Database as a Tool: Agentic RAG with ADK, MCP Toolbox, and Cloud SQL

1. Introduction

AI agents are only as useful as the data they can access. Most real-world data lives in databases — and connecting agents to databases typically means writing connection management, query logic, and embedding pipelines inside your agent code. Every agent that needs database access repeats this work, and every query change requires redeploying the agent.

This codelab shows a different approach. You declare your database tools in a YAML file — standard SQL queries, vector similarity search, even automatic embedding generation — and MCP Toolbox for Databases handles all database operations as an MCP server. Your agent code stays minimal: load the tools, let Gemini decide which one to call.

What you'll build

A Restaurant Concierge for "Foodie Finds" — an ADK agent powered by Gemini that helps diners browse a restaurant's menu using standard filters (category, cuisine type) and discover dishes through natural language descriptions like "I want something spicy and vegetarian." The agent reads from and writes to a Cloud SQL PostgreSQL database entirely through MCP Toolbox for Databases, which handles all database access — including automatic embedding generation for vector search. By the end, both the Toolbox and the agent run on Cloud Run.

What you'll learn

How MCP (Model Context Protocol) standardizes tool access for AI agents, and how MCP Toolbox for Databases applies this to database operations
Set up MCP Toolbox for Databases as middleware between an ADK agent and Cloud SQL PostgreSQL
Define database tools declaratively in tools.yaml — no database code in your agent
Build an ADK agent that loads tools from a running Toolbox server using ToolboxToolset
Generate vector embeddings using Cloud SQL's built-in embedding() function and enable semantic search with pgvector
Use the valueFromParam feature for automatic vector ingestion on write operations
Deploy both the Toolbox server and the ADK agent to Cloud Run

Prerequisites

A Google Cloud account with a trial billing account
Basic familiarity with Python and SQL
Prior experience with Cloud Database and ADK will be helpful

2. Set Up Your Environment

This step prepares your Cloud Shell environment, configures your Google Cloud project, and clones the reference repository.

Open Cloud Shell

Open Cloud Shell in your browser. Cloud Shell provides a pre-configured environment with all the tools you need for this codelab. Click Authorize when prompted to

Then click "View" -> "Terminal" to open the terminal.Your interface should look similar to this

This will be our main interface, IDE on top, terminal on the bottom

Set up your working directory

Create your working directory. All code you write in this codelab lives here:

mkdir -p ~/build-agent-adk-toolbox-cloudsql
cloudshell workspace ~/build-agent-adk-toolbox-cloudsql && cd ~/build-agent-adk-toolbox-cloudsql

After that, let's prepare several directories to manage things like seeding scripts and logs

mkdir -p ~/build-agent-adk-toolbox-cloudsql/scripts
mkdir -p ~/build-agent-adk-toolbox-cloudsql/logs

Set up your Google Cloud project

Create the .env file with the location variables:

# For Vertex AI / Gemini API calls
echo "GOOGLE_CLOUD_LOCATION=global" > .env
# For Cloud SQL, Cloud Run, Artifact Registry
echo "REGION=us-central1" >> .env

To simplify project setup in your terminal, download this project setup script into your working directory:

curl -sL https://raw.githubusercontent.com/alphinside/cloud-trial-project-setup/main/setup_verify_trial_project.sh -o setup_verify_trial_project.sh

Run the script. It verifies your trial billing account, creates a new project (or validates an existing one), saves your project ID to a .env file in the current directory, and sets the active project in gcloud.

bash setup_verify_trial_project.sh && source .env

The script will:

Verify you have an active trial billing account
Check for an existing project in .env (if any)
Create a new project or reuse the existing one
Link the trial billing account to your project
Save the project ID to .env
Set the project as the active gcloud project

Verify the project is set correctly by checking the yellow text next to your working directory in the Cloud Shell terminal prompt. It should display your project ID.

