[MCP] Always include core MCP tools + return instructions from firebase_init #9045
Conversation
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Summary of Changes
Hello @fredzqm, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!
This pull request refactors the Firebase initialization process to centralize and return post-setup instructions from various features. Instead of features logging instructions directly, they now append them to a shared instructions array within the setup object. This allows the firebase_init Managed Control Plane (MCP) tool to collect and present a unified list of "next steps" to the user upon successful project initialization, improving the user experience by providing clear guidance after setup.
Highlights
- Centralized Instruction Collection: The
Setupinterface now includes aninstructionsarray, allowing various Firebase initialization features to append guidance and next steps. This centralizes the collection of post-setup information. - Unified Output for MCP Tool: The
firebase_initManaged Control Plane (MCP) tool has been updated to gather all instructions added by features to thesetup.instructionsarray and present them as a consolidated 'To get started' guide in its final output. - Refactored Data Connect Setup: The Data Connect feature's
postSetupfunction, which previously handled instruction logging, has been removed. Its logic has been integrated directly into theactuatefunction, streamlining the initialization flow. - Comprehensive Test Updates: Numerous test files across different Firebase features (e.g., Data Connect, Firestore, Functions, Genkit, Storage) have been updated to correctly initialize the
instructions: []property in theirsetupmock objects, ensuring compatibility with the new instruction collection mechanism.
Using Gemini Code Assist
The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.
Invoking Gemini
You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.
| Feature | Command | Description |
|---|---|---|
| Code Review | /gemini review |
Performs a code review for the current pull request in its current state. |
| Pull Request Summary | /gemini summary |
Provides a summary of the current pull request in its current state. |
| Comment | @gemini-code-assist | Responds in comments when explicitly tagged, both in issue comments and review comments. |
| Help | /gemini help |
Displays a list of available commands. |
Customization
To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.
Limitations & Feedback
Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.
You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.
Footnotes
-
Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩
There was a problem hiding this comment.
Code Review
This pull request refactors the firebase init flow to collect post-setup instructions from various features and display them at the end. This functionality is also leveraged by the firebase_init MCP tool to return these instructions to the user. The changes are well-structured and improve the modularity of the initialization process. My review includes a few minor suggestions to fix a typo in a user-facing message, correct a confusing code comment, and improve output formatting.
| @@ -17,6 +17,9 @@ export function availableTools(activeFeatures?: ServerFeature[]): ServerTool[] { | |||
| if (!activeFeatures?.length) { | |||
| activeFeatures = Object.keys(tools) as ServerFeature[]; | |||
| } | |||
| if (!activeFeatures.includes("core")) { | |||
There was a problem hiding this comment.
Emm, this is embarrassing
fredzqm
changed the title
github-project-automation
bot
moved this to Approved [PR]
in [Cloud] Extensions + Functions
github-project-automation
bot
moved this from Approved [PR]
to Done
in [Cloud] Extensions + Functions
While testing this, I realized that all of the core MCP tools were not included.