Google Cloud Firestore MCP server

Create a powerful Model Context Protocol (MCP) server for Google Cloud Firestore to manage NoSQL data, perform real-time queries, and synchronize data across applications. This integration enables AI agents to automate database operations, manage collections and documents, execute transactions, and maintain data quality with secure service account authentication.

Setting up an MCP server

This article covers the standard steps for creating an MCP server in AI Gateway and connecting it to an AI client. The steps are the same for every integration — application-specific details (API credentials, OAuth endpoints, and scopes) are covered in the Authentication section on this page.

Before you begin

You'll need:

• Access to AI Gateway with permission to create MCP servers.
• API credentials for the application you're connecting (see the Authentication section on this page for what to collect).

Create an MCP server

Find the app in the catalog

1. Sign in to AI Gateway and select App Catalog from the left navigation.
2. Search for the application you want to connect, then select it from the catalog.
3. Select Create MCP Server to start the wizard.

App Configuration

Confirm the Base URL for the API, then, under Tools, select the endpoints you want to expose. Select Next.

MCP Server Setup

1. Enter a Name for your server — something descriptive that identifies both the application and its purpose.
2. Enter a Description so your team knows what the server is for.
3. Set the log level: choose Production Mode for terser logs, or Non-Production Mode for more verbose logs that can help with debugging.
4. Select Next.

Authentication

Enter the authentication details for the application. This varies by service — see the Authentication section on this page for the specific credentials, OAuth URLs, and scopes to use.

Review

Look over the summary of your MCP server configuration, then select Create & Deploy. AI Gateway provisions the server and provides a server URL you'll use when configuring your AI client.

---

Connect to an AI client

Once your server is deployed, you'll need to add it to the AI client your team uses. Select your client for setup instructions:

• Claude Desktop
• Claude Code
• Cursor
• VS Code
• Windsurf

Tips

• You can create multiple MCP servers for the same application — for example, a read-only server for reporting agents and a read-write server for automation workflows.
• If you're unsure which OAuth scopes to request, start with the minimum read-only set and add write scopes only when needed. Most application pages include scope recommendations.

Authentication

Google Cloud Firestore uses OAuth 2.0 with service accounts for API access. Create a service account in your Google Cloud project with the Cloud Datastore User role and download a JSON key file. In Google Cloud Console, go to IAM & Admin > Service Accounts, create a service account with the Cloud Datastore User role, and download a JSON key.

Value	Setting
Token endpoint	https://oauth2.googleapis.com/token
Scopes	https://www.googleapis.com/auth/cloud-platform

Available tools

These tools let AI agents perform full CRUD operations on Firestore documents, execute queries, manage collections, and handle transactions. Together they enable building data-driven applications with real-time synchronization and complex querying.

Tool	Description
Get document	Retrieve a single document by ID
Create document	Create a new document in a collection
Update document	Modify an existing document
Delete document	Remove a document
List documents	Query all documents in a collection with filters
Query documents	Execute complex queries with multiple conditions
Batch get	Retrieve multiple documents by ID in one call
Batch write	Create, update, or delete multiple documents atomically
Begin transaction	Start a multi-step atomic operation
Commit transaction	Save all changes from a transaction
Rollback transaction	Discard a transaction if validation fails
Export database	Create a backup by exporting all data
Import database	Restore data from a previous export
Create index	Optimize queries with composite indexes
List collections	View all collections in the database

Tips

Use Firestore's transactional writes to keep data consistent across collections — for example, atomically update both an order and inventory counts together.

Use batch operations when importing or updating large datasets instead of individual writes to improve performance and reduce costs.

Create composite indexes for queries that filter by multiple conditions — without indexes, Firestore scans all documents, which is slow and expensive.

Use transactions to validate data before writing — for example, check that an order total matches the sum of line items before committing.

Periodically export your database to Cloud Storage for disaster recovery and long-term data archival.

Use Firestore's built-in backup and restore for point-in-time recovery when you need to recover recent data.