MCP.so
ログイン

MCP Server Firebase

@sheep52031

基本情報

カテゴリ

クラウドとインフラ

トランスポート

stdio

作者

sheep52031

MCP Server Firebase について

概要はまだありません

MCP Server Firebase の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "mcp-server-firebase-sheep52031": {
      "command": "npx",
      "args": [
        "wrangler",
        "secret",
        "put",
        "FIREBASE_PROJECT_ID"
      ]
    }
  }
}

MCP Server Firebase のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is MCP Server Firebase?

MCP Server Firebase is a Model Context Protocol (MCP) server implementation that integrates with Firebase Firestore. It offers two deployment modes: a local Node.js mode using the Firebase Admin SDK and a Cloudflare Workers mode using the Firebase REST API. It is designed for developers and AI agents that need a standardized way to perform Firestore operations through the MCP protocol.

How to use MCP Server Firebase?

After installing dependencies with npm install, configure the server according to your chosen mode. For local mode, set the SERVICE_ACCOUNT_KEY_PATH environment variable to your Firebase service account key. For Workers mode, configure FIREBASE_PROJECT_ID, FIREBASE_API_KEY, and FIREBASE_AUTH_DOMAIN in wrangler.toml or as Cloudflare Secrets. Run npm run dev for local mode, npm run dev:worker for Workers development, or npm run dev:all for both. Connect your MCP client to the server endpoint (e.g., http://localhost:8765 for local) and use tools such as mcp_firebase_mcp_firestore_add_document to interact with Firestore.

Key features of MCP Server Firebase

  • Firestore document CRUD operations (create, read, update, delete)
  • Query collections and subcollections with filters
  • Dual deployment: local Node.js or Cloudflare Workers
  • Uses MCP protocol for standardized AI tool integration
  • Supports serverless environments via Firebase REST API

Use cases of MCP Server Firebase

  • AI agents reading and writing Firestore data in real-time
  • Serverless Firestore workflows deployed on Cloudflare Workers
  • Integrating Firebase into MCP-compatible AI clients
  • Automating content management with structured data queries

よくある質問

1

How does MCP Server Firebase differ from directly using the Firebase Admin SDK?

It provides a standardized MCP interface, allowing AI clients to interact with Firestore through a unified tool-based API without writing custom integration code.

2

What are the runtime requirements?

Local mode requires Node.js 18 or later and a Firebase service account key file. Cloudflare Workers mode requires a Firebase project ID, Web API key, and authentication domain.

3

Where is data stored?

All data remains in your own Firebase Firestore database. The server acts as a proxy and does not cache or store data elsewhere.

コメント

「クラウドとインフラ」の他のコンテンツ