Integrating Gumloop with Lakebase Data via CData Connect AI

Gumloop is a visual automation platform designed to create AI-powered workflows by combining triggers, AI nodes, APIs, and data connectors. By integrating Gumloop with CData Connect AI through the built-in MCP (Model Context Protocol) Server, workflows can seamlessly access and interact with live Lakebase data.

The platform provides a low-code environment, making it easier to orchestrate complex processes without heavy development effort. Its flexibility allows integration across multiple business applications, enabling end-to-end automation with live data.

This article outlines the steps required to configure Lakebase connectivity in Connect AI, register the MCP server in Gumloop, and build a workflow that queries Lakebase data.

Step 1: Configure Lakebase Connectivity for Gumloop

Connectivity to Lakebase from Gumloop is made possible through CData Connect AI's Remote MCP Server. To interact with Lakebase data from Gumloop, we start by creating and configuring a Lakebase connection in CData Connect AI.

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

2. Select "Lakebase" from the Add Connection panel
👁 Selecting a data source

3. Enter the necessary authentication properties to connect to Lakebase. To connect to Databricks Lakebase, start by setting the following properties:
   • DatabricksInstance: The Databricks instance or server hostname, provided in the format instance-abcdef12-3456-7890-abcd-abcdef123456.database.cloud.databricks.com.
   • Server: The host name or IP address of the server hosting the Lakebase database.
   • Port (optional): The port of the server hosting the Lakebase database, set to 5432 by default.
   • Database (optional): The database to connect to after authenticating to the Lakebase Server, set to the authenticating user's default database by default.

   OAuth Client Authentication

   To authenicate using OAuth client credentials, you need to configure an OAuth client in your service principal. In short, you need to do the following:

   1. Create and configure a new service principal
   2. Assign permissions to the service principal
   3. Create an OAuth secret for the service principal

   For more information, refer to the Setting Up OAuthClient Authentication section in the Help documentation.

   OAuth PKCE Authentication

   To authenticate using the OAuth code type with PKCE (Proof Key for Code Exchange), set the following properties:

   • AuthScheme: OAuthPKCE.
   • User: The authenticating user's user ID.

   For more information, refer to the Help documentation.

   👁 Configuring a connection (Salesforce is shown)
   
4. Click Save & Test
5. Navigate to the Permissions tab in the Add Lakebase Connection page and update the User-based permissions. 👁 Updating permissions
   

Add a Personal Access Token

A Personal Access Token (PAT) is used to authenticate the connection to Connect AI from Gumloop. 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. 👁 Creating a new PAT
   
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 Lakebase connection configured and a PAT generated, Gumloop is prepared to connect to Lakebase data through the CData MCP server.

Step 2: Connect to the MCP server in Gumloop

The MCP server endpoint and authentication values from Connect AI must be added to Gumloop credentials.

1. Sign in to Gumloop and create an account
2. Visit the Gumloop Credentials page to configure MCP server
3. Click on Add Credentials and search and select MCP Server
👁 Configuring MCP server
👁 MCP server app

4. Provide the following details:
   • URL: https://mcp.cloud.cdata.com/mcp
   • Label: A descriptive name such as Lakebase-mcp-server
   • Access Token / API Key: leave blank
   • Additional Header: Authorization: Basic YOUR EMAIL:YOUR PAT
   👁 Configuring to CData MCP server
   
   • Save the credentials
   👁 Saved MCP Credentials
   

The MCP server is now available to build workflows in Gumloop.

Step 3: Build a workflow and explore live Lakebase data with Gumloop

1. Visit Gumloop Personal workspace and click on the Create Flow
👁 Create Gumloop workflow

2. Select the icon or press Ctrl + B to add a node or a subflow
👁 Add a node

3. Search for Ask AI and select it
👁 Select Ask AI

4. Click Show More Options and enable the Connect MCP Server? option
👁 Enable 'Connect MCP Server?'

5. From the MCP Servers dropdown, choose the saved MCP credential
6. Add a Prompt and Choose an AI Model according to your requirements
👁 Add Prompt

7. After configuring the required details, Click Run to run the pipeline
👁 Example 1: Gumloop workflow execution
👁 Example 2: Gumloop workflow execution

With the workflow run completed, Gumloop demonstrates successful retrieval of Lakebase data through the CData Connect AI MCP server, with the MCP Client node providing the ability to ask questions, retrieve records, and perform actions on the data.

Get CData Connect AI

To get live data access to hundreds of SaaS, Big Data, and NoSQL sources directly from your cloud applications, try CData Connect AI today!