Read queries, schemas and tables. Changes wait for approval.
The screenshots show GateRook 2.0.0: the Snowflake 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 Snowflake, choose its card and select Continue to configure.
Prepare a Snowflake account identifier, user, role and warehouse. Use a role limited to the data the AI should read; the role is an important access boundary.
GateRook supports an RSA key pair or a programmatic access token for this connector. Register the public key on the Snowflake user, or create a token for that user with suitable role and network restrictions.
Enter a Name, for example snowflake-demo. Your AI app uses this name to choose the connection.
Enter Account identifier as organization-account, not a web URL, and enter User. Enable Private connectivity only when your computer can reach the configured private endpoint.
Choose Key pair under Sign in with and supply Private key (PEM), or choose Programmatic access token and enter the token. The key must be an unencrypted RSA private key of at least 2048 bits.
Set Warehouse and Role. Use Database and Schema for the default namespace, and narrow Tables with names such as ANALYTICS.PUBLIC.ORDERS or a deliberate pattern.
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.
A key-pair error can mean the key does not match the user’s registered public key. A token may be refused by the user’s network policy. If sign-in works but a query fails, check warehouse access and the selected role’s grants.
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 Snowflake on the endpoint and passing its connection test, ask your AI app to use snowflake-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 schemas available through snowflake-demo.”
- “Describe ANALYTICS.PUBLIC.ORDERS on snowflake-demo.”
- “Using snowflake-demo, count orders by status with the configured warehouse and role.”
| Tool | What it does | Starts as |
|---|---|---|
snowflake_list_schemas | Schemas and tables agents may use in one database, with row counts and sizes, from its INFORMATION_SCHEMA. | Read only |
snowflake_describe_table | Columns, types, nullability, defaults and comments of one table or view, with its row count and size. | Read only |
snowflake_query | One SELECT, WITH … SELECT, SHOW or DESCRIBE. Snowflake plans a SELECT first, and one whose plan changes data is refused. Rows are capped by the endpoint. | Read only |
snowflake_execute | One INSERT, UPDATE, DELETE, MERGE, TRUNCATE or DDL statement. You approve the exact statement. | Approval |
You can change each tool’s mode on the endpoint. Every call your AI makes appears in Activity.