Data catalogs, databases and SQL reads within a workgroup's limits. Changes wait for approval.
The screenshots show GateRook 2.0.0: the Amazon Athena 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 Athena, choose its card and select Continue to configure.
Choose the AWS region, workgroup and data catalog. Configure a suitable per-query data limit in the Athena workgroup because queries can incur scan charges.
Prepare AWS credentials with access to Athena, the required catalog metadata and the underlying data. Queries also need an authorized results location or the workgroup’s managed results configuration.
Enter a Name, for example athena-demo. Your AI app uses this name to choose the connection.
Enter Region and Workgroup. Set Data catalog to the catalog you use, such as AwsDataCatalog, and optionally enter a Default database.
Restrict Databases to the intended database names or catalog.database entries. Enter Query results location only when the workgroup does not already supply the required result handling.
Choose an AWS Profile or access key under Credentials source. For a dedicated role, fill Role to assume, configure its trust policy and retain 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.
A query can fail because of catalog, source-data or results-location permissions even after AWS sign-in succeeds. If the workgroup overrides client settings, its results location and other enforced settings take precedence.
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 Athena on the endpoint and passing its connection test, ask your AI app to use athena-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 databases available through athena-demo.”
- “Describe analytics.orders on athena-demo.”
- “Using athena-demo, count yesterday’s orders by status within the workgroup’s scan limit.”
| Tool | What it does | Starts as |
|---|---|---|
athena_list_catalogs | Data catalogs agents may use in the region. | Read only |
athena_list_databases | Databases agents may use in one data catalog. Pages with nextCursor. | Read only |
athena_list_tables | Tables and views of one database. Pages with nextCursor. | Read only |
athena_describe_table | Columns with types and comments, partition keys, the table type and its location. | Read only |
athena_query | One SELECT, WITH, VALUES, SHOW, DESCRIBE or EXPLAIN in the connection's workgroup. Athena's own IO plan checks a query first: it must write no table and read only databases of the connection. Reports the data scanned; pages with nextCursor. | Read only |
athena_execute | One INSERT, UPDATE, DELETE, MERGE, CREATE, ALTER, DROP, MSCK REPAIR TABLE, OPTIMIZE or VACUUM statement. You approve the exact text with the tables Athena's plan reads and writes. | Approval |
You can change each tool’s mode on the endpoint. Every call your AI makes appears in Activity.