Activate Required API

Next, we need to enable several API for the product that we will be interacting with:

gcloud services enable \
  aiplatform.googleapis.com \
  sqladmin.googleapis.com \
  compute.googleapis.com \
  run.googleapis.com \
  cloudbuild.googleapis.com \
  artifactregistry.googleapis.com

Vertex AI API (aiplatform.googleapis.com) — your agent uses Gemini models, and Toolbox uses the embedding API for vector search.
Cloud SQL Admin API (sqladmin.googleapis.com) — you provision and manage a PostgreSQL instance.
Compute Engine API (compute.googleapis.com) — required for creating Cloud SQL instances.
Cloud Run, Cloud Build, Artifact Registry — used in the deployment step later in this codelab

3. Preparing Scripts for Database Initialization

This step starts Cloud SQL instance creation and runs an automated setup script that waits for the instance to be ready, then creates the database, seeds it with job listings, and generates embeddings — all in one operation.

First, let's add the database password to your .env file and reload it:

echo "DB_PASSWORD=restaurant-pwd" >> .env
echo "DB_INSTANCE=restaurant-instance" >> .env
echo "DB_NAME=restaurant_db" >> .env
source .env

Creating Bash script for instance and database creation

Then, create the scripts/setup_database.sh script with the following command

mkdir -p ~/build-agent-adk-toolbox-cloudsql/scripts
cloudshell edit scripts/setup_database.sh

Then, copy the following code into the scripts/setup_database.sh file

#!/bin/bash
set -e
source .env

echo "================================================"
echo "Database Setup"
echo "================================================"
echo ""

# Step 1: Create Cloud SQL instance
echo "[1/5] Creating Cloud SQL instance..."

# Check if instance already exists
if gcloud sql instances describe "$DB_INSTANCE" --quiet >/dev/null 2>&1; then
    echo "      Instance already exists"
else
    echo "      Creating instance (takes 5-10 minutes)..."
    gcloud sql instances create "$DB_INSTANCE" \
        --database-version=POSTGRES_17 \
        --tier=db-custom-1-3840 \
        --edition=ENTERPRISE \
        --region="$REGION" \
        --root-password="$DB_PASSWORD" \
        --enable-google-ml-integration \
        --database-flags cloudsql.enable_google_ml_integration=on \
        --quiet
fi
echo "      ✓ Instance ready"
echo ""

# Step 2: Verify instance is ready
echo "[2/5] Verifying instance state..."

STATE=$(gcloud sql instances describe "$DB_INSTANCE" --format='value(state)')

if [ "$STATE" != "RUNNABLE" ]; then
    echo "ERROR: Instance not ready (state: $STATE)"
    exit 1
fi
echo "      ✓ Instance is RUNNABLE"
echo ""

# Step 3: Grant IAM permissions
echo "[3/5] Granting Vertex AI permissions..."

SERVICE_ACCOUNT=$(gcloud sql instances describe "$DB_INSTANCE" \
    --format='value(serviceAccountEmailAddress)')

if [ -z "$SERVICE_ACCOUNT" ]; then
    echo "ERROR: Could not retrieve service account"
    exit 1
fi

gcloud projects add-iam-policy-binding "$GOOGLE_CLOUD_PROJECT" \
    --member="serviceAccount:$SERVICE_ACCOUNT" \
    --role="roles/aiplatform.user" \
    --quiet

echo "      ✓ Permissions granted"
echo ""

# Step 4: Create database
echo "[4/5] Creating database..."

# Check if database already exists
if gcloud sql databases describe "$DB_NAME" \
    --instance="$DB_INSTANCE" --quiet >/dev/null 2>&1; then
    echo "      Database already exists"
else
    gcloud sql databases create "$DB_NAME" \
        --instance="$DB_INSTANCE" \
        --quiet
fi

echo "      ✓ Database '$DB_NAME' ready"
echo ""

# Step 5: Seed database and generate embeddings
echo "[5/5] Seeding database and generating embeddings..."

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
SETUP_SCRIPT="${SCRIPT_DIR}/setup_restaurant_db.py"

if [ ! -f "$SETUP_SCRIPT" ]; then
    echo "ERROR: Setup script not found: $SETUP_SCRIPT"
    exit 1
fi

uv run "$SETUP_SCRIPT"

echo ""
echo "================================================"
echo "Setup complete!"
echo "================================================"
echo ""

