Firebase MCP Server

What does “Firebase” MCP Server do?

Firebase MCP is a Model Context Protocol (MCP) server that enables AI assistants to work directly with Firebase services, making it easier for developers to integrate AI-powered workflows with backend infrastructure. By exposing Firebase’s Firestore (a document database), Storage (for file management and uploads), and Authentication (user management and verification) as MCP tools, the server allows AI assistants to perform tasks like querying databases, managing files, and handling user authentication. This integration streamlines development workflows by letting AI agents interact programmatically with Firebase resources, automate repetitive tasks, and provide intelligent application support without leaving your preferred development environment.

List of Prompts

No explicit prompt templates mentioned in the available documentation or repository files.

List of Resources

No explicit MCP resource primitives listed in the available documentation or repository files.

List of Tools

• Firestore: Enables document database operations, such as reading from and writing to Firestore collections.
• Storage: Provides file management capabilities, including robust upload functionality to Firebase Storage.
• Authentication: Allows user management and verification operations using Firebase Authentication.

Use Cases of this MCP Server

• Database Management: Use AI agents to automate Firestore operations—like querying, updating, or deleting documents—improving efficiency for backend tasks.
• File Management: Streamline file uploads and downloads to Firebase Storage, enabling AI assistants to handle media or document workflows.
• User Management: Automate user authentication, registration, and verification via Firebase Authentication, reducing manual administrative overhead.
• CI/CD Automation: Integrate the MCP server in development pipelines to manage test databases or handle user data in automated test scenarios.
• Contextual AI Assistants: Enhance AI assistants with real-time access to Firebase data, making them more context-aware for application support and troubleshooting.

How to set it up

Windsurf

1. Ensure you have Node.js installed and a Firebase project with service account credentials.
2. Locate your Windsurf MCP settings file.
3. Add the Firebase MCP server to your configuration:

   {
     "mcpServers": {
       "firebase-mcp": {
         "command": "npx",
         "args": ["@gannonh/firebase-mcp@latest"]
       }
     }
   }
   

4. Save the file and restart Windsurf.
5. Verify setup by checking for Firebase MCP connection in your MCP server list.

Claude

1. Prerequisites: Node.js and Firebase project credentials.
2. Open ~/Library/Application Support/Claude/claude_desktop_config.json.
3. Add the Firebase MCP server:

   {
     "mcpServers": {
       "firebase-mcp": {
         "command": "npx",
         "args": ["@gannonh/firebase-mcp@latest"]
       }
     }
   }
   

4. Save changes and restart Claude Desktop.
5. Confirm Firebase MCP is running via the Claude interface.

Cursor

1. Prerequisites: Node.js and Firebase credentials.
2. Find your Cursor MCP configuration file.
3. Add Firebase MCP server entry:

   {
     "mcpServers": {
       "firebase-mcp": {
         "command": "npx",
         "args": ["@gannonh/firebase-mcp@latest"]
       }
     }
   }
   

4. Save and restart Cursor.
5. Validate by listing available MCP servers in Cursor.

Cline

1. Ensure Node.js and Firebase credentials are available.
2. Open the configuration file for Cline.
3. Insert Firebase MCP configuration:

   {
     "mcpServers": {
       "firebase-mcp": {
         "command": "npx",
         "args": ["@gannonh/firebase-mcp@latest"]
       }
     }
   }
   

4. Save and restart Cline.
5. Check that Firebase MCP appears in your active MCP servers.

Securing API Keys

Store sensitive credentials in environment variables. Example using env and inputs in JSON:

{
  "mcpServers": {
    "firebase-mcp": {
      "command": "npx",
      "args": ["@gannonh/firebase-mcp@latest"],
      "env": {
        "FIREBASE_SERVICE_ACCOUNT": "path/to/your/serviceAccountKey.json"
      },
      "inputs": {
        "projectId": "your-firebase-project-id"
      }
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "firebase-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “firebase-mcp” to whatever the actual name of your MCP server is, and replace the URL with your own MCP server URL.

Overview

Based on the tables above, the Firebase MCP server is highly practical for integrating AI assistants with Firebase, but lacks detailed documentation on prompt templates and MCP resource primitives. Its coverage of the main Firebase tools is strong, and setup/security guidance is present. The lack of sampling/roots/resource info reduces its completeness slightly.

MCP Score