Preview: This product is subject to the "Pre-GA Offerings Terms" in the General Service Terms section of the Service Specific Terms. Pre-GA products and features are available "as is" and might have limited support. For more information, see the launch stage descriptions.

The Datastream managed MCP extension lets you manage and monitor your Datastream resources, such as streams, connection profiles, and stream objects, from your AI application.

Google and Google Cloud managed MCP servers can be used in your AI applications with enterprise-ready governance, security, and access control.

1. In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

   Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

2. Get your administrator to grant you the MCP Tool User role (roles/mcp.toolUser) on the Google Cloud project. If you created a new project, then you already have the required permissions.

3. Ensure your administrator has enabled the Datastream API on the Google Cloud project.

This extension uses Google Application Default Credentials (ADC) to perform authentication. To login with ADC, run the following command in your terminal:

gcloud auth application-default login

For additional details, see the ADC documentation.

To install the extension, run the following command in your terminal:

gemini extensions install https://github.com/gemini-cli-extensions/datastream

To see a complete list of available tools and their schemas, see the Datastream MCP reference.

The following are example use cases for the Datastream MCP server:

• List, get, start, and delete streams in your project.
• List connection profiles to verify connectivity settings for sources and destinations.
• List and get details of specific stream objects to track replication progress and status.
• Use the get_operation tool to poll the status of operations such as starting or deleting a stream.

• List all running Datastream streams in project PROJECT_ID and location LOCATION.
• What's the status of the Datastream stream STREAM_ID in LOCATION?
• Start the Datastream stream STREAM_ID in LOCATION.
• List the objects being replicated by the stream projects/PROJECT_ID/locations/LOCATION/streams/STREAM_ID.
• Check the replication status for the source table TABLE_NAME in the stream projects/PROJECT_ID/locations/LOCATION/streams/STREAM_ID.

In the prompts, replace the following:

• PROJECT_ID with your Google Cloud project identifier.
• LOCATION with the location of your Google Cloud project.
• STREAM_ID with your Datastream stream identifier.
• TABLE_NAME with the name of your source table.

MCP introduces new security risks and considerations due to the wide variety of actions that you can take with MCP tools. To minimize and manage these risks, Google Cloud offers defaults and customizable policies to control the use of MCP tools in your Google Cloud organization or project.

For more information about MCP security and governance, see AI security and safety.

The Datastream MCP server doesn't have its own quotas. There is no limit on the number of call that can be made to the MCP server. You are still subject to the quotas enforced by the APIs called by the MCP server tools.

• Explore the Datastream remote MCP server reference documentation, which includes a list of all available tools, and the full input and output schema for each tool.
• See the Datastream overview.
• Learn about MCP security and governance.