Cloud SQL for PostgreSQL uses GateRook’s PostgreSQL connector. With a database user and password, through the instance's IP and server CA certificate, or the Cloud SQL Auth Proxy on this computer.
The screenshots show GateRook 2.0.0: the Cloud SQL for PostgreSQL form, the endpoint selector, and this connector’s actual tool preview. The form and preview have not been saved. Select a screenshot to open it at full size.
1. Create a connection and enter the settings
In GateRook, open Connections, select Add connection, search for Cloud SQL for PostgreSQL, choose its card and select Continue to configure.
Have a Cloud SQL PostgreSQL database user and password ready. Choose a direct network path to the instance or run the Cloud SQL Auth Proxy on this computer.
The proxy authenticates to Google Cloud separately from the database login. Keep its listener on loopback and leave it running while GateRook uses the connection.
Enter a Name, for example cloud-sql-postgresql-demo. Your AI app uses this name to choose the connection.
Choose Cloud SQL for PostgreSQL. Enter a Name, the instance Host and Port, and database User and Password. For a local Auth Proxy, use 127.0.0.1 and the port that proxy listens on.
For direct TLS access, configure SSL mode and CA certificate (PEM) to match the instance’s certificate policy. For a loopback Auth Proxy, Auto can use its local connection while the proxy encrypts the remote connection.
Select Load databases, then choose only the databases this connection should expose. If loading fails because the account cannot connect to postgres, set Discovery database to a database it can access and try again.
Choose Development, Staging or Production to match the service. Review the connector’s limit and access settings before continuing.

2. Test the connection and add it to an endpoint
Select Continue to test. GateRook checks the settings from your computer. Review the result and resolve any connection, certificate or permission error before continuing.
If a proxy connection fails, check that the proxy is running and can authenticate to Google Cloud, then check the separate database credentials. Private IP connections still require network reachability.
After the test passes, select Continue to add to an endpoint. Choose the endpoint your AI app uses, review its tool modes, then select Save connection. GateRook offers default as the starter endpoint.

3. Use the connection from your AI IDE
After saving Cloud SQL for PostgreSQL on the endpoint and passing its connection test, ask your AI app to use cloud-sql-postgresql-demo, or the name you chose. If its tools are missing, confirm the endpoint assignment and refresh the MCP connection or start a new chat.
The preview below shows this connector’s default tools before saving. The table explains what each tool can do; connection settings, credentials and endpoint policies can restrict access further.

Start with a small read request. Replace example resource names with existing resources your connection may access. Open Activity after the call to inspect its connection, tool, arguments, policy decision and result metadata.
Ask your AI, for example
- “List the tables in my Cloud SQL PostgreSQL database.”
- “Describe the selected Cloud SQL PostgreSQL table.”
- “Show the most recent ten records from the table I select in Cloud SQL.”
| Tool | What it does | Starts as |
|---|---|---|
sql_list_schemas | List schemas, tables and views in the selected PostgreSQL database, within the connection and policy restrictions. | Read only |
sql_describe_table | Describe a table’s columns, types, keys and indexes where available. | Read only |
sql_query | Run one validated PostgreSQL read statement in a read-only transaction, then roll it back. Function allowlists, database permissions and output limits apply. | Read only |
sql_execute | Run supported data or schema changes with Approval by default. Database permissions and the environment policy determine which changes are allowed. | Approval |
You can change each tool’s mode on the endpoint. Every call your AI makes appears in Activity.