Integrate Cursor with Live SQL Analysis Services 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 SQL Analysis Services 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 SQL Analysis Services 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 SQL Analysis Services data.

Step 1: Configure SQL Analysis Services connectivity for Cursor

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

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

2. Select SQL Analysis Services from the Add Connection panel

3. Enter the necessary authentication properties to connect to SQL Analysis Services.

   To connect, provide authentication and set the Url property to a valid SQL Server Analysis Services endpoint. You can connect to SQL Server Analysis Services instances hosted over HTTP with XMLA access. See the Microsoft documentation to configure HTTP access to SQL Server Analysis Services.

   To secure connections and authenticate, set the corresponding connection properties, below. The data provider supports the major authentication schemes, including HTTP and Windows, as well as SSL/TLS.

   • HTTP Authentication

     Set AuthScheme to "Basic" or "Digest" and set User and Password. Specify other authentication values in CustomHeaders.

   • Windows (NTLM)

     Set the Windows User and Password and set AuthScheme to "NTLM".

   • Kerberos and Kerberos Delegation

     To authenticate with Kerberos, set AuthScheme to NEGOTIATE. To use Kerberos delegation, set AuthScheme to KERBEROSDELEGATION. If needed, provide the User, Password, and KerberosSPN. By default, the data provider attempts to communicate with the SPN at the specified Url.

   • SSL/TLS:

     By default, the data provider attempts to negotiate SSL/TLS by checking the server's certificate against the system's trusted certificate store. To specify another certificate, see the SSLServerCert property for the available formats.

   You can then access any cube as a relational table: When you connect the data provider retrieves SSAS metadata and dynamically updates the table schemas. Instead of retrieving metadata every connection, you can set the CacheLocation property to automatically cache to a simple file-based store.

   See the Getting Started section of the CData documentation, under Retrieving Analysis Services Data, to execute SQL-92 queries to the cubes.

   
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 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

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 SQL Analysis Services connection configured and a PAT generated, Cursor can now connect to SQL Analysis Services 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
3. In the left navigation, open the Tools & MCP tab and click 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"
         }
       }
     }
   }
   		

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

Step 3: Chat with CData Connect AI from Cursor

1. From the top bar, click Toggle AI Pane to open the chat window
2. Test the connection by entering "List connections"
3. You can also run queries like "Query SQL Analysis Services data and list the high priority accounts"

Cursor is now fully integrated with the CData Connect AI MCP Server and can act on live SQL Analysis Services 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!