Build Adobe Target-Powered Applications in Cursor with CData Code Assist MCP
Cursor is an AI-powered code editor that integrates agentic AI into everyday development workflows. With support for MCP, Cursor can connect to local tools and enterprise data sources directly from the editor, enabling natural language interaction with live systems without switching context.
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 Adobe Target, configuring the connection to Adobe Target, connecting the Code Assist MCP add-on to Cursor, and querying live Adobe Target data from within the editor.
Step 1: Download and install the CData Code Assist MCP for Adobe Target
- To begin, download the CData Code Assist MCP for Adobe Target
- Find and double-click the installer to begin the installation
- 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 Adobe Target.
Step 2: Configure the connection to Adobe Target
- After installation, open the CData Code Assist MCP for Adobe Target configuration wizard
NOTE: If the wizard does not open automatically, search for "CData Code Assist MCP for Adobe Target" in the Windows search bar and open the application.
- In MCP Configuration > Configuration Name, either select an existing configuration or choose
to create a new one
- Name the configuration (e.g. "cdata_adobetarget") and click OK
-
Enter the appropriate connection properties in the configuration wizard
To connect to Adobe Target, you must provide the Tenant property along with OAuth connection properties mentioned below. Note that while other connection properties can influence processing behavior, they do not affect the ability to connect.
To determine your Tenant name:
- Log in to Adobe Experience. The URL will look similar to: "https://experience.adobe.com/#/@mycompanyname/preferences/general-section".
- Extract the value after the "/#/@". In this example, it is "mycompanyname".
- Set the Tenant connection property to that value.
User Accounts (OAuth)
You must set AuthScheme to OAuthClient for all user account flows.
Note: Adobe authentication via OAuth requires updating your token every two weeks.
All Applications
CData provides an embedded OAuth application that simplifies OAuth authentication. Alternatively, you can create a custom OAuth application. Review Creating a Custom OAuth App in the Help documentation for more information.Obtaining the OAuth Access Token
Set the following properties to connect:
- InitiateOAuth: Set to GETANDREFRESH to automatically perform the OAuth exchange and refresh the OAuthAccessToken as needed.
- OAuthClientId : Set to the client Id assigned when you registered your app.
- OAuthClientSecret : Set to the client secret assigned when you registered your app.
- CallbackURL : Set to the redirect URI defined when you registered your app. For example: https://localhost:3333
With these settings, the provider obtains an access token from Adobe Target, which it uses to request data. The OAuth values are stored in the location specified by OAuthSettingsLocation, ensuring they persist across connections.
- Click Connect to authenticate with Adobe Target through OAuth
- Then, click Save Configuration to save the Code Assist MCP add-on
This process creates a .mcp configuration file that Cursor 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 Cursor.
Step 3: Connect the Code Assist MCP add-on to Cursor
- Download the Cursor desktop application and complete the sign-up flow for your account
-
From the top menu, click Settings to open the settings panel
-
In the left navigation, open the Tools & MCP tab and click Add Custom MCP
- Cursor opens an mcp.json file in the editor
- Add the code shown below and save the file
- After saving and testing your connection in the configuration wizard, click Next
- Select Cursor from the AI MCP Tool dropdown
- Follow the MCP Client Instructions to create the required folders for the MCP config
- Copy the displayed JSON code and paste it into your configuration file
- In Cursor, open the project folder you created with the mcp.json config
- The Code Assist MCP add-on should appear as Running under Installed MCP Servers
Option 1: Manually add the MCP configuration
{
"mcpServers": {
"cdata-local": {
"command": "C:/Program Files/Java/jdk-17/bin/java.exe",
"args": [
"-jar",
"C:/Program Files/CData/CData Code Assist MCP for Adobe Target/lib/cdata.mcp.adobetarget.jar",
"cdata_adobetarget"
]
}
}
}
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_adobetarget").
Option 2: Copy the MCP configuration from the CData Code Assist MCP for Adobe Target UI
Step 4: Query live Adobe Target data in Cursor
- From the top bar, click Toggle AI Pane to open the chat window
- Ask questions about your Adobe Target data using natural language. For example:
"List all tables available in my Adobe Target data connection."
Cursor is now fully integrated with CData Code Assist MCP for Adobe Target and can use the MCP tools exposed to explore schemas and execute live queries against Adobe Target.
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 Adobe Target data during development. When you're ready to move to production, CData Adobe Target 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.