Schemas, tables and SQL queries in read-only transactions. Changes wait for approval.
The screenshots show GateRook 2.0.0: the Amazon Redshift 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 Amazon Redshift, choose its card and select Continue to configure.
Find the AWS region, provisioned cluster identifier or Serverless workgroup, and database name. This connector uses the Redshift Data API.
Prepare AWS credentials allowed to call the Data API and the chosen database sign-in method. The database identity also needs permissions on the schemas and tables the AI will read.
Enter a Name, for example redshift-demo. Your AI app uses this name to choose the connection.
Enter Region, choose the warehouse Type, and fill Cluster identifier or Workgroup. Enter the intended Database.
Under Database sign-in, choose the AWS identity, a database user with temporary credentials for a cluster, or the user stored in a Secrets Manager secret. Supply Database user or Secret when the selected option asks for it.
Select your Credentials source and supply an AWS Profile or access-key credentials. If using Role to assume, configure its trust policy and keep the recommended Session policy.
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.
Check that the cluster or workgroup supports and permits Data API access. For authentication failures, verify the AWS permissions and selected database identity separately; a Secrets Manager sign-in must reference the correct secret.
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 Amazon Redshift on the endpoint and passing its connection test, ask your AI app to use redshift-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 on redshift-demo.”
- “Describe the orders table in the public schema on redshift-demo.”
- “Using redshift-demo, count orders by status without modifying any data.”
| Tool | What it does | Starts as |
|---|---|---|
redshift_list_schemas | Schemas of the connection's database. | Read only |
redshift_list_tables | Tables, views and their kinds in one schema. | Read only |
redshift_describe_table | Columns of one table or view with their types, nullability and defaults. | Read only |
redshift_query | One SELECT, WITH, SHOW or EXPLAIN, run in a READ ONLY transaction that is rolled back. Values as :name parameters. Pages with nextCursor. | Read only |
redshift_execute | One INSERT, UPDATE, DELETE, MERGE or DDL statement. You approve the exact text with Redshift's plan and row estimate. | Approval |
You can change each tool’s mode on the endpoint. Every call your AI makes appears in Activity.