How to Connect to Live Snowflake Data from Google ADK Agents (via CData Connect AI)

Google ADK (Agent Development Kit) is a powerful, model-agnostic framework for building AI agents that can interact with various data sources and services. When combined with CData Connect AI Remote MCP, you can leverage Google ADK to build intelligent agents that interact with your Snowflake data in real-time through natural language queries. This article outlines the process of connecting to Snowflake using Connect AI Remote MCP and configuring a Google ADK agent to interact with your Snowflake data through ADK Web.

CData Connect AI offers a dedicated cloud-to-cloud interface for connecting to Snowflake data. The CData Connect AI Remote MCP Server enables secure communication between Google ADK agents and Snowflake. This allows your agents to read from and take actions on your Snowflake data, all without the need for data replication to a natively supported database. With its inherent optimized data processing capabilities, CData Connect AI efficiently channels all supported SQL operations, including filters and JOINs, directly to Snowflake. This leverages server-side processing to swiftly deliver the requested Snowflake data.

In this article, we show how to configure a Google ADK agent to conversationally explore (or Vibe Query) your data using natural language. With Connect AI you can build agents with access to live Snowflake data, plus hundreds of other sources.

Getting Started

---

Step 1: Configure Snowflake Connectivity for Google ADK

Connectivity to Snowflake from Google ADK agents is made possible through CData Connect AI Remote MCP. To interact with Snowflake data from your ADK agent, we start by creating and configuring a Snowflake connection in CData Connect AI.

1. Log into Connect AI, click Sources, and then click Add Connection

2. Select "Snowflake" from the Add Connection panel

3. Enter the necessary authentication properties to connect to Snowflake.

   To connect to Snowflake:

   1. Set User and Password to your Snowflake credentials and set the AuthScheme property to PASSWORD or OKTA.
   2. Set URL to the URL of the Snowflake instance (i.e.: https://myaccount.snowflakecomputing.com).
   3. Set Warehouse to the Snowflake warehouse.
   4. (Optional) Set Account to your Snowflake account if your URL does not conform to the format above.
   5. (Optional) Set Database and Schema to restrict the tables and views exposed.

   See the Getting Started guide in the CData driver documentation for more information.

   
4. Click Save & Test
5. Navigate to the Permissions tab in the Add Snowflake Connection page and update the User-based permissions.

Add a Personal Access Token

A Personal Access Token (PAT) is used to authenticate the connection to Connect AI from your Google ADK agent. It is best practice to create a separate PAT for each service to maintain granularity of access.

1. Click on the Gear icon () at the top right of the Connect AI app to open the settings page.
2. On the Settings page, go to the Access Tokens section and click Create PAT.
3. Give the PAT a name and click Create.
4. The personal access token is only visible at creation, so be sure to copy it and store it securely for future use.

With the connection configured and a PAT generated, we are ready to connect to Snowflake data from your Google ADK agent.

Step 2: Configure Your Google ADK Agent for CData Connect AI

Follow these steps to configure your Google ADK agent to connect to CData Connect AI. You can use our pre-built agent as a starting point, available at https://github.com/CDataSoftware/adk-mcp-client, or follow the instructions below to create your own.

1. Ensure you have the Google ADK Python SDK installed. If not, install it using pip:

   pip install google-genkit google-adk

2. Create or update your agent's configuration file (typically agent.py) to include the CData Connect AI MCP connection. You'll need to configure the MCP toolset with your Connect AI credentials.
3. Set up your environment variables or configuration for the MCP server connection. Create a .env file in your project root with the following variables:

   MCP_SERVER_URL=https://mcp.cloud.cdata.com/mcp
   MCP_USERNAME=YOUR_EMAIL
   MCP_PASSWORD=YOUR_PAT
       

   Replace YOUR_EMAIL with your Connect AI email address and YOUR_PAT with the Personal Access Token created in Step 1.
4. Configure your agent.py file to use the CData Connect AI MCP Server. Here's an example configuration:

   import os
   import base64
   from google.adk.agents import LlmAgent
   from google.adk.tools.mcp_tool.mcp_toolset import MCPToolset
   from google.adk.tools.mcp_tool.mcp_session_manager import StreamableHTTPConnectionParams
   from dotenv import load_dotenv
   
