# Adk Examples > Repo with example code for building various types of agents using Agent Development Kit (ADK) - **Type:** MCP server - **Install:** `agentstack add mcp-neutrollized-adk-examples` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [Neutrollized](https://agentstack.voostack.com/s/neutrollized) - **Installs:** 0 - **Category:** [Integrations](https://agentstack.voostack.com/c/integrations) - **Latest version:** 0.1.0 - **License:** Apache-2.0 - **Upstream author:** [Neutrollized](https://github.com/Neutrollized) - **Source:** https://github.com/Neutrollized/adk-examples - **Website:** https://medium.com/google-cloud/getting-started-with-agent-development-kit-function-tools-3f038ee646ea ## Install ```sh agentstack add mcp-neutrollized-adk-examples ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # Agent Development Kit (ADK) examples Repo with example code for building various types of agents using [ADK](https://google.github.io/adk-docs/) ## Setup - install required Python packages/modules for the example you want to run: `pip install -r requirements.txt` - `.env` file in your agent's folder (Google AI Studio) ``` GOOGLE_GENAI_USE_VERTEXAI=FALSE GOOGLE_API_KEY=a1b2c3yourapikeyherex7y8z9 ``` - `.env` file in your agent's folder (Vertex AI) ``` GOOGLE_GENAI_USE_VERTEXAI=TRUE GOOGLE_CLOUD_PROJECT=myproject-123 GOOGLE_CLOUD_LOCATION=us-central1 ``` **NOTE:** while you can use any location you wish, not all locations supports every Gemini model ## Examples 0. A very basic agent that leverages Google Search as the tool to help the user find answers. If you're new to programming and/or ADK, I suggest you start here :) 1. Simple [Weather and Time agent](./01_weather_time_agent/) that uses [function tools](https://google.github.io/adk-docs/tools/function-tools/) to find latitude & longitude of a given city, country and its weather and time (timezone-adjusted). Uses sub-agents to handle specific tasks, each with its own persona. You can find a short write-up of it on my [Medium](https://medium.com/google-cloud/getting-started-with-agent-development-kit-function-tools-3f038ee646ea). I wrote a follow-up article about [Agent Evaluation](https://medium.com/google-cloud/testing-with-agent-development-kit-agent-evaluations-76a9eec27965) and added the evalset and instructions to for this particular agent example. I then added a [callback function](https://medium.com/google-cloud/developing-with-agent-development-kit-using-callbacks-7a6285139432) to make the agent a little more robust. 2. Model Context Protocol (MCP) example that uses FastMCP and ngrok to host the [MCP server](./02_math_agent_w_fastmcp/mcp_server/) which the [math agent](./02_math_agent_w_fastmcp/) connects to get tools to help it perform basic math (add/subtract/multiply/divide). Read about this on my [Medium](https://medium.com/google-cloud/developing-with-agent-development-kit-featuring-fastmcp-ngrok-807c552b90fd). 3. Another MCP example. This time it is a [travel recommendation agent](./03_travel_rec_agent_w_maps_mcp/) that uses a local Google Maps Platform MCP server (via Stdio) to find attractions and restaurants near a give origin location. In its current form, the directions and travel distance returned can be quite wrong and hence I wouldn't really rely on it for directions. I built my own [Google Maps MCP server (in Python)](https://github.com/Neutrollized/google-maps-mcp-server) that I'll be using going forward in future examples. 4. Simple [Weather agent](./04_weather_agentengine_w_sessions/) that uses function tools and callback functions. The example here also uses [sessions](https://google.github.io/adk-docs/sessions/session/) and [state](https://google.github.io/adk-docs/sessions/state/) store user preferences which get initialized during session creation. The callback function will look for the presence of a particular key in the state and modify the system instructions accordingly (in this case, whether to provide the response in imperial or metric units). 5. I explored the use of safeguard LLMs such as IBM's Granite Guardian, Meta's Llama Guard, and Google's ShieldGemma. I leveraged Ollama to run these models on my local machine to [add guardrails to my basic search agent](./05_guardrails/). You can read my Medium article [here](https://medium.com/@glen.yu/guardrails-with-agent-development-kit-featuring-safeguard-llm-models-6d696198a063). 6. Using a Google Maps MCP server that I wrote and leveraging some newer ADK features for an improved [travel recommendation agent](./06_improved_travel_rec_agent/) and more complete experience for the user. ## Sample Agent demos [](https://www.youtube.com/watch?v=tqddvZ0WdMk) ## Source & license This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [Neutrollized](https://github.com/Neutrollized) - **Source:** [Neutrollized/adk-examples](https://github.com/Neutrollized/adk-examples) - **License:** Apache-2.0 - **Homepage:** https://medium.com/google-cloud/getting-started-with-agent-development-kit-function-tools-3f038ee646ea Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** no - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** yes - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/mcp-neutrollized-adk-examples - Seller: https://agentstack.voostack.com/s/neutrollized - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.