcontainer/
├── devcontainer.json    # Dev container configuration
├── Dockerfile          # Container image definition
└── bashrc              # Custom bash configuration

requirements.txt         # Python dependencies
.env.example            # Environment variables template

🔍 Development Tips

  1. Package Management: This setup uses uv for fast Python package installation
  2. Code Quality: Pre-commit hooks are automatically installed with ruff, black, and mypy
  3. Authentication: Use gcloud auth application-default login for local development
  4. Environment Variables: Copy .env.example to .env and customize
  5. Testing: Place tests in a tests/ directory and run with adk-test
  6. Linting: Use adk-lint for ruff linting or adk-check for comprehensive checks

📚 Additional Resources

Happy coding! 🎉

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.