Creating Python script for data seed

After that, create the seeding script python file scripts/setup_restaurant_db.py using the command below

cloudshell edit scripts/setup_restaurant_db.py

Then, copy the following code into scripts/setup_restaurant_db.py file

import os
import sys
from pathlib import Path
from dotenv import load_dotenv
from google.cloud.sql.connector import Connector
import pg8000
import time

# Load environment variables from .env file
env_path = Path(__file__).parent.parent / '.env'
load_dotenv(env_path)
EMBEDDING_MODEL='gemini-embedding-001'

# Verify required environment variables
required_vars = ['GOOGLE_CLOUD_PROJECT', 'REGION', 'DB_PASSWORD']
missing_vars = [var for var in required_vars if not os.environ.get(var)]

if missing_vars:
    print(f"ERROR: Missing required environment variables: {', '.join(missing_vars)}", file=sys.stderr)
    print(f"", file=sys.stderr)
    print(f"Expected .env file location: {env_path}", file=sys.stderr)
    if not env_path.exists():
        print(f"✗ File not found at that location", file=sys.stderr)
    else:
        print(f"✓ File exists but is missing the variables above", file=sys.stderr)
    print(f"", file=sys.stderr)
    print(f"Make sure your .env file contains:", file=sys.stderr)
    for var in missing_vars:
        print(f"  {var}=<value>", file=sys.stderr)
    sys.exit(1)

