Source URL: https://cloud.google.com/blog/products/databases/gemini-cli-extensions-for-google-data-cloud/
Source: Cloud Blog
Title: Launching Gemini CLI extensions for Google Data Cloud
Feedly Summary: In June, Google introduced Gemini CLI, an open-source AI agent that brings the power of Gemini directly into your terminal. And today, we’re excited to announce open-source Gemini CLI extensions for Google Data Cloud services.
Building applications and analyzing trends with services like Cloud SQL, AlloyDB and BigQuery has never been easier — all from your local development environment! Whether you’re just getting started or a seasoned developer, these extensions make common data interactions such as app development, deployment, operations, and data analytics more productive and easier. So, let’s jump right in!
Using a Data Cloud Gemini CLI extension
Before you get started, make sure you have enabled the APIs and configured the IAM permissions required to access specific services.
To retrieve the newest functionality, install the latest release of the Gemini CLI (v0.6.0):
npm install -g @google/gemini-cli@latest
Next, install the extension:
gemini extensions install https://github.com/gemini-cli-extensions/
Replace <EXTENSION> with the name of the service you want to use. For example, alloydb, cloud-sql-postgresql or bigquery-data-analytics.
Before starting the Gemini CLI, you’ll need to configure the extension to connect with your Google Cloud project by adding the required environment variables. The table below provides more information on the configuration required.
Extension Name
Description
Configuration
alloydb
Create resources and interact with AlloyDB for PostgreSQL databases and data.
Configuration
alloydb-observability
Monitor database performance and health for AlloyDB for PostgreSQL databases.
Configuration
bigquery-data-analytics
Discover and ask questions from BigQuery data.
Configuration
bigquery-conversational-analytics
Dive deeper , discover insights from BigQuery data using the built-in stateless agent offered by Conversational Analytics API
Configuration
cloud-sql-mysql
Connect and interact with a Cloud SQL for MySQL database and data.
Configuration
cloud-sql-mysql-observability
Monitor database performance and health for Cloud SQL for MySQL databases.
Configuration
cloud-sql-postgresql
Create resources and interact with Cloud SQL for PostgreSQL databases and data.
Configuration
cloud-sql-postgresql-observability
Monitor database performance and health for Cloud SQL for PostgreSQL databases.
Configuration
cloud-sql-sqlserver
Connect and interact with a Cloud SQL for SQL Server database and data.
Configuration
cloud-sql-sqlserver-observability
Monitor database performance and health for Cloud SQL for SQL Server databases.
Configuration
dataplex
Connect to Dataplex Universal Catalog to discover, manage, monitor, and govern data and AI artifacts across your data platform.
Configuration
firestore-native
Connect and interact with Firestore databases, collections, and documents.
Configuration
looker
Connect to Looker to query data, run Looks, and create dashboards.
Configuration
mysql
Connect and interact with a MySQL database and data.
Configuration
postgres
Connect and interact with a PostgreSQL database and data.
Configuration
spanner
Connect and interact with a Spanner database and data.
Configuration
sql-server
Connect and interact with a SQL Server database and data.
Configuration
mcp-toolbox
Load custom tools using MCP Toolbox for Databases.
Configuration
Now, you can start the Gemini CLI using command gemini. You can view the extensions installed with the command /extensions
You can list the MCP servers and tools included in the extension using command /mcp list
Using the Gemini CLI for Cloud SQL for PostgreSQL extension
The Cloud SQL for PostgreSQL extension lets you perform a number of actions. Some of the main ones are included below:
Create instance: Creates a new Cloud SQL instance for PostgreSQL (and also MySQL, or SQL Server)
List instances: Lists all Cloud SQL instances in a given project
Get instance: Retrieves information about a specific Cloud SQL instance
Create user: Creates a new user account within a specified Cloud SQL instance, supporting both standard and Cloud IAM users
Curious about how to put it in action? Like any good project, start with a solid written plan of what you are trying to do. Then, you can provide that project plan to the CLI as a series of prompts, and the agent will start provisioning the database and other resources:
After configuring the extension to connect to the new database, the agent can generate the required tables based on the approved plan. For easy testing, you can prompt the agent to add test data.
Now the agent can use the context it has to generate an API to make the data accessible.
As you can see, these extensions make it incredibly easy to start building with Google Cloud databases!
Using the BigQuery Analytics extensions
For your analytical needs, we are thrilled to give you a first look at the Gemini CLI extension for BigQuery Data Analytics. We are also excited to give access to the Conversational Analytics API through the BigQuery Conversational Analytics extension. This is the first step in our journey to bring the full power of BigQuery directly into your local coding environment, creating an integrated and unified workflow.
With this extension you can
Explore data: Use natural language to search for your tables.
Analyze: Ask business questions on the data and generate intelligent insights.
Dive deeper: Use conversational analytics APIs to dive deeper into the insights.
And extend: Use other tools or extensions to extend into advanced workflows like charting, reporting, code management, etc.
