Payment systems are the last place you want an assistant with write access, and this build simply does not have one — the query tool runs SELECT. That makes it usable for the questions merchants actually have, about takings, orders and customers, without the risk profile of a full integration. CData points at its paid products for read-write access, so this is the reporting path, and the licensed driver plus Maven build is the entry fee.
A local, read-only MCP server that exposes Square as a relational SQL model. It wraps CData's JDBC driver for Square, which presents the account's objects as tables, so an assistant can discover the schema and answer questions about live payments and merchant data with SELECT queries.
- The tables available in Square, returned as CSV with a header row — `get_tables`
- The columns on a chosen table, so a query uses real column names — `get_columns`
- A SQL SELECT executed against live Square data — `run_query`
- Tool names prefixed with the server name from your properties file, so several CData servers can sit side by side
- A `Tables` property that limits which tables are exposed at all
A Square account, plus CData's JDBC driver for Square downloaded and licensed separately — `java -jar cdata.jdbc.square.jar --license` takes your name, email and TRIAL or a license key. Java and Maven: `mvn clean install` builds the runnable JAR. Then a `.prp` file with the prefix, server name and version, the driver JAR path, the driver class `cdata.jdbc.square.SquareDriver`, and the JDBC connection string from the driver's connection-string utility, which opens a browser for OAuth. The client entry runs java with the JAR and the `.prp` path. Communication is over stdio, so client and server must be on the same machine. MIT licensed.
Build from source — clone the repository and build it, then deploy it and point your client at the endpoint