home / mcp / sap hybris c4c mcp server

SAP Hybris C4C MCP Server

This read-only MCP Server allows you to connect to SAP Hybris C4C data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "cdatasoftware-sap-hybris-c4c-mcp-server-by-cdata": {
      "command": "java",
      "args": [
        "-jar",
        "/PATH/TO/CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/sap-hybris-c4c.prp"
      ]
    }
  }
}

You can query live SAP Hybris C4C data through a lightweight MCP server that wraps the CData JDBC Driver. This server exposes data via a simple MCP interface, so you can ask natural-language questions and get up-to-date results without writing SQL. Data access is read-only, designed for conversational querying and easy integration with MCP clients like Claude Desktop.

How to use

Use an MCP client on the same machine as the server to connect to the local MCP endpoint. Start the server, then load the MCP into your client configuration so you can ask questions like, “What are my open Hybris C4C opportunities this quarter?” or “Show me the top accounts by revenue.” The client will invoke the server’s tools behind the scenes, returning results in a familiar conversational format. You do not need to know SQL; you simply describe what you want to know and the MCP server translates your request into queries against SAP Hybris C4C via the CData JDBC Driver.

How to install

Prerequisites: you need Java installed on your machine and Maven for building the MCP server. Ensure a compatible JRE/JDK is available and that you have a working network connection for any required dependencies.

1. Clone the MCP server project and navigate into it.

2. Build the server artifact.

git clone https://github.com/cdatasoftware/sap-hybris-c4c-mcp-server-by-cdata.git
cd sap-hybris-c4c-mcp-server-by-cdata
mvn clean install

3. Install the CData JDBC Driver for SAP Hybris C4C from the CData site and license it according to your platform. Follow the driver’s licensing steps to enable local access.

4. Create a JDBC connection file (a .prp file) that configures the driver to connect to SAP Hybris C4C. This file includes the JDBC URL and optional tables you want to expose.

5. Run the MCP server locally using the built JAR and your .prp file.

Additional configuration and startup details

To start the MCP server on your machine, use the following pattern. Replace paths with your actual locations and the name of your .prp configuration file.

java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/sap-hybris-c4c.prp
```
> Note: The server runs via stdio, so it expects a client on the same machine. For persistent access from multiple clients, run the server on the host with proper access controls and ensure the MCP client is configured to connect to the local stdio endpoint.

Security and troubleshooting notes

If you cannot see or connect to the MCP server from your client, ensure you have fully restarted the client after starting the server. Verify that the .prp file contains the correct JDBC URL and credentials. If you run into data retrieval issues, verify the driver license is active and the connection string is valid. When issues arise, check that the server process is running and that no firewall rules block the local communication.

Tools and usage patterns

Once configured, your MCP client can use built-in tools to explore and query the data. Typical actions include listing available tables, listing columns for a table, and running read-only queries to retrieve results for your questions.

JSON-RPC Request Examples

You can script requests to the MCP server using the JSON-RPC surface exposed by the client. The server’s tools support querying table metadata and executing read-only queries, returning results in a structured format.

Available tools

get_tables

Retrieves a list of tables available in the data source. The output is CSV with column headers on the first line.

get_columns

Retrieves a list of columns for a specified table. The output is CSV with column headers on the first line.

run_query

Executes a SQL SELECT query against the exposed data source and returns the results.