# Menu items data
MENU_ITEMS = [
    ("Truffle Mushroom Risotto", "Italian", "Main Course",
     "Arborio rice, truffle oil, porcini mushrooms, parmesan, white wine",
     "$28", "Vegetarian, Gluten-Free", True,
     "A creamy, luxurious risotto made with arborio rice slow-cooked in white wine and mushroom broth, finished with shaved black truffle and aged parmesan. The porcini mushrooms add a deep, earthy flavor that pairs beautifully with the delicate truffle oil drizzled on top."),
    ("Spicy Tuna Tartare", "Japanese", "Appetizer",
     "Ahi tuna, sriracha, sesame oil, avocado, crispy wonton",
     "$22", "Gluten-Free, Dairy-Free", True,
     "Fresh ahi tuna diced and tossed with sriracha aioli, toasted sesame oil, and lime juice, served atop creamy avocado slices with crispy wonton chips. A perfect balance of heat, richness, and crunch inspired by modern Japanese fusion cuisine."),
    ("Lamb Kofta Kebab", "Middle Eastern", "Main Course",
     "Ground lamb, cumin, coriander, yogurt sauce, flatbread",
     "$24", "Halal", True,
     "Hand-formed spiced lamb kebabs grilled over charcoal, seasoned with cumin, coriander, and sumac. Served with warm flatbread, tangy yogurt-cucumber sauce, and a fresh herb salad. A classic Middle Eastern street food elevated with premium ingredients."),
    ("Pad Thai", "Thai", "Main Course",
     "Rice noodles, shrimp, tamarind, peanuts, bean sprouts, lime",
     "$19", "Gluten-Free, Dairy-Free", True,
     "Stir-fried rice noodles with tiger shrimp, scrambled egg, and a sweet-sour tamarind sauce, topped with crushed peanuts, fresh bean sprouts, and a squeeze of lime. This classic Thai street food dish balances sweet, sour, salty, and umami in every bite."),
    ("Margherita Pizza", "Italian", "Main Course",
     "San Marzano tomatoes, fresh mozzarella, basil, olive oil",
     "$18", "Vegetarian", True,
     "A Neapolitan-style pizza with a thin, charred crust topped with crushed San Marzano tomatoes, creamy buffalo mozzarella, fresh basil leaves, and a drizzle of extra virgin olive oil. Simple, classic, and made with imported Italian ingredients."),
    ("Miso Glazed Black Cod", "Japanese", "Main Course",
     "Black cod, white miso, mirin, sake, pickled ginger",
     "$36", "Gluten-Free, Dairy-Free", True,
     "Buttery black cod marinated for 72 hours in a sweet white miso glaze with mirin and sake, then broiled until caramelized. Served with pickled ginger and steamed bok choy. A signature dish inspired by Nobu's iconic preparation."),
    ("Caesar Salad", "American", "Appetizer",
     "Romaine lettuce, parmesan, croutons, anchovy dressing",
     "$14", "Contains Gluten", True,
     "Crisp romaine hearts tossed with a house-made anchovy-garlic dressing, shaved parmesan, and golden sourdough croutons. A timeless salad that serves as the perfect light starter or side dish with grilled proteins."),
    ("Chicken Tikka Masala", "Indian", "Main Course",
     "Chicken thigh, tomato cream sauce, garam masala, basmati rice",
     "$21", "Gluten-Free", True,
     "Tender chunks of tandoori-marinated chicken simmered in a rich, creamy tomato sauce spiced with garam masala, cumin, and fenugreek. Served over fragrant basmati rice with warm garlic naan on the side."),
    ("Chocolate Lava Cake", "French", "Dessert",
     "Dark chocolate, butter, eggs, vanilla, powdered sugar",
     "$15", "Vegetarian", True,
     "A warm, individual-sized chocolate cake with a molten dark chocolate center that flows when you break through the delicate outer shell. Made with 70% Belgian dark chocolate and served with a scoop of vanilla bean ice cream."),
    ("Pho Bo", "Vietnamese", "Main Course",
     "Rice noodles, beef brisket, star anise, cinnamon, bean sprouts, Thai basil",
     "$17", "Gluten-Free, Dairy-Free", True,
     "A deeply aromatic beef broth simmered for 12 hours with star anise, cinnamon, and charred ginger, ladled over rice noodles and thinly sliced beef brisket. Served with fresh Thai basil, bean sprouts, jalapeño, and lime for the table to customize."),
    ("Lobster Bisque", "French", "Appetizer",
     "Lobster, heavy cream, cognac, tarragon, cayenne",
     "$19", "Gluten-Free", True,
     "A velvety smooth soup made from roasted lobster shells, finished with heavy cream, a splash of cognac, and fresh tarragon. Each bowl is garnished with tender lobster meat and a pinch of cayenne for subtle warmth."),
    ("Falafel Plate", "Middle Eastern", "Main Course",
     "Chickpeas, herbs, tahini, pickled vegetables, hummus",
     "$16", "Vegan, Gluten-Free", True,
     "Crispy-on-the-outside, fluffy-on-the-inside chickpea fritters seasoned with fresh parsley, cilantro, and cumin. Served with creamy tahini sauce, house-made hummus, pickled turnips, and warm pita bread."),
    ("Crème Brûlée", "French", "Dessert",
     "Heavy cream, vanilla bean, egg yolks, caramelized sugar",
     "$13", "Vegetarian, Gluten-Free", True,
     "A classic French custard made with Madagascar vanilla bean and farm-fresh egg yolks, topped with a perfectly torched layer of caramelized sugar that cracks with a satisfying snap. Rich, creamy, and elegantly simple."),
    ("Korean BBQ Short Ribs", "Korean", "Main Course",
     "Beef short ribs, soy sauce, sesame, garlic, pear marinade",
     "$32", "Dairy-Free", False,
     "Premium beef short ribs marinated overnight in a sweet and savory blend of soy sauce, Asian pear, garlic, and toasted sesame. Grilled tableside over charcoal and served with lettuce wraps, pickled daikon, and gochujang dipping sauce."),
    ("Tiramisu", "Italian", "Dessert",
     "Mascarpone, espresso, ladyfingers, cocoa, Marsala wine",
     "$14", "Vegetarian, Contains Gluten", True,
     "Layers of espresso-soaked ladyfingers and whipped mascarpone cream flavored with Marsala wine, dusted with premium Dutch cocoa powder. Made fresh daily and chilled for 24 hours to develop rich, complex flavors."),
]


def get_connection():
    """Create a connection to Cloud SQL using the connector."""
    project = os.environ['GOOGLE_CLOUD_PROJECT']
    region = os.environ['REGION']
    password = os.environ['DB_PASSWORD']
    instance = os.environ['DB_INSTANCE']
    database = os.environ['DB_NAME']

    connector = Connector()
    conn = connector.connect(
        f"{project}:{region}:{instance}",
        "pg8000",
        user="postgres",
        password=password,
        db=database
    )
    return conn, connector


