Fieldglass answers are usually locked behind a report you have to request: who is on assignment, at what rate, under which supplier. Exposed as relational tables with a SELECT in front, those become questions you can just ask. The server never writes, so nothing you ask can disturb the programme — and the setup cost is a Maven build, a licensed driver install and a property file.
A local, read-only bridge between an assistant and SAP Fieldglass. CData's JDBC driver exposes SAP Fieldglass as relational SQL models; this server wraps the driver so a model can discover the tables and query them, and you can ask in plain language instead of writing SQL. It runs over stdio, so the client has to be on the same machine.
- `get_tables` lists the tables the driver exposes, returned as CSV with a header row
- `get_columns` lists the columns on one of those tables, in the same CSV shape
- `run_query` executes a SQL SELECT against live SAP Fieldglass data
- Tool names carry the prefix you set in the property file — the sample config uses `Prefix=sapfieldglass`
- Leaving `Tables=` blank exposes everything the driver can reach; naming tables there narrows it
Java and Maven: `mvn clean install` builds `CDataMCP-jar-with-dependencies.jar`. Separately install the CData JDBC Driver for SAP Fieldglass and license it by running `java -jar cdata.jdbc.sapfieldglass.jar --license`, entering `TRIAL` or a license key. Build the connection string with the same jar, authenticating in the browser if the source uses OAuth, then write a `.prp` file naming the driver path, the driver class `cdata.jdbc.sapfieldglass.SAPFieldglassDriver` and that JDBC URL. Point your client at `java -jar` with the built jar and the `.prp` file.
Build from source — clone the repository and build it, then point your client at the binary