Pub/Sub Managed MCP Extension

The Pub/Sub managed MCP extension lets you manage Pub/Sub resources and publish messages. You can create, list, get, update, and delete Pub/Sub topics, subscriptions, and snapshots, as well as publish messages to topics.

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 Pub/Sub 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/pubsub

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

The following are sample use cases for the Pub/Sub MCP server:

• Create a Pub/Sub pipeline that includes a topic with subscriptions.
• Create a subscription that uses Pub/Sub features such as message filtering.
• Add Single Message Transforms (SMTs) to your existing Pub/Sub pipeline.

• "Build a pipeline that consumes messages from Pub/Sub topic my-topic, filters out messages that have attribute priority=low, and writes the messages to Cloud Storage bucket my-bucket."
• "Create a subscription from topic my-topic to BigQuery table my-table, with failed deliveries sent to my-dead-letter-topic."

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 Pub/Sub 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 Pub/Sub 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 Pub/Sub overview.
• Learn about MCP security and governance.