feat(mcp): Add support for setting up iOS projects #9332
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This change introduces the capability for the MCP agent to guide users through setting up Firebase AI Logic in native iOS/Swift projects.
### Description
Previously, the `init` command explicitly excluded iOS from the Firebase AI Logic setup flow. This update removes that limitation and provides the necessary prompts, guides, and safety protocols to offer a complete and safe setup experience for iOS developers.
Key changes include:
- **Updated Core `init` Prompt:** The main `init` prompt (`src/mcp/prompts/core/init.ts`) has been modified to recognize iOS as a supported platform for the AI Logic feature.
- **Enhanced AI Initialization Guide:** The guide (`src/mcp/resources/guides/init_ai.ts`) has been significantly updated with iOS-specific instructions:
- **Project Configuration:** The agent is now instructed on how to download the `GoogleService-Info.plist` and guide the user to place it in their Xcode project.
- **Safe SDK Handling:** A critical safety protocol has been added. The agent is now instructed to first inspect the `.xcodeproj` file for the `firebase-ios-sdk`. If the SDK is missing, the agent is strictly forbidden from modifying the project file and will instead provide the user with exact, step-by-step manual instructions for adding the dependency via Swift Package Manager in Xcode.
- **Swift Code Snippets:** The documentation tables have been populated with the necessary links to fetch Swift code snippets for initialization and various AI features.
- **Agent Directives:** A project-specific directive has been added to `GEMINI.md` to ensure that all agents correctly escape backticks in tool parameters, improving the reliability of future automated changes.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This change introduces the capability for the MCP agent to guide users through setting up Firebase AI Logic in native iOS/Swift projects.
Description
Previously, the
initcommand explicitly excluded iOS from the Firebase AI Logic setup flow. This update removes that limitation and provides the necessary prompts, guides, and safety protocols to offer a complete and safe setup experience for iOS developers.Key changes include:
initPrompt: The maininitprompt (src/mcp/prompts/core/init.ts) has been modified to recognize iOS as a supported platform for the AI Logic feature.src/mcp/resources/guides/init_ai.ts) has been significantly updated with iOS-specific instructions:GoogleService-Info.plistand guide the user to place it in their Xcode project..xcodeprojfile for thefirebase-ios-sdk. If the SDK is missing, the agent is strictly forbidden from modifying the project file and will instead provide the user with exact, step-by-step manual instructions for adding the dependency via Swift Package Manager in Xcode.GEMINI.mdto ensure that all agents correctly escape backticks in tool parameters, improving the reliability of future automated changes.