def create_schema(cursor):
    """Create extensions and menu_items table."""
    cursor.execute("CREATE EXTENSION IF NOT EXISTS google_ml_integration")
    cursor.execute("CREATE EXTENSION IF NOT EXISTS vector")
    cursor.execute("""
        CREATE TABLE IF NOT EXISTS menu_items (
            id SERIAL PRIMARY KEY,
            name VARCHAR NOT NULL,
            cuisine_type VARCHAR NOT NULL,
            category VARCHAR NOT NULL,
            ingredients VARCHAR NOT NULL,
            price VARCHAR NOT NULL,
            dietary_tags VARCHAR NOT NULL,
            available BOOLEAN NOT NULL DEFAULT TRUE,
            description TEXT NOT NULL,
            description_embedding vector(3072)
        )
    """)


def seed_menu_items(cursor, conn):
    """Insert menu items."""
    cursor.execute("SELECT COUNT(*) FROM menu_items")
    existing_count = cursor.fetchone()[0]

    if existing_count > 0:
        print(f"      {existing_count} menu items already exist, skipping seed")
        return 0

    cursor.executemany("""
        INSERT INTO menu_items (name, cuisine_type, category, ingredients, price, dietary_tags, available, description)
        VALUES (%s, %s, %s, %s, %s, %s, %s, %s)
    """, MENU_ITEMS)
    conn.commit()
    return len(MENU_ITEMS)


def generate_embeddings(cursor, conn):
    """Generate embeddings using Cloud SQL's embedding() function."""
    cursor.execute("SELECT COUNT(*) FROM menu_items WHERE description_embedding IS NULL")
    null_count = cursor.fetchone()[0]

    if null_count == 0:
        print("      All menu items already have embeddings")
        return 0

    cursor.execute(f"""
        UPDATE menu_items
        SET description_embedding = embedding('{EMBEDDING_MODEL}', description)::vector
        WHERE description_embedding IS NULL
    """)
    rows_updated = cursor.rowcount
    conn.commit()
    return rows_updated


def main():
    conn, connector = get_connection()
    cursor = conn.cursor()

    try:
        create_schema(cursor)
        conn.commit()

        seeded = seed_menu_items(cursor, conn)
        if seeded > 0:
            print(f"      ✓ Inserted {seeded} menu items")

        # Waiting for vertex role propagation
        time.sleep(60)
        embedded = generate_embeddings(cursor, conn)
        if embedded > 0:
            print(f"      ✓ Generated {embedded} embeddings")

    except Exception as e:
        print(f"ERROR: {e}", file=sys.stderr)
        sys.exit(1)
    finally:
        cursor.close()
        conn.close()
        connector.close()


if __name__ == "__main__":
    main()

Now, let's go to the next step

4. Create and Initialize the Database

Now our scripts are ready to be executed. We will need Python to execute our prepared script, so let's prepare that one first

Set up the Python project

uv is a fast Python package and project manager written in Rust ( uv documentations ). This codelab uses it for speed and simplicity in maintaining the Python project

Initialize a Python project and add the required dependencies:

uv init
uv add cloud-sql-python-connector --extra pg8000
uv add python-dotenv

Note that we are utilizing cloud-sql-python-connector Python SDK here to initialize a secure connection with our database instance which is authenticated using Application Default Credentials.

Execute the setup script

Now, we can run the setup script in the background and inspect the console output which will be written to logs/atabase_setup.log file using the following command. You can continue to the next section while waiting this to be finished

mkdir -p ~/build-agent-adk-toolbox-cloudsql/logs
bash scripts/setup_database.sh > logs/database_setup.log 2>&1 &

Download the Toolbox binary

We will utilize MCP Toolbox in this tutorial, fortunately it comes with a pre-built binary that is ready to be used in the Linux environment. Now, let's download it in the background as well as it takes quite a while. Run the following command to download the binary and inspect the output log on the logs/toolbox_dl.log . You can continue to the next section while waiting this to be finished

cd ~/build-agent-adk-toolbox-cloudsql
curl -O https://storage.googleapis.com/mcp-toolbox-for-databases/v1.1.0/linux/amd64/toolbox > logs/toolbox_dl.log 2>&1 &

Understanding the setup script `scripts/setup_database.sh`

Now let's try to understand the setup script we previously configured. It does the following process

The very first command we execute there is the gcloud sql instances create command with the following flag

db-custom-1-3840 is the smallest dedicated-core Cloud SQL tier (1 vCPU, 3.75 GB RAM) in ENTERPRISE edition. You can read more details in here. A dedicated core is required for the Vertex AI ML integration — shared-core tiers (db-f1-micro, db-g1-small) do not support it.
--root-password sets the password for the default postgres user.
--enable-google-ml-integration enables Cloud SQL's built-in integration with Vertex AI, which lets you call embedding models directly from SQL using the embedding() function.

