The value of putting channel metrics behind SQL is combination: comparing periods, filtering by a dimension and sorting by something the dashboard does not offer as a view. The assistant discovers the columns itself, so you do not have to know YouTube's metric names to ask. Read-only removes any worry about pointing it at a live channel, and the setup — licensed driver, Maven build, one Google authentication — is the same shape as every other CData source.
A local, read-only MCP server that exposes YouTube Analytics as a relational SQL model. It wraps CData's JDBC driver for YouTube Analytics, which presents channel and video metrics as tables, so an assistant can find the right dimensions and query them live instead of reading a dashboard.
- The tables available in YouTube Analytics, returned as CSV with a header row — `get_tables`
- The columns on a chosen table, so a query uses the real metric and dimension names — `get_columns`
- A SQL SELECT executed against live YouTube Analytics data — `run_query`
- Tool names prefixed with the server name from your properties file, so multiple CData servers coexist in one client
- A `Tables` property that restricts which tables are exposed
A YouTube channel and account, plus CData's JDBC driver for YouTube Analytics downloaded and licensed separately — `java -jar cdata.jdbc.yanalytics.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.yanalytics.YAnalyticsDriver`, and the JDBC connection string from the driver's connection-string utility, which opens a browser for the Google OAuth step. 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 point your client at the binary