I think I’m starting to see the potential.. So I could MPC cursor to my local Postgres (or, after some practice to build confidence, prod Postgres). Then use cursor to help debug.

This sounds risky but very useful if it works as intended!

Yes, I have used that workflow to fix a tricky data corruption issue earlier this week.

A buggy feature left DB in invalid state, I described the issue to Claude + Postgres MCP to both query the DB to analyze and then generate SQL scripts to fix, and validation and rollback scripts. Easy enough to do without the tooling... but with the tooling, it took probably a quarter or less of the time.

Is this not just hiding the "complexity" of SQL behind an LLM and hoping for the best?

If you know SQL and know what you're trying to find, what can the LLM do quickly that you couldn't just constructing a query to get what you want?

Alternatively if you don't know SQL, aren't you never going to learn it if every opportunity you have you bust out an LLM and hope for the best?

AS far as risk, I cannot imagine using an MCP with write capabilities to a DB, the Supabase one is read-only, which is perfect.