Integrate Cline with Live Databricks Data via CData Connect AI

Cline is an autonomous AI coding agent that runs inside modern IDEs such as VS Code and Cursor. It enables developers to build agent-driven workflows that can reason through tasks, execute actions, and interact with external systems directly from the editor using a structured execution model.

By integrating Cline with CData Connect AI through the built-in MCP (Model Context Protocol) Server, the agent gains the ability to query, analyze, and act on live Databricks data in real time. This integration bridges Cline's in-IDE agent framework with the governed enterprise connectivity of CData Connect AI, ensuring all data access runs securely against authorized sources without manual data movement.

This article outlines the steps to configure Databricks connectivity in Connect AI, generate the required personal access token, register the Connect AI MCP Server in Cline, and verify that the agent can successfully interact with live Databricks data from within the IDE.

Getting Started

---

Step 1: Configure Databricks connectivity for Cline

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

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

2. Select Databricks from the Add Connection panel
👁 Selecting data source

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

   To connect to a Databricks cluster, set the properties as described below.

   Note: The needed values can be found in your Databricks instance by navigating to Clusters, and selecting the desired cluster, and selecting the JDBC/ODBC tab under Advanced Options.

   • Server: Set to the Server Hostname of your Databricks cluster.
   • HTTPPath: Set to the HTTP Path of your Databricks cluster.
   • Token: Set to your personal access token (this value can be obtained by navigating to the User Settings page of your Databricks instance and selecting the Access Tokens tab).
   👁 Configuring a connection (Salesforce is shown)
   
4. Click Save & Test
5. Navigate to the Permissions tab and update 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 Cline. 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
👁 Creating a new PAT

4. Copy the token when displayed and store it securely. It will not be shown again

With the Databricks connection configured and a PAT generated, Cline can now connect to Databricks data through the CData Connect Ai.

Step 2: Install and set up Cline

Cline is distributed as an IDE extension and can be installed in environments such as VS Code or Cursor. In this example, Cursor is used, but the steps are identical for supported IDEs.

1. Open Cursor and install the Cline extension from the Extensions Marketplace 👁 Installing the Cline extension in Cursor
   
2. Complete the initial Cline setup flow, including model selection and permission prompts
3. After setup is complete, the Cline agent panel opens automatically inside the IDE

Step 3: Add the Connect AI Remote MCP Server

Once Cline is running, add the CData Connect AI Remote MCP Server so the agent can access live Databricks data through Connect AI.

1. In the Cline panel, click MCP Servers 👁 Opening MCP Servers in Cline
   
2. Open Remote Servers and click Edit Configuration 👁 Editing remote MCP server configuration
   
3. This opens a JSON configuration file. Paste the configuration below

   {
    "mcpServers": {
    "mcp": {
    "url": "https://mcp.cloud.cdata.com/mcp",
    "type": "streamableHttp",
    "headers": {
    "Authorization": "Basic your_email:your_PAT"
    },
    "disabled": false,
    "autoApprove": []
    }
    }
   }
   

   Note: Cline will use Basic authentication with Connect AI. Combine your Connect AI user email and the PAT you created earlier. For example, [email protected]:ABC123...XYZ789 and add the value for the Authorization header like, Basic [email protected]:ABC123...XYZ789.

   👁 Configuring MCP server
   
4. Save the file and return to the MCP Servers screen to confirm the server is listed and enabled 👁 Configured MCP server listed in Cline
   

Step 4: Query live data from Cline

With the MCP server registered, Cline can now interact with live data sources exposed by Connect AI.

1. Click the icon in the Cline panel to start a New Task/Chat 👁 Starting a new chat in Cline
   
2. At the bottom of the chat window, confirm that the configured MCP server is selected 👁 Selecting the configured MCP server
   
3. Start interacting with the agent by entering prompts such as:
   • List connections
   • Show schemas for a catalog
   • Query recent records from Databricks data
   👁 Sample output from querying through the MCP server
   

Cline is now fully configured to access and query live Databricks data through the CData Connect AI Remote MCP Server, enabling real-time, data-driven workflows directly from your IDE.

Get CData Connect AI

To access hundreds of SaaS, Big Data, and NoSQL sources through secure, AI-ready interfaces, try CData Connect AI today.