Can this MCP access my entire Google Cloud project?

No. This MCP is designed to be surgical. It restricts the agent to one specific Firestore collection to ensure your other data remains untouched.

What happens if I try to update a document that already exists?

The set_document capability will update the existing fields in that document rather than creating a duplicate.

Which AI clients can use this MCP?

You can use this with any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

Do I need to manage my own GCP credentials?

Vinkius hosts the MCP and manages the necessary credentials so you don't have to.

Is this suitable for production data?

Yes, because the access is strictly scoped to a single collection, it provides a safe way to let an agent interact with live data.

Why limit the agent to a single Firestore Collection?

To enforce zero-trust security. An autonomous AI agent storing its task logs shouldn't have access to query or modify critical user data in other collections.

How are JSON types converted to Firestore fields?

The capability automatically performs a basic mapping. Strings become stringValue, integers become integerValue, and booleans become booleanValue. Complex nested objects may be serialized as strings.

Can I query multiple documents at once?

No. To maintain deterministic behavior, this capability is designed for key-value (document ID) access patterns. If you need complex queries, consider a custom BigQuery MCP.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Google Firestore Collection to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Give your AI agent a secure, dedicated NoSQL database.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 3 capabilities

We ship only the actions that matter.

Capability set01 / 01

01-03

3 capabilities in this set.

Part of 3 available through Google Firestore Collection.

01
Get document
This capability reads a specific document from your configured Firestore collection. Use it when your agent needs to pull existing data for context.
02
Delete document
This capability removes a document from the collection. It is used to clear out old data or specific records your agent no longer needs.
03
Set document
This capability creates new documents or updates existing ones in the collection. It handles field updates if the document already exists.

Real work

What teams actually run

Agentic Memory

An agent saves user preferences in a document so it remembers them in future conversations.

Workflow Automation

An agent writes the results of a processed task directly into a Firestore collection for later use.

Stateful Chatbots

The agent stores and retrieves chat history to maintain context over long periods.

Data Management

An agent cleans up temporary files or old records by deleting specific documents.

Automate a task

Put Google Firestore Collection to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Google Firestore Collection works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Google Firestore Collection to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

881ms average. Fast in production.

Google Firestore Collection is checked daily against the live service.

Daily averagePeak 1074ms

Oct 3Today

Fastest day: 722ms
Slowest day: 1074ms
14-day trend: Stable-2%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 3 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Google Firestore Collection, so you can see the experience inside your AI.

It does not authenticate your account with Google Firestore Collection. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Google Firestore Collection Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_D9PPFFrmux8dXozdC2CFNnwDeOgr9v7H0CtVCBNC/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Google Firestore Collection capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "google-firestore-collection-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_D9PPFFrmux8dXozdC2CFNnwDeOgr9v7H0CtVCBNC/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Google Firestore Collection in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Google Firestore Collection owners hand off.

Developers and engineers who need to bridge the gap between LLM reasoning and persistent cloud storage.

01
Backend Engineers
They hand off specific database tasks to an agent to automate data entry or retrieval.
02
AI Product Developers
They use this to give their agents a reliable place to store user preferences or session data.
03
Data Engineers
They use the scoped access to let agents interact with specific datasets without risking core infrastructure.

FAQ

Questions Google Firestore Collection owners ask.

01
Can this MCP access my entire Google Cloud project?
No. This MCP is designed to be surgical. It restricts the agent to one specific Firestore collection to ensure your other data remains untouched.
02
What happens if I try to update a document that already exists?
The set_document capability will update the existing fields in that document rather than creating a duplicate.
03
Which AI clients can use this MCP?
You can use this with any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.
04
Do I need to manage my own GCP credentials?
Vinkius hosts the MCP and manages the necessary credentials so you don't have to.
05
Is this suitable for production data?
Yes, because the access is strictly scoped to a single collection, it provides a safe way to let an agent interact with live data.
06
Why limit the agent to a single Firestore Collection?
To enforce zero-trust security. An autonomous AI agent storing its task logs shouldn't have access to query or modify critical user data in other collections.
07
How are JSON types converted to Firestore fields?
The capability automatically performs a basic mapping. Strings become stringValue, integers become integerValue, and booleans become booleanValue. Complex nested objects may be serialized as strings.
08
Can I query multiple documents at once?
No. To maintain deterministic behavior, this capability is designed for key-value (document ID) access patterns. If you need complex queries, consider a custom BigQuery MCP.

Explore

More in Industry Titans

Connect Google Firestore Collection to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-03

Get document

Delete document

Set document

What teams actually run

Agentic Memory

Workflow Automation

Stateful Chatbots

Data Management

Building your own app? The connector is yours to use.

Google Firestore Collection Connector

Claude Desktop

Backend Engineers

AI Product Developers

Data Engineers

Can this MCP access my entire Google Cloud project?

What happens if I try to update a document that already exists?

Which AI clients can use this MCP?

Do I need to manage my own GCP credentials?

Is this suitable for production data?

Why limit the agent to a single Firestore Collection?

How are JSON types converted to Firestore fields?

Can I query multiple documents at once?

Matillion (Cloud Data Integration & ELT) AI Connector

Hevo Data (ETL & Data Pipeline) AI Connector

Google Cloud Storage Bucket AI Connector

Azure Cosmos DB Container AI Connector

Suggestions

Data Pipeline Prover AI Connector

Data.gov Catalog AI Connector

Import.io (Web Data Extraction) AI Connector

data.world AI Connector