Three tools is the whole surface, and that is the point — the JDBC driver turns SAP Hybris C4C into ordinary tables, so the model writes SELECT statements instead of learning an API shape. What you trade for that is a driver install and a licensing step before the first query, and a server that only reads: there is no write, update, or delete path here.
A local Java server that puts SAP Hybris C4C behind three SQL tools. CData's JDBC Driver for SAP Hybris C4C exposes the service as relational tables, and this server wraps the driver so a model can find a table, read its columns, and run a SELECT against live data without anyone writing the API calls.
- `saphybris_get_tables` returns the tables the driver exposes, as CSV with a header row
- `saphybris_get_columns` returns the columns on one table, in the same CSV shape
- `saphybris_run_query` executes a SQL SELECT statement
- The `saphybris` part is the `Prefix` you set in the property file (`Prefix=saphybris` in the sample), so several CData servers can sit in one client without their tool names colliding
- Leave `Tables=` empty to reach everything, or list table names there to expose only those
Build it yourself: clone the repository and run `mvn clean install`, which produces `CDataMCP-jar-with-dependencies.jar`. Install the CData JDBC Driver for SAP Hybris C4C separately and license it — `java -jar cdata.jdbc.saphybris.jar --license`, then name, email, and TRIAL or your key. Write a `sap-hybris-c4c.prp` file carrying `DriverClass=cdata.jdbc.saphybris.SAPHybrisDriver` and the JDBC URL from the driver's connection-string utility, and launch the server as `java -jar CDataMCP-jar-with-dependencies.jar sap-hybris-c4c.prp`. Transport is stdio, so the server runs on the same machine as the client.