Build SAS xpt-Powered Applications in GitHub Copilot with CData Code Assist MCP

GitHub Copilot is an AI-powered coding assistant that integrates directly into Visual Studio Code and other IDEs. With support for MCP, GitHub Copilot can connect to local tools and enterprise data sources, enabling natural language interaction with live systems during development.

Model Context Protocol (MCP) is an open standard for connecting LLM clients to external services through structured tool interfaces. MCP servers expose capabilities such as schema discovery and live querying, allowing AI agents to retrieve and reason over real-time data safely and consistently.

In this article, we guide you through installing the CData Code Assist MCP for SASxpt, configuring the connection to SAS xpt, connecting the Code Assist MCP add-on to GitHub Copilot, and querying live SAS xpt data from within Visual Studio Code.

Prerequisites

• Visual Studio Code is installed on your machine
• GitHub Copilot Chat extension is enabled in Visual Studio Code
• CData Code Assist MCP for SASxpt has been installed

Step 1: Download and install the CData Code Assist MCP for SASxpt

1. To begin, download the CData Code Assist MCP for SASxpt
2. Find and double-click the installer to begin the installation
3. Run the installer and follow the prompts to complete the installation

When the installation is complete, you are ready to configure your Code Assist MCP add-on by connecting to SAS xpt.

Step 2: Configure the connection to SAS xpt

1. After installation, open the CData Code Assist MCP for SASxpt configuration wizard

   NOTE: If the wizard does not open automatically, search for "CData Code Assist MCP for SASxpt" in the Windows search bar and open the application.

   
2. In MCP Configuration > Configuration Name, either select an existing configuration or choose to create a new one
3. Name the configuration (e.g. "cdata_sasxpt") and click OK

4. Enter the appropriate connection properties in the configuration wizard

   Connecting to Local SASXpt Files

   You can connect to local SASXpt file by setting the URI to a folder containing SASXpt files.

   Connecting to S3 data source

   You can connect to Amazon S3 source to read SASXpt files. Set the following properties to connect:

   • URI: Set this to the folder within your bucket that you would like to connect to.
   • AWSAccessKey: Set this to your AWS account access key.
   • AWSSecretKey: Set this to your AWS account secret key.
   • TemporaryLocalFolder: Set this to the path, or URI, to the folder that is used to temporarily download SASXpt file(s).

   Connecting to Azure Data Lake Storage Gen2

   You can connect to ADLS Gen2 to read SASXpt files. Set the following properties to connect:

   • URI: Set this to the name of the file system and the name of the folder which contacts your SASXpt files.
   • AzureAccount: Set this to the name of the Azure Data Lake storage account.
   • AzureAccessKey: Set this to our Azure DataLakeStore Gen 2 storage account access key.
   • TemporaryLocalFolder: Set this to the path, or URI, to the folder that is used to temporarily download SASXpt file(s).
   
5. Click Connect to authenticate with SAS xpt
6. Click Save & Test to finalize the connection

This process creates a .mcp configuration file that GitHub Copilot will reference when launching the Code Assist MCP add-on. Now with your Code Assist MCP add-on configured, you are ready to connect it to GitHub Copilot.

Step 3: Connect the Code Assist MCP add-on to GitHub Copilot

1. Download and install Visual Studio Code and enable the GitHub Copilot Chat extension

Option 1: Manually add the MCP configuration

1. Open or create the mcp.json file:
   • For global configuration: %%APPDATA%%/Roaming/Code/User/mcp.json
   • For project-specific configuration: /.vscode/mcp.json
2. Add the JSON code shown below and save the file

{
  "servers": {
    "cdata_sasxpt": {
      "command": "C:\Program Files\CData\CData Code Assist MCP for SASxpt\jre\bin\java.exe",
      "args": [
        "-Dfile.encoding=UTF-8",
        "-jar",
        "C:\Program Files\CData\CData Code Assist MCP for SASxpt\lib\cdata.mcp.sasxpt.jar",
        "cdata_sasxpt"
      ]
    }
  }
}

NOTE: The command value should point to your Java 17+ java.exe executable, and the JAR path should point to the installed CData Code Assist MCP add-on .jar file. The final argument must match the MCP configuration name you saved in the CData configuration wizard (e.g. "cdata_sasxpt").

Option 2: Copy the MCP configuration from the CData Code Assist MCP for SASxpt UI

1. After saving and testing your connection in the configuration wizard, click Next
2. Select Github Copilot from the AI MCP Tool dropdown
3. Follow the MCP Client Instructions to create the required configuration file
4. Copy the displayed JSON code and paste it into your configuration file

Step 4: Query live SAS xpt data in GitHub Copilot

1. Launch Visual Studio Code and open the GitHub Copilot Chat interface. Select the tool icon to enable the configured Code Assist MCP add-on
2. Ask questions about your SAS xpt data using natural language. For example:

   "List all tables available in my SAS xpt data data connection."

   
3. Start building with natural language prompts:

   For my project, data from the SampleTable_1 is very important. Pull data from the most important columns like Id and Column1.
   

GitHub Copilot is now fully integrated with CData Code Assist MCP for SASxpt and can use the MCP tools to explore schemas and execute live queries against SAS xpt.

Build with Code Assist MCP. Deploy with CData Drivers.

Download Code Assist MCP for free and give your AI tools schema-aware access to live SAS xpt data during development. When you're ready to move to production, CData SAS xpt Drivers deliver the same SQL-based access with enterprise-grade performance, security, and reliability.

Visit the CData Community to share insights, ask questions, and explore what's possible with MCP-powered AI workflows.