   # Load environment variables
   load_dotenv()
   
   # Get configuration from environment
   MCP_SERVER_URL = os.getenv('MCP_SERVER_URL', 'https://mcp.cloud.cdata.com/mcp')
   MCP_USERNAME = os.getenv('MCP_USERNAME', '')
   MCP_PASSWORD = os.getenv('MCP_PASSWORD', '')
   
   # Create auth header for MCP server
   auth_header = {}
   if MCP_USERNAME and MCP_PASSWORD:
       credentials = f"{MCP_USERNAME}:{MCP_PASSWORD}"
       auth_header = {"Authorization": f"Basic {base64.b64encode(credentials.encode()).decode()}"}
   
   # Define your agent with CData MCP tools
   root_agent = LlmAgent(
       model='gemini-2.0-flash-exp',  # You can use any supported model
       name='data_query_assistant',
       instruction="""You are a data query assistant with access to Snowflake data through CData Connect AI.
       
       You can help users explore and query their Snowflake data in real-time.
       Use the available MCP tools to:
       - List available databases and schemas
       - Explore table structures
       - Execute SQL queries
       - Provide insights about the data
       
       Always explain what you're doing and format results clearly.""",
       
       tools=[
           MCPToolset(
               connection_params=StreamableHTTPConnectionParams(
                   url=MCP_SERVER_URL,
                   headers=auth_header
               )
           )
       ],
   )
       

5. Run your agent with ADK Web. From your project directory, execute:

   adk web --port 5000 .

   Note: If you installed ADK with pip install --user, the adk command may not be in your PATH. You can either:

   • Use the full path: ~/Library/Python/3.x/bin/adk (on macOS)
   • Add to PATH: export PATH="$HOME/Library/Python/3.x/bin:$PATH"
   • Use a virtual environment where the PATH is automatically configured
6. Open the ADK Web interface in your browser (typically http://localhost:5000).
7. Select your agent from the dropdown menu (it will be named based on the name parameter in your agent configuration).
8. Start interacting with your Snowflake data through natural language queries. Your agent now has access to your Snowflake data through the CData Connect AI MCP Server.

Step 3: Build Intelligent Agents with Live Snowflake Data Access

With your Google ADK agent configured and connected to CData Connect AI, you can now build sophisticated agents that interact with your Snowflake data using natural language. The MCP integration provides your agents with powerful data access capabilities.

Available MCP Tools for Your Agent

Your Google ADK agent has access to the following CData Connect AI MCP tools:

• queryData: Execute SQL queries against connected data sources and retrieve results
• getCatalogs: Retrieve a list of available connections from CData Connect AI
• getSchemas: Retrieve database schemas for a specific catalog
• getTables: Retrieve database tables for a specific catalog and schema
• getColumns: Retrieve column metadata for a specific table
• getProcedures: Retrieve stored procedures for a specific catalog and schema
• getProcedureParameters: Retrieve parameter metadata for stored procedures
• executeProcedure: Execute stored procedures with parameters

Example Use Cases

Here are some examples of what your Google ADK agents can do with live Snowflake data access:

• Data Analysis Agent: Build an agent that analyzes trends, patterns, and anomalies in your Snowflake data
• Report Generation Agent: Create agents that generate custom reports based on natural language requests
• Data Quality Agent: Develop agents that monitor and validate data quality in real-time
• Business Intelligence Agent: Build agents that answer complex business questions by querying multiple data sources
• Automated Workflow Agent: Create agents that trigger actions based on data conditions in Snowflake

Testing Your Agent

Once deployed to ADK Web, you can interact with your agent through natural language queries. For example:

• "Show me all customers from the last 30 days"
• "What are the top performing products this quarter?"
• "Analyze sales trends and identify anomalies"
• "Generate a summary report of active projects"
• "Find all records that match specific criteria"

Your Google ADK agent will automatically translate these natural language queries into appropriate SQL queries and execute them against your Snowflake data through the CData Connect AI MCP Server, providing real-time insights without requiring users to write complex SQL or understand the underlying data structure.

Get CData Connect AI

To get live data access to 300+ SaaS, Big Data, and NoSQL sources directly from your Google ADK agents and cloud applications, try CData Connect AI today!