Unlocking Extensibility with Model Context Protocol (MCP)
We’re previewing foundational support for the Model Context Protocol (MCP) in Firebase Studio. Now you can add MCP servers to your workspace, extending and personalizing your workflows with Gemini in Firebase Studio. For example, you can use the Firebase MCP server to explore your data in Cloud Firestore using natural language while you are building or debugging your application, or use Context7 to get library specific context for Gemini (i.e. try building app with MediaPipe’s on-device ML).
Setting up MCP Server
To add an MCP server, you’ll create a .idx/mcp.json file in your project.
From the Explorer (Win: Ctrl+Shift+E, Mac: Cmd+Shift+E), right-click the .idx folder and select New file. Name the file mcp.json and press Enter.
Add the following server configuration to the mcp.json file. This example configures the Firebase
MCP server:
{
"mcpServers": {
"firebase": {
"command": "npx",
"args": [
"-y",
"firebase-tools@latest",
"experimental:mcp",
"--dir",
"/home/user/studio"
]
}
}
}
This configuration tells Gemini to use the firebase MCP server, running firebase-tools@latest in experimental MCP mode, with your current workspace directory as the project context.
The Future of MCP in Firebase Studio
This foundational release is just the first step. As we plan our next phase, we’re turning to our community to help guide the way. Your real-world use cases and feedback will determine the future of AI extensibility in Firebase Studio. Please join this conversation to share your experience and tell us what we should build next.