Build with MCP Toolbox

Step-by-step tutorials and project guides for building AI agents and workflows with the MCP Toolbox.

  less than a minute  

Now that you understand the core concepts and have your server configured, it is time to put those tools to work in real-world scenarios.

Explore the step-by-step guides below to learn how to integrate your databases with different orchestration frameworks and build capable AI agents:

Python Quickstart (Local)

How to get started running MCP Toolbox locally with Python, PostgreSQL, and Agent Development Kit, LangGraph, LlamaIndex or GoogleGenAI.

JS Quickstart (Local)

How to get started running MCP Toolbox locally with JavaScript, PostgreSQL, and orchestration frameworks such as LangChain, GenkitJS, LlamaIndex and GoogleGenAI.

Go Quickstart (Local)

How to get started running MCP Toolbox locally with Go, PostgreSQL, and orchestration frameworks such as LangChain Go, GenkitGo, Go GenAI and OpenAI Go.

Deploy ADK Agent and MCP Toolbox

How to deploy your ADK Agent to Vertex AI Agent Engine and connect it to an MCP Toolbox deployed on Cloud Run.

Quickstart (MCP)

How to get started running Toolbox locally with MCP Inspector.

Pre- and Post- Processing

Intercept and modify interactions between the agent and its tools either before or after a tool is executed.

Prompts using Gemini CLI

How to get started using Toolbox prompts locally with PostgreSQL and Gemini CLI.

AlloyDB

How to get started with Toolbox using AlloyDB.

BigQuery

How to get started with Toolbox using BigQuery.

Looker

How to get started with Toolbox using Looker.

Neo4j

How to get started with Toolbox using Neo4j.

Snowflake

How to get started running Toolbox with MCP Inspector and Snowflake as the source.



Last modified March 6, 2026: docs: Add Build with MCP Toolbox Section (#2649) (103b2936a4f)