How to Use the Google Firestore Collection MCP in Mastra AI

Q: How do I register the Google Firestore Collection MCP Server tools with a Mastra AI agent?

Install the client with npm install @mastra/mcp@latest. Instantiate MCPClient, call mcpClient.listTools(), and spread those tools directly into your Mastra agent's tool array.

Q: Does Mastra AI support human approval before running deletedocument?

Yes, you can use the requireToolApproval setting on your Mastra AI agent. This pauses the workflow and asks for confirmation before the tool executes.

Q: How does the Google Firestore Collection MCP Server handle retries in Mastra AI?

If a network hiccup interrupts setdocument, Mastra AI uses its built-in workflow engine to retry the operation. This keeps your database writes reliable during transient failures.

Persist workflow state in your Mastra AI agents using this dedicated Google Firestore Collection MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Google Firestore Collection MCP to Mastra AI

Create your Vinkius account to connect Google Firestore Collection to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Google Firestore Collection with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Write Mastra AI step results using the set_document tool

The `set_document` tool saves execution data from your Mastra AI workflows directly into your Firestore collection. If a workflow step fails, the Mastra framework automatically retries the write using exponential backoff to ensure your Firestore document is successfully updated. You register the MCP Server by calling `new MCPClient` and spreading the tools into your Mastra agent configuration. This gives your automated workflows a reliable persistence layer without manual database setup.

Branch Mastra AI workflows based on retrieved documents

The `get_document` tool reads a document's current Firestore state to determine which path your Mastra AI workflow should follow next. You can check user subscription status or previous run data before executing subsequent workflow steps. Mastra handles the underlying SSE or HTTP transport automatically when calling this Firestore tool. This lets you build complex decision trees rather than debugging connection states.

Human-in-the-loop Firestore document deletion

The `delete_document` tool purges state records from Firestore once a Mastra AI workflow reaches its final step. You can pair this tool with Mastra's `requireToolApproval` setting to force a human review before any Firestore data is permanently erased. This setup ensures your Mastra agents never delete critical records without explicit permission. It keeps your Firestore database clean while maintaining strict operational guardrails.

Setup guide

Set up Google Firestore Collection MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Google Firestore Collection tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "google-firestore-collection-mcp-client",
  servers: {
    "google-firestore-collection-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Google Firestore Collection Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Google Firestore Collection tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Google Firestore Collection transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Google Firestore Collection. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Google Firestore Collection now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Google Firestore Collection MCP in Mastra