This initial release provides a comprehensive suite of tools to Gemini CLI:
Metadata tools: Discover and understand the BigQuery data landscape.
Query execution tool: Run any BigQuery query and get the results back, summarized to your console.
AI-powered forecasting: Leverage BigQuery’s built-in AI.Forecast function for powerful time-series predictions directly from the command line.
Deeper data Insights: The“ask_data_insights” tool provides access to server-side BigQuery agent for richer data insights.
And more …
[Note: To use the conversational analytics extension you need to enable additional APIs. Refer to documentation for additional info.]
Here is an example journey with analytics extensions:
Explore and analyze your data , e.g.,
code_block
<ListValue: [StructValue([(‘code’, ‘> find tables related to PyPi downloads\r\n \r\n✦ I found the following tables related to PyPi downloads:\r\n\r\n * file_downloads: projects/bigquery-public-data/datasets/pypi/tables/file_downloads\r\n * distribution_metadata: projects/bigquery-public-data/datasets/pypi/tables/distribution_metadata’), (‘language’, ”), (‘caption’, <wagtail.rich_text.RichText object at 0x7ff67c5c7280>)])]>
code_block
<ListValue: [StructValue([(‘code’, ‘> Using bigquery-public-data.pypi.file_downloads show me top 10 downloaded pypi packages this month \r\n\r\n✦ Here are the top 10 most downloaded PyPI packages this month:\r\n\r\n 1. boto3: 685,007,866 downloads\r\n 2. botocore: 531,034,851 downloads\r\n 3. urllib3: 512,611,825 downloads\r\n 4. requests: 464,595,806 downloads\r\n 5. typing-extensions: 459,505,780 downloads\r\n 6. certifi: 451,929,759 downloads\r\n 7. charset-normalizer: 428,716,731 downloads\r\n 8. idna: 409,262,986 downloads\r\n 9. grpcio-status: 402,535,938 downloads\r\n 10. aiobotocore: 399,650,559 downloads’), (‘language’, ”), (‘caption’, <wagtail.rich_text.RichText object at 0x7ff67c5c7af0>)])]>
Run deeper insights
Using “ask_data_insights” to trigger an agent on the BigQuery (Conversational analytics API) to answer your questions. The server side agent is smart enough to gather additional context about your data and offer deeper insights into your questions.
You can go further and generate charts and reports by mixing BigQuery data with your local tools. Here’s a prompt to try:
”using bigquery-public-data.pypi.file_downloads can you forecast downloads for the last four months of 2025 for package urllib3? Please plot a chart that includes actual downloads for the first 8 months, followed by the forecast for the last four months”
Get started today!
Ready to level up your Gemini CLI extensions for our Data Cloud services? Read more in the extensions documentation. Check out our templates and start building your own extensions to share with the community!
AI Summary and Description: Yes
Summary: The text presents the introduction of Google’s Gemini CLI and its new extensions for Google Data Cloud services. It highlights the integration of AI capabilities directly into development environments, facilitating tasks such as application development, data analytics, and cloud resource management in a more streamlined manner.
Detailed Description: The introduction of the Gemini CLI and its extensions signifies a significant step for developers working with Google Cloud services, enhancing their capability to build and analyze applications effectively. Here are the key components of the text:
– **Gemini CLI Overview**:
– An open-source AI agent that allows interaction with Google Cloud services directly from the terminal.
– Enables seamless application development and data analysis for all skill levels.
– **Key Features of the Extensions**:
– **Ease of Use**: Streamlined commands for various operations like creating instances, monitoring performance, and data interactions.
– **Data Cloud Services**: Extensions available for services such as Cloud SQL, AlloyDB, and BigQuery facilitate straightforward integration and operational capabilities.
– **Installation Process**:
– Clear steps outlined for installing the Gemini CLI and its extensions, including necessary API and IAM permissions configuration.
– **Available Extensions**: The document provides descriptions for multiple extensions, including:
– **AlloyDB Extensions**: Interact and monitor PostgreSQL database performance.
– **BigQuery Data Analytics Extensions**: Analyze data using natural language queries and AI.
– **Cloud SQL Extensions**: Manage MySQL, PostgreSQL, and SQL Server databases easily.
– **Functionality**: Users can:
– Execute commands for data exploration.
– Generate intelligent insights and visualizations.
– Leverage built-in AI functions for analytics, making the CLI a powerful tool for developers.
– **Interactivity and Flexibility**: The extensions allow developers to mix BigQuery data with local tools for customized workflows, such as generating charts and reports or conducting AI-powered forecasts.
– **Practical Implications**:
– Enhances productivity and accelerates development cycles.
– Empowers organizations to integrate machine learning and data analytics into their operations effectively.
– Supports governance and compliance through structured data management features.
This comprehensive suite introduces a novel toolset for developers and data analysts engaged in cloud computing, providing new dimensions in the management and analysis of cloud-based data environments.