Integrate Cursor with Live AlloyDB Data via CData Connect AI

Cursor is an AI-powered code editor that embeds conversational and agent-style assistance alongside your development workflow. By extending Cursor with MCP (Model Context Protocol) tools, you can give its AI agents secure access to external systems such as APIs and databases.

Integrating Cursor with CData Connect AI via the built-in MCP server allows the editor's AI to query, analyze, and act on live AlloyDB data without copying data into the IDE. The result is a development experience where you can chat with your governed enterprise data directly from Cursor.

This article outlines how to configure AlloyDB connectivity in Connect AI, generate the required access token, register Connect AI's MCP Server in Cursor, and then use the AI chat pane to explore live AlloyDB data.

Step 1: Configure AlloyDB connectivity for Cursor

Connectivity to AlloyDB from Cursor is made possible through CData Connect AI's Remote MCP Server. To interact with AlloyDB data from Cursor, start by creating and configuring a AlloyDB 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 AlloyDB from the Add Connection panel
👁 Selecting data source

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

   The following connection properties are usually required in order to connect to AlloyDB.

   • Server: The host name or IP of the server hosting the AlloyDB database.
   • User: The user which will be used to authenticate with the AlloyDB server.
   • Password: The password which will be used to authenticate with the AlloyDB server.

   You can also optionally set the following:

   • Database: The database to connect to when connecting to the AlloyDB Server. If this is not set, the user's default database will be used.
   • Port: The port of the server hosting the AlloyDB database. This property is set to 5432 by default.

   Authenticating with Standard Authentication

   Standard authentication (using the user/password combination supplied earlier) is the default form of authentication.

   No further action is required to leverage Standard Authentication to connect.

   Authenticating with pg_hba.conf Auth Schemes

   There are additional methods of authentication available which must be enabled in the pg_hba.conf file on the AlloyDB server.

   Find instructions about authentication setup on the AlloyDB Server here.

   Authenticating with MD5 Authentication

   This authentication method must be enabled by setting the auth-method in the pg_hba.conf file to md5.

   Authenticating with SASL Authentication

   This authentication method must be enabled by setting the auth-method in the pg_hba.conf file to scram-sha-256.

   Authenticating with Kerberos

   The authentication with Kerberos is initiated by AlloyDB Server when the ∏ is trying to connect to it. You should set up Kerberos on the AlloyDB Server to activate this authentication method. Once you have Kerberos authentication set up on the AlloyDB Server, see the Kerberos section of the help documentation for details on how to authenticate with Kerberos. 👁 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 Cursor. 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. The personal access token is only visible at creation, so be sure to copy it and store it securely for future use

With the AlloyDB connection configured and a PAT generated, Cursor can now connect to AlloyDB data through Connect AI.

Step 2: Configure Connect AI in Cursor

Next, configure Cursor to use Connect AI. Cursor reads MCP configuration from an mcp.json file in the user configuration directory and exposes the registered servers under the Tools & MCP settings. Once configured, Cursor's AI chat can call the tools exposed by CData Connect AI.

1. Download the Cursor desktop application and complete the sign-up flow for your account
2. From the top menu, click Settings to open the settings panel 👁 Opening Cursor Settings
   
3. In the left navigation, open the Tools & MCP tab and click Add Custom MCP 👁 Tools & MCP tab with Add Custom MCP
   
4. Cursor opens an mcp.json file in the editor
5. Add the following configuration. Make sure to base64-encode your email:PAT before inserting into the header:

   {
    "mcpServers": {
    "cdata-mcp": {
    "url": "https://mcp.cloud.cdata.com/mcp",
    "headers": {
    "Authorization": "Basic your_base64_encoded_email_PAT"
    }
    }
    }
   }
   		

   👁 Configuring mcp.json with Connect AI
   
6. Save the file
7. Return to Settings and then select Tools & MCP. You can now see cdata-mcp enabled with an active indicator 👁 Connect AI enabled
   

Step 3: Chat with CData Connect AI from Cursor

1. From the top bar, click Toggle AI Pane to open the chat window 👁 Opening the AI pane
   
2. Test the connection by entering "List connections"
3. You can also run queries like "Query AlloyDB data and list the high priority accounts" 👁 Querying AlloyDB data from Connect AI
   

Cursor is now fully integrated with the CData Connect AI MCP Server and can act on live AlloyDB data directly from the editor.

Get CData Connect AI

To access hundreds of SaaS, Big Data, and NoSQL sources directly from your development tools, try CData Connect AI today!