Tables and GoogleSQL or PostgreSQL queries in read-only transactions. Changes wait for approval.
The screenshots show GateRook 2.0.0: the Google Cloud Spanner 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 Google Cloud Spanner, choose its card and select Continue to configure.
Find the Google Cloud project ID, Spanner instance ID and database ID. GateRook supports both GoogleSQL and PostgreSQL-dialect databases.
Use Application Default Credentials on this computer or a service account key. A service account that only reads can use the Spanner Database Reader role on the intended database.
Enter a Name, for example spanner-demo. Your AI app uses this name to choose the connection.
Enter Project, Instance and Database using their IDs, rather than display names.
Under Authentication, select Existing Google sign-in (ADC) or Service account key (JSON). For ADC, prepare a local sign-in with gcloud auth application-default login; for a key, enter its JSON in Service account key.
Set Service account to impersonate when using a dedicated identity. If your database uses fine-grained access control, enter its Database role under Advanced and grant the identity access to that role.
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.
For access errors, check the project and database IDs, the identity used by ADC, and its database permissions. Impersonation also requires permission for the signed-in identity to obtain tokens for the named service account.
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 Google Cloud Spanner on the endpoint and passing its connection test, ask your AI app to use spanner-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 and views available on spanner-demo.”
- “Describe the primary key and indexes of Orders on spanner-demo.”
- “Using spanner-demo, count orders by status with a read-only query.”
| Tool | What it does | Starts as |
|---|---|---|
spanner_list_tables | Tables and views of the database, with their schema, kind and the parent an interleaved table belongs to. | Read only |
spanner_describe_table | Columns with their types, the primary key, indexes, the interleaving parent and, where the credentials may read it, the table's DDL. | Read only |
spanner_query | One GoogleSQL or PostgreSQL-dialect query, run in a read-only transaction in which Spanner refuses every change. Pages with nextCursor at the first page's snapshot; add ORDER BY for stable pages. | Read only |
spanner_execute | One INSERT, UPDATE or DELETE, committed in its own transaction, or one schema change (CREATE, ALTER, DROP). You approve the exact text. | Approval |
You can change each tool’s mode on the endpoint. Every call your AI makes appears in Activity.