The Memorystore for Redis managed MCP extension lets you manage Memorystore for Redis instances from your AI-enabled development environments and AI agent platforms.

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 Memorystore for Redis 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/memorystore-for-redis

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

The following are sample use cases for the Memorystore for Redis MCP server:

• "Why do you create a Memorystore for Redis instance with authentication enabled?"

  By creating an instance and enabling the AUTH feature for it, incoming client connections must authenticate to connect to the instance. To connect, the client sends the AUTH command and an AUTH string, which is a randomly generated string that's unique for the instance. The AI agent of the Memorystore for Redis MCP server uses the create_instance MCP tool to create the instance.

• "Why do you view all active Memorystore for Redis instances in a specific region?"

  By listing these instances, you can ensure that resources match your current architecture. The AI agent of the Memorystore for Redis MCP server uses the list_instances MCP tool to retrieve a formatted list of instances in the specified region.

• "Why do you retrieve connection endpoints and operational metadata from a Memorystore for Redis instance in a specific region?"

  You need this information for application integration and system maintenance. The AI agent of the Memorystore for Redis MCP server uses the get_instance MCP tool to retrieve information about the instance, such as its discovery endpoint and replica count.

• "How can you optimize Memorystore for Redis for your data-intensive applications?"

  To increase both the CPU capacity and the memory throughput for these applications significantly, you can scale a Memorystore for Redis instance by increasing the instance's replica count. The AI agent of the Memorystore for Redis MCP server uses the update_instance MCP tool to update the replica count for the instance.

• "How can you protect your data from failures that might occur from either a Memorystore for Redis instance or the region where it's located?"

  Export a snapshot of the data in your instance to a Cloud Storage bucket. If a regional or instance failure occurs, then you can restore your data to a new instance to resume operations. The AI agent of the Memorystore for Redis MCP server uses the export_instance MCP tool to export your data.

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 Memorystore for Redis 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 Memorystore for Redis 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 Memorystore for Redis overview.
• Learn about MCP security and governance.