Build SAP-Powered Applications in Gemini Code Assist with CData Code Assist MCP
Gemini Code Assist is an AI-powered coding companion that integrates intelligent code generation into everyday development workflows. With support for MCP, Gemini Code Assist can connect to live enterprise data sources directly from Visual Studio Code, enabling natural language interaction with structured data without switching context or manually writing data access code.
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.
This guide walks through installing the CData Code Assist MCP for SAP ERP, configuring the connection to SAP, connecting the Code Assist MCP add-on to Gemini Code Assist, and querying live SAP data from within the editor.
About SAP Data Integration
CData provides the easiest way to access and integrate live data from SAP. Customers use CData connectivity to:
- Access every edition of SAP, including SAP R/3, SAP NetWeaver, SAP ERP / ECC 6.0, and SAP S/4 HANA on premises data that is exposed by the RFC.
- Perform actions like sending IDoc or IDoc XML files to the server and creating schemas for functions or queries through SQL stored procedures.
-
Connect optimally depending on where a customer's SAP instance is hosted.
- Customers using SAP S/4HANA cloud public edition will use SAP NetWeaver Gateway connectivity
- Customers using SAP S/4HANA private edition will use either SAP ERP or SAP NetWeaver Gateway connectivity.
While most users leverage our tools to replicate SAP data to databases or data warehouses, many also integrate live SAP data with analytics tools such as Tableau, Power BI, and Excel.
Getting Started
Prerequisites
Before starting, ensure the following requirements are met:
- Visual Studio Code is installed on the machine
- Gemini Code Assist extension is enabled in Visual Studio Code
- CData Code Assist MCP for SAP ERP has been installed
- Access to SAP
Note: Gemini Code Assist must already be set up and functional in Visual Studio Code before configuring MCP servers. MCP servers are accessed when Gemini Code Assist is running in Agent mode.
Step 1: Download and install the CData Code Assist MCP for SAP ERP
-
To begin, download the CData Code Assist MCP for SAP ERP
- 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, the Code Assist MCP add-on is ready for configuration by connecting to SAP.
Step 2: Configure the connection to SAP
-
After installation, open the CData Code Assist MCP for SAP ERP configuration wizard
NOTE: If the wizard does not open automatically, search for "CData Code Assist MCP for SAP ERP" 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_saperp") and click OK
-
Enter the appropriate connection properties in the configuration wizard
You can connect to SAP systems using either librfc32.dll, librfc32u.dll, NetWeaver, or Web Services (SOAP). Set the ConnectionType connection property to CLASSIC (librfc32.dll), CLASSIC_UNICODE (librfc32u.dll), NETWEAVER, or SOAP.
If you are using the SOAP interface, set the Client, RFCUrl, SystemNumber, User, and Password properties, under the Authentication section.
Otherwise, set Host, User, Password, Client, and SystemNumber.
Note: We do not distribute the librfc32.dll or other SAP assemblies. You must find them from your SAP installation and install them on your machine.
For more information, see this guide on obtaining the connection properties needed to connect to any SAP system.
- Click Connect to authenticate with SAP
-
Then, click Save Configuration to save the Code Assist MCP add-on
This process creates a .mcp configuration file that Gemini Code Assist will reference when launching the Code Assist MCP add-on. With the Code Assist MCP add-on configured, it is ready to connect to Gemini Code Assist.
Step 3: Connect the Code Assist MCP add-on to Gemini Code Assist
- Ensure Visual Studio Code is installed and the Gemini Code Assist extension is enabled
-
From the configuration wizard, click Next after saving and testing the connection
-
Select Gemini Code Assist from the AI MCP Tool dropdown
-
Click Copy JSON to copy the generated MCP configuration to the clipboard
-
Paste the copied JSON into the appropriate configuration file based on the desired scope:
- User-level: Configuration applies across all projects for the current user
- Workspace-level: Configuration applies only to the current workspace or project
NOTE: The configuration includes the path to Java 17+ executable and the CData Code Assist MCP add-on JAR file. The final argument must match the MCP configuration name saved in the wizard (e.g. "cdata_saperp").
- Save the configuration file and restart Visual Studio Code if necessary
Step 4: Query live SAP data in Gemini Code Assist
-
Open Visual Studio Code and select Gemini Code Assist in the activity bar
-
Enter /mcp in the chat prompt to verify the connection status. The SAP Code Assist MCP add-on should appear with a green connection indicator
-
Ask questions about SAP data using natural language. For example:
"Provide the list of all tables available in my SAP data connection."
-
Generate code that works with live SAP data. For example:
"Write a function to retrieve records from the MARA table where MANDT matches a given value."
Gemini Code Assist is now fully integrated with the CData Code Assist MCP add-on and can use the MCP tools exposed to explore schemas, execute live queries against SAP, and generate data-aware code.
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 SAP data during development. When you're ready to move to production, CData SAP 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.