MCP Firebase Server MCP Server

This server implements the Model Context Protocol (MCP) to act as a bridge between a Large Language Model (LLM) like Claude and Firebase (Firestore).

Local serverstdioPython

What is the MCP Firebase Server MCP server?

MCP Firebase Server MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. This server implements the Model Context Protocol (MCP) to act as a bridge between a Large Language Model (LLM) like Claude and Firebase (Firestore). It allows the LLM to read from and write to Firestore collections by exposing these.

Configuration and credentials

You will need 2 environment variables: SERVICE_ACCOUNT_KEY_PATH, FIREBASE_STORAGE_BUCKET. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

  • Python 3.7+ (preferably 3.8+ for asynccontextmanager and full type hinting features used by MCP) * Pip (Python package installer) or uv (recommended by MCP docs for project management) * A Firebase project with Firestore enabled. * A Firebase service account key JSON file.

Setting it up

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

Choosing this one

Among the AI and media services options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. It is maintained by davo20019; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the mcp firebase server mcp server does with a few real requests.

How to install the MCP Firebase Server MCP server

{
  "mcpServers": {
    "firebase": { // A unique name you assign to this server instance in the client's config
      "command": "/full/path/to/your/mc-firebase-server/run_server.sh", // IMPORTANT: Use the absolute path to the script
      "args": [], // Typically empty if run_server.sh handles everything
      // "cwd": "/full/path/to/your/mc-firebase-server/", // Usually not needed if run_server.sh cds to its own dir
      "env": {
        // Replace with the ACTUAL absolute path to your service account key file
        "SERVICE_ACCOUNT_KEY_PATH": "/path/to/your/serviceAccountKey.json", 
        // Optional: Replace with your actual Firebase Storage bucket name if needed by future tools
        "FIREBASE_STORAGE_BUCKET": "your-project-id.appspot.com" 
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Python 3.7+ (preferably 3.8+ for asynccontextmanager and full type hinting features used by MCP) * Pip (Python package installer) or uv (recommended by MCP docs for project management) * A Firebase project with Firestore enabled. * A Firebase service account key JSON file.
VariableDescriptionRequired
SERVICE_ACCOUNT_KEY_PATHCredential the server authenticates with.Yes
FIREBASE_STORAGE_BUCKETConfiguration value read at startup.Optional

Frequently asked questions

It connects MCP Firebase Server to MCP-compatible AI assistants such as Claude and Cursor. Instead of copying data back and forth by hand, the assistant works with MCP Firebase Server directly.