Cloud SQL for MySQL uses GateRook’s MySQL 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 MySQL 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 MySQL, choose its card and select Continue to configure.
Prepare a Cloud SQL MySQL database user and password. Connect directly over an authorized network path or run the Cloud SQL Auth Proxy locally.
The proxy’s Google Cloud identity and the MySQL user are separate. Keep the proxy’s listener on loopback and leave the proxy running.
Enter a Name, for example cloud-sql-mysql-demo. Your AI app uses this name to choose the connection.
Choose Cloud SQL for MySQL. Enter a Name, database User and Password, and the instance Host and Port. For the local proxy use 127.0.0.1 and its actual listening port.
For a direct TLS connection, configure SSL mode and CA certificate (PEM) for the instance. On a loopback Auth Proxy, keep Allow public key retrieval enabled when using MySQL 8.4 password authentication; the proxy secures the remote hop.
Select Load databases and choose the databases your AI should access. Use Database allowlist if you need a narrower boundary within that selection.
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 the local proxy connection fails, check proxy authorization and database credentials separately. With MySQL 8.4 and later, a public-key-retrieval error requires reviewing Allow public key retrieval for that loopback proxy connection.
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 MySQL on the endpoint and passing its connection test, ask your AI app to use cloud-sql-mysql-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 MySQL database.”
- “Describe the columns and indexes of the selected Cloud SQL table.”
- “Count today’s records by status in my Cloud SQL MySQL connection.”
| Tool | What it does | Starts as |
|---|---|---|
sql_list_schemas | List tables and views in the selected MySQL-compatible 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 MySQL-compatible read statement in a read-only transaction, then roll it back. Function allowlists, database permissions and output limits apply. | Read only |
sql_execute | Run one supported data or schema change with Approval by default. Database permissions and the environment policy apply; schema changes can commit implicitly. | Approval |
You can change each tool’s mode on the endpoint. Every call your AI makes appears in Activity.