Verify whether the instance already in RUNNABLE status
Grant the Cloud SQL instance's service account permission to call Vertex AI using the gcloud projects add-iam-policy-binding command. This is required for the built-in embedding() function that we will use when seeding the database
Creating the database
Executing the seeding script setup_restaurant_db.py script

Understanding the seed script `scripts/setup_restaurant_db.py`

Now, moving to the seeding script, this script do the following things:

Initialize connection to the database instance
Installs two PostgreSQL extensions:

google_ml_integration — provides the embedding() SQL function, which calls Vertex AI embedding models directly from SQL. This is a database-level extension that makes ML functions available inside restaurant_db. The instance-level flag (--enable-google-ml-integration) you set during instance creation allows the Cloud SQL VM to reach Vertex AI — the extension makes the SQL functions available within this specific database.
vector (pgvector) — adds the vector data type and distance operators for storing and querying embeddings.

Create the table, notes that the description_embedding column is vector(3072) — a pgvector column that stores 3072-dimensional vectors.
Seed the initial menu items data
Generate the embedding data from description field and fill the description_embedding using the built in vertex integration via the embedding() function

embedding('gemini-embedding-001', description) — calls Vertex AI's Gemini embedding model directly from SQL, passing each job's description text. This is the google_ml_integration extension you installed in the seed script.
::vector — casts the returned float array to pgvector's vector type so it can be stored and queried with distance operators.
The UPDATE runs across all 15 rows, generating one 3072-dimensional embedding per job description.

This will prepare initial data which will be accessed by our agent

5. Configure MCP Toolbox for Databases

This step introduces MCP Toolbox for Databases, configures it to connect to your Cloud SQL instance, and defines two standard SQL query tools.

What is MCP and why use Toolbox?

MCP (Model Context Protocol) is an open protocol that standardizes how AI agents discover and interact with external tools. It defines a client-server model: the agent hosts an MCP client, and tools are exposed by MCP servers. Any MCP-compatible client can use any MCP-compatible server — the agent doesn't need custom integration code for each tool.

MCP Toolbox for Databases is an open-source MCP server built specifically for database access. Without it, you would write Python functions that open database connections, manage connection pools, construct parameterized queries to prevent SQL injection, handle errors, and embed all of that code inside your agent. Every agent that needs database access repeats this work. Changing a query means redeploying the agent.

With Toolbox, you write a YAML file. Each tool maps to a parameterized SQL statement. Toolbox handles connection pooling, parameterized queries, authentication, and observability. Tools are decoupled from the agent — update a query by editing tools.yaml and restarting Toolbox, without touching agent code. The same tools work across ADK, LangGraph, LlamaIndex, or any MCP-compatible framework.

Write the tools configuration

Now, we need to create a file called tools.yaml in the Cloud Shell Editor to set up our tools configuration

cloudshell edit tools.yaml

The file uses multi-document YAML — each block separated by --- is a standalone resource. Every resource has a kind that declares what it is (sources for database connections, tools for agent-callable actions) and a type that specifies the backend (cloud-sql-postgres for the source, postgres-sql for SQL-based tools). A tool references its source by name, which is how Toolbox knows which connection pool to execute against. Environment variables use ${VAR_NAME} syntax and are resolved at startup.

Now, let's copy the following scripts first into tools.yaml file

# tools.yaml

# --- Data Source ---
kind: source
name: restaurant-db
type: cloud-sql-postgres
project: ${GOOGLE_CLOUD_PROJECT}
region: ${REGION}
instance: ${DB_INSTANCE}
database: ${DB_NAME}
user: postgres
password: ${DB_PASSWORD}

---