This document describes how to create a data agent in Cloud SQL for MySQL Studio using an agent context file. A data agent is associated with a single agent context file.
To learn about data agents, see Data agents overview.Before you begin
Complete the following prerequisites before creating an agent.
Enable required services
Enable the following services for your project:
Prepare a Cloud SQL instance
- Make sure that you have access to an existing Cloud SQL instance or create a new one. For more information, see Create instances for Cloud SQL.
- Populate the database with the data and schema that the end user wants to access.
Required roles and permissions
- Add an IAM user or service account to the cluster at the instance level. For more information, see Manage users with IAM database authentication.
- Grant the
cloudsql.studioUserandcloudsql.instanceUserroles to the IAM user at the project level. For more information, see Add IAM policy binding for a project. You must also grant database privileges to
an IAM user or service account. For more information, see Grant database privileges to an
individual IAM user or service account.
Grant executesql permission to Cloud SQL instance
To grant the executesql permission to Cloud SQL instance and enable the Cloud SQL
Data API, run the following command:
gcloud beta sql instances patch INSTANCE_ID --data-api-access=ALLOW_DATA_API
INSTANCE_ID with your Cloud SQL instance ID.
Create a data agent
To create a data agent, perform the following steps:
In the Google Cloud console, go to the Cloud SQL page.
Select an instance from the list.
In the navigation menu, click Cloud SQL Studio.
Sign in to Studio using Identity and Access Management (IAM) authentication.
In the Explorer pane, next to Data Agents, click View actions.
Click Create agent.
In Agent name, provide a unique agent name. The agent name is case-sensitive and can contain letters, numbers, hyphens, and underscores.
Optional. In Agent description, add a description for your agent.
Optional. Click Show Advanced Options and in Select a location, select a region for storing agent context.
Click Create.
Build agent context
After creating an agent, follow the steps in Build contexts using Gemini CLI to create an agent context file. You can then edit your agent to upload the context file.
Edit an agent
To edit a data agent, perform the following steps:
In the Google Cloud console, go to the Cloud SQL page.
Select an instance from the list.
In the navigation menu, click Cloud SQL Studio.
Sign in to Studio using Identity and Access Management (IAM) authentication.
In the Explorer pane, next to Data Agents, click View actions.
Click Edit agent.
Optional: Edit Agent description.
Click Browse in the Upload agent context file section, and select the agent context file.
Click Save.
Delete a data agent
To delete a data agent, perform the following steps:
In the Google Cloud console, go to the Cloud SQL page.
Select an instance from the list.
In the navigation menu, click Cloud SQL Studio.
Sign in to Studio using Identity and Access Management (IAM) authentication.
In the Explorer pane, next to Data Agents, click View actions.
Click Delete agent.
In the Delete agent confirmation dialog, enter the name of the agent.
Click Confirm to delete the agent.
What's next
- Learn more about data agents.
- Learn how to inspect and call a data agent.