Integrate Devin with Live Lakebase Data Using CData Connect AI

Devin is an AI software engineer from Cognition that plans, writes, and tests code in autonomous sessions. It supports the model context protocol (MCP) through its built-in MCP marketplace, allowing you to install remote MCP servers and give Devin access to external tools and live data sources.

By integrating Devin with CData Connect AI through the built-in MCP Server, Devin gains governed, real-time access to live Lakebase data. You can list catalogs, explore schemas, and query records from Lakebase data using natural language prompts, with all data access running securely against authorized sources.

This article explains how to configure Lakebase connectivity in Connect AI, install the CData Connect AI MCP Server from the Devin MCP marketplace, and verify the integration by querying live Lakebase data from a Devin session.

Step 1: Configure Lakebase connectivity for Devin

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

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

2. Select Lakebase from the Add Connection panel

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.

   
4. Click Save & Test
5. Navigate to the Permissions tab and update user-based permissions

With the Lakebase connection configured, Devin can now connect to Lakebase data through Connect AI.

Step 2: Install the Connect AI MCP Server in Devin

Next, install the CData Connect AI MCP Server from the Devin MCP servers list so your sessions can discover and call live data tools through Connect AI.

Note: Installing MCP servers in Devin requires the Manage MCP Servers permission. If you don't have this permission, use the Suggest option or contact your organization admin.

1. Log into Devin and navigate to Settings and Connections, then select the MCP servers tab
2. Search for CData Connect AI in the marketplace and select the verified listing

3. Click Install and enable. When prompted, complete the OAuth flow to authenticate with your Connect AI account
4. Once installed, confirm the Enable in sessions toggle is on and click Test tools. Devin validates the connection and lists the available Connect AI tools, such as getCatalogs, getSchemas, getTables, and queryData

With the MCP server installed and enabled, the Connect AI tools are available to every Devin session in your workspace.

Step 3: Query live Lakebase data from Devin

With the integration complete, start a Devin session and interact with live Lakebase data through natural language prompts.

1. From the Devin home page, start a new session
2. In the session prompt, ask Devin to work with your Connect AI data, for example:
   • Can you list the connections in CData Connect AI
   • Show the available schemas and tables for Lakebase
   • Query the top 5 records from a table in Lakebase
3. Devin calls the Connect AI MCP Server and returns live results from Lakebase data directly in the session. You can follow the tool calls, inputs, and outputs in the Progress panel

At this point, Devin communicates with the Connect AI MCP Server and retrieves live Lakebase data through remote MCP tools directly from your sessions, whether you're exploring data, building features against it, or automating engineering tasks.

Get started with CData Connect AI

To access hundreds of SaaS, big data, and NoSQL sources directly from your cloud applications, try CData Connect AI today. Download a free 14-day trial of CData Connect AI, and our Support Team is available to help with any questions you have.