Access Live Snowflake Data in Roo Code via CData Connect AI

Anusha M B
Anusha M B
Technical Marketing Engineer
Leverage the CData Connect AI Remote MCP Server to enable Roo Code agents to securely access and build applications with live Snowflake data through MCP integration.

Roo Code is an open-source AI coding agent that runs inside VS Code with real file system access, terminal control, and multi-step workflows. It works across entire project workspaces through specialized modes like Code, Architect, and Orchestrator. Available as a VS Code Extension for local development, or as Cloud Agents that integrate with Slack and GitHub. Roo Code natively supports MCP, connecting external tools and data sources via STDIO or Streamable HTTP.

By default, Roo Code has no access to live enterprise data. CData Connect AI bridges this gap by exposing 350+ data sources. Once connected, Roo can introspect live schemas, validate queries, and generate code directly inside VS Code, retrieved by real enterprise data.

About Snowflake Data Integration

CData simplifies access and integration of live Snowflake data. Our customers leverage CData connectivity to:

  • Reads and write Snowflake data quickly and efficiently.
  • Dynamically obtain metadata for the specified Warehouse, Database, and Schema.
  • Authenticate in a variety of ways, including OAuth, OKTA, Azure AD, Azure Managed Service Identity, PingFederate, private key, and more.

Many CData users use CData solutions to access Snowflake from their preferred tools and applications, and replicate data from their disparate systems into Snowflake for comprehensive warehousing and analytics.

For more information on integrating Snowflake with CData solutions, refer to our blog: https://www.cdata.com/blog/snowflake-integrations.


Getting Started


Step 1: Configure Snowflake connectivity for Roo Code

Connectivity to Snowflake from Roo Code is made possible through CData Connect AI's Remote MCP Server. To interact with Snowflake data from Roo Code, 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 and update user-based permissions

Add a Personal Access Token

A Personal Access Token (PAT) is used to authenticate the connection to Connect AI from Roo Code. It is best practice to create a separate PAT for each integration to maintain granular access control.

  1. Click the gear icon at the top right of the Connect AI app to open Settings
  2. On the Settings page, go to the Access Tokens section and click Create PAT
  3. Give the PAT a descriptive name and click Create
  4. Copy the token when displayed and store it securely. It will not be shown again

With the Snowflake connection configured and a PAT generated, Roo Code can now connect to Snowflake data through Connect AI.

Step 2: Configure Connect AI in Roo Code

CData Connect AI can be integrated with Roo Code by registering the MCP Server directly in the Roo Code MCP configuration panel. Once registered, Roo Code agents can call live Snowflake data through MCP tools without additional setup.

Method 1: Direct MCP configuration

Users can register the CData Connect AI MCP Server directly in the Roo Code MCP settings. Once registered, agents in any project can query live Snowflake data through MCP tools without additional setup.

  1. Open VS Code with the Roo Code extension installed
  2. Click the Roo Code icon in the Activity Bar
  3. Navigate to Settings, then choose MCP Servers in the Roo Code pane and turn on Enable MCP Servers, now click Edit Global MCP to open the MCP configuration file
  4. In the mcp_settings.json file, add the following inside the mcpServers object, replacing base64encode with your Base64-encoded email:PAT
    {
        "mcpServers": {
            "cdata-mcp": {
                "type": "streamable-http",
                "url": "https://mcp.cloud.cdata.com/mcp",
                "headers": {
                    "Authorization": "Basic base64encode(USERNAME:PAT)"
                }
            }
        }
    }
            
  5. Save the file to register the MCP server
  6. Return to the MCP Servers panel and confirm that cdata-mcp is listed and its toggle is enabled. If it is not enabled, toggle it on

With the CData MCP Server registered and enabled, Roo Code agents can now query and act on live Snowflake data through Connect AI in any project.

Query live Snowflake data from Roo Code

With the MCP server configured, start a conversation in the Roo Code chat panel to interact with live Snowflake data.

  1. Open the Roo Code chat and enter a prompt to explore your data, for example:
    • List all available catalogs in my cdata-mcp connection.
    • Show the schemas and tables available for Snowflake.
    • Query the top 5 records from Snowflake data.
  2. The agent calls the CData Connect AI MCP Server and returns live results from Snowflake data

Method 2: Build an application with natural language

Users can direct Roo Code to build a full application that connects to the CData Connect AI MCP Server through a natural language prompt. The agent gathers the required endpoint and credentials interactively, then generates a working application wired to live Snowflake data — all from the Roo Code chat panel inside VS Code.

  1. Open the Roo Code panel in VS Code and select your preferred model from the dropdown
  2. Enter a prompt that describes the application you want to build. For example:
    I would like to build a small application that connects to a remote MCP 
    HTTPS server. I already have the MCP endpoint URL and the required 
    credentials. The application should:
      - Establish a connection to the remote MCP server
      - Authenticate using the provided credentials
      - Retrieve and list all available catalogs from the MCP
    
    Please make sure the credentials are stored securely in a .env file
    and not hardcoded in the application.
            
  3. Roo Code will prompt you to provide the MCP endpoint URL and authentication credentials. Supply the following values:
    • MCP Endpoint URL: https://mcp.cloud.cdata.com/mcp
    • Authorization: Basic base64(email:PAT)
  4. Roo Code creates the project directory, initializes a Node.js project, installs the necessary packages, and stores credentials securely in a .env file

At this point, Roo Code has built an application that communicates with the CData Connect AI MCP Server and retrieves live Snowflake data, all from a single natural language prompt inside VS Code.

Get CData Connect AI

To access 350+ SaaS, Big Data, and NoSQL sources directly from Roo Code, try CData Connect AI today! Sign up for a free 14-day trial of CData Connect AI, and as always, our world-class Support Team is available to assist you with any questions you may have.

Ready to get started?

Learn more about CData Connect AI or sign up for free trial access:

Free Trial