At Google I/O in May, we launched an experimental Firebase Model Context Protocol (MCP) server to help AI agents understand and manage your Firebase project, resources, and data all through natural language prompts that you provide — for example, “show items in the cart collection” even “delete a document from my Firestore collection”.

The Model Context Protocol (MCP) extends the capabilities of AI tools used by millions of developers every day. By connecting to MCP servers, coding agents can directly access data and take action with integrated services. The Firebase CLI includes an MCP server to connect to your favorite IDEs and AI tools.

We’ve made improvements to the Firebase MCP server since launch, including:

• New MCP tools leveraging Gemini in Firebase (like dataconnect_generate_schema to generate a schema for Firebase Data Connect).
• New MCP tools covering many more Firebase products (like Cloud Functions for Firebase and Crashlytics)
• More consolidated, streamlined MCP tools (like a single validate_security_rules tool that can be used across Firestore, Storage, and Realtime Database).
• New deploy MCP prompt to deploy your web app to a Firebase hosting product.

Thanks to your feedback, we’ve improved the quality and stability of the Firebase MCP server, and we’re happy to announce that the Firebase MCP server is graduating from its experimental phase.

But wait, there’s more!

Introducing the new Firebase extension for Gemini CLI

Firebase is also integrating with the Gemini CLI, Google’s open-source AI agent that brings the power of Gemini models directly into your terminal. Starting today, Firebase has an official extension in the Gemini CLI gallery, alongside many other new helpful extensions from Google (like the Flutter extension). This new extension bundles our graduated MCP server together with additional context files (custom instructions for LLMs), giving you a powerful, integrated way to work with your Firebase project, resources, and data.

Getting started with the Firebase extension for Gemini CLI

To get started, just type the following into your command line:

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

What can this extension do for you?

Our goal is to reduce friction in your common development tasks, whether it’s adding database support, deploying your app, or even adding genAI features to your app!

• /firebase:init
  This command provides you options like setting up backend services for your app and implementing genAI features that access the Gemini API.

  With a single command, you can set up Firebase for your app. This command helps set up Firestore as your database and Firebase Authentication as a way to secure your app and your user’s data. It also helps you to deploy your app in one go!
  If you’re building an AI feature in your app, this command can give you a head start. It sets up Firebase AI Logic and writes the code to easily and securely access the Gemini API directly from your mobile and web apps. Learn more here.

• /firebase:deploy
  This command deploys your application to a Firebase hosting service regardless of whether it’s a static app or a full-stack app. The prompt instructs the AI to analyze your code and choose the correct Firebase hosting service based on the app’s needs. No more decision-making or misconfigured services.

• /firebase:consult
  This command accesses detailed up-to-date documentation for the Firebase platform. Just ask a question and the model will find an answer grounded in the latest Firebase documentation.

All these commands work with existing Firebase projects. But if you’re new to Firebase, don’t worry! All these commands can also help you set up Firebase in your app from scratch!

Why use Gemini CLI to build your Firebase app?

You spend a large portion of your time in the terminal. This new Firebase extension for Gemini CLI is a step towards giving your Gemini CLI environment a practical, working understanding of Firebase.

The exciting part is that we’ve really improved how well your coding agent handles complex, long-running tasks. Things like setting up a new database or deploying an app have always been tricky because they take time and often need your approval at certain steps. The new commands in the Gemini CLI extension are designed to manage that entire process—from creating resources to managing them, and even cleaning them up if needed.

Our goal is to make this a helpful, low-friction way to bring AI-assisted development into your daily flow. It’s not going to solve every problem, but we think it can make these specific setup and deployment tasks a lot smoother.

What’s next

Firebase is always trying to make it easier for you to build and manage your apps. And we couldn’t do that without your crucial feedback. When you try out the new extension, please let us know what you think in our GitHub repository.

To stay updated on improvements, don’t forget to star the GitHub repository!

We’re excited to see what you build next!