Firebase

Provides secure MCP access to Firebase Firestore and Storage for a DAM-focused data source.

python

0

GitHub Stars

python

Language

2 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "lt012071-dam-firebase-mcp-server": {
      "command": "python",
      "args": [
        "/path/to/mcp-server/main.py",
        "--google-credentials",
        "/path/to/your/service-account-credentials.json",
        "--transport",
        "stdio"
      ],
      "env": {
        "PYTHONPATH": "/path/to/mcp-server"
      }
    }
  }
}

You set up a Python-based MCP server that provides secure, MCP-compliant access to Firebase Firestore and Storage for a Digital Asset Management workflow. It lets you query asset data, version histories, comments, and storage files through standardized MCP tools, with options for both local (stdio) and HTTP transports.

How to use

You run the MCP server locally and connect with an MCP client to perform read-only queries against Firestore collections and the Storage bucket. Use the stdio transport for local development and testing, or HTTP transport to expose the server over a network. After starting, your client can search assets, versions, comments, and files in storage using the available MCP tools.

How to install

Prerequisites You need Python 3.11 or higher and a Firebase project with Firestore and Storage enabled. You also require a Google Cloud service account JSON file with appropriate permissions.

Install dependencies First, install the Python packages specified for this server.

pip install -r requirements.txt

Run the server with stdio transport (for MCP clients) using your service account credentials.

python main.py --google-credentials /path/to/service-account.json --transport stdio

Run the server with HTTP transport (for web access) once you’re ready to expose it over the network. Note that you should provide a reachable host/port and ensure credentials are securely managed.

python main.py --google-credentials /path/to/service-account.json --transport http --host 0.0.0.0 --port 8000

Enable debug logging during startup if you need more visibility into initialization and request handling.

python main.py --google-credentials /path/to/service-account.json --debug

Configuration and security notes

Configuration details include a dedicated MCP server configuration that binds to the stdio transport for local use. Environment variables are supported where shown in examples, and credentials must be supplied via the service account JSON file.

Security considerations Always use a service account with restricted permissions. Do not commit credentials files to version control. Access is designed to be read-only to safeguard assets.

Docker and containerized deployment

The server can be deployed in Docker. Build the image from the Docker configuration and run with Docker Compose or a direct container run command to expose the desired port.

Service account setup and usage

Create a service account in your Firebase project, download the JSON credentials file, and configure the server to use these credentials. Grant necessary permissions for Firestore and Storage as required by your access patterns.

Important security note: Never commit credentials files to version control and limit access to the credentials file on the host.

Examples of available tools you can use through MCP

The server exposes tools to query assets, their versions, comments, and storage files. You can search assets by category, tags, uploader, and date ranges; search versions by asset and update date; search comments by asset and creation date; and search storage files by prefix and upload date.

Available tools

search_assets

Query the Firestore assets collection for assets with filters such as category, tags, visibility, and date ranges.

search_versions

Query the Firestore versions collection to retrieve asset versions, including file URLs and metadata.

search_comments

Query the Firestore comments collection to fetch comments tied to assets with timestamps.

search_asset_files

Search files in the Firebase Storage bucket, returning metadata like name, size, contentType, and download URLs.