Firestore using MCP

Connect your IDE to Firestore using Toolbox.

Model Context Protocol (MCP) is an open protocol for connecting Large Language Models (LLMs) to data sources like Firestore. This guide covers how to use MCP Toolbox for Databases to expose your developer assistant tools to a Firestore instance:

Set up Firestore

Create or select a Google Cloud project.
- Create a new project
- Select an existing project
Enable the Firestore API for your project.
Create a Firestore database if you haven’t already.
Set up authentication for your local environment.
- Install gcloud CLI
- Run gcloud auth application-default login to authenticate

Install MCP Toolbox

Download the latest version of Toolbox as a binary. Select the correct binary corresponding to your OS and CPU architecture. You are required to use Toolbox version V0.10.0+:

curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/linux/amd64/toolbox

curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/darwin/arm64/toolbox

curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/darwin/amd64/toolbox

curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/windows/amd64/toolbox

Make the binary executable:
```
chmod +x toolbox
```
Verify the installation:
```
./toolbox --version
```

Configure your MCP Client

Install Claude Code.
Create a .mcp.json file in your project root if it doesn’t exist.

Add the following configuration, replace the environment variables with your values, and save:

{
  "mcpServers": {
    "firestore": {
      "command": "./PATH/TO/toolbox",
      "args": ["--prebuilt","firestore","--stdio"],
      "env": {
        "FIRESTORE_PROJECT": "your-project-id",
        "FIRESTORE_DATABASE": "(default)"
      }
    }
  }
}

Restart Claude code to apply the new configuration.

Open Claude desktop and navigate to Settings.
Under the Developer tab, tap Edit Config to open the configuration file.

Add the following configuration, replace the environment variables with your values, and save:

{
  "mcpServers": {
    "firestore": {
      "command": "./PATH/TO/toolbox",
      "args": ["--prebuilt","firestore","--stdio"],
      "env": {
        "FIRESTORE_PROJECT": "your-project-id",
        "FIRESTORE_DATABASE": "(default)"
      }
    }
  }
}

Restart Claude desktop.
From the new chat screen, you should see a hammer (MCP) icon appear with the new MCP server available.

Open the Cline extension in VS Code and tap the MCP Servers icon.
Tap Configure MCP Servers to open the configuration file.

Add the following configuration, replace the environment variables with your values, and save:

{
  "mcpServers": {
    "firestore": {
      "command": "./PATH/TO/toolbox",
      "args": ["--prebuilt","firestore","--stdio"],
      "env": {
        "FIRESTORE_PROJECT": "your-project-id",
        "FIRESTORE_DATABASE": "(default)"
      }
    }
  }
}

You should see a green active status after the server is successfully connected.

Create a .cursor directory in your project root if it doesn’t exist.
Create a .cursor/mcp.json file if it doesn’t exist and open it.

Add the following configuration, replace the environment variables with your values, and save:

{
  "mcpServers": {
    "firestore": {
      "command": "./PATH/TO/toolbox",
      "args": ["--prebuilt","firestore","--stdio"],
      "env": {
        "FIRESTORE_PROJECT": "your-project-id",
        "FIRESTORE_DATABASE": "(default)"
      }
    }
  }
}

Cursor and navigate to Settings > Cursor Settings > MCP. You should see a green active status after the server is successfully connected.

Open VS Code and create a .vscode directory in your project root if it doesn’t exist.
Create a .vscode/mcp.json file if it doesn’t exist and open it.

Add the following configuration, replace the environment variables with your values, and save:

{
  "mcpServers": {
    "firestore": {
      "command": "./PATH/TO/toolbox",
      "args": ["--prebuilt","firestore","--stdio"],
      "env": {
        "FIRESTORE_PROJECT": "your-project-id",
        "FIRESTORE_DATABASE": "(default)"
      }
    }
  }
}

Open Windsurf and navigate to the Cascade assistant.
Tap on the hammer (MCP) icon, then Configure to open the configuration file.

Add the following configuration, replace the environment variables with your values, and save:

{
  "mcpServers": {
    "firestore": {
      "command": "./PATH/TO/toolbox",
      "args": ["--prebuilt","firestore","--stdio"],
      "env": {
        "FIRESTORE_PROJECT": "your-project-id",
        "FIRESTORE_DATABASE": "(default)"
      }
    }
  }
}

Install the Gemini CLI.
In your working directory, create a folder named .gemini. Within it, create a settings.json file.

Add the following configuration, replace the environment variables with your values, and then save:

{
  "mcpServers": {
    "firestore": {
      "command": "./PATH/TO/toolbox",
      "args": ["--prebuilt","firestore","--stdio"],
      "env": {
        "FIRESTORE_PROJECT": "your-project-id",
        "FIRESTORE_DATABASE": "(default)"
      }
    }
  }
}

Install the Gemini Code Assist extension in Visual Studio Code.
Enable Agent Mode in Gemini Code Assist chat.
In your working directory, create a folder named .gemini. Within it, create a settings.json file.

Add the following configuration, replace the environment variables with your values, and then save:

{
  "mcpServers": {
    "firestore": {
      "command": "./PATH/TO/toolbox",
      "args": ["--prebuilt","firestore","--stdio"],
      "env": {
        "FIRESTORE_PROJECT": "your-project-id",
        "FIRESTORE_DATABASE": "(default)"
      }
    }
  }
}

Use Tools

Your AI tool is now connected to Firestore using MCP. Try asking your AI assistant to list collections, get documents, query collections, or manage security rules.

The following tools are available to the LLM:

firestore-get-documents: Gets multiple documents from Firestore by their paths
firestore-list-collections: List Firestore collections for a given parent path
firestore-delete-documents: Delete multiple documents from Firestore
firestore-query-collection: Query documents from a collection with filtering, ordering, and limit options
firestore-get-rules: Retrieves the active Firestore security rules for the current project
firestore-validate-rules: Validates Firestore security rules syntax and errors

Note

Prebuilt tools are pre-1.0, so expect some tool changes between versions. LLMs will adapt to the tools available, so this shouldn’t affect most users.

Last modified August 27, 2025: chore(main): release 0.13.0 (#1175) (1a6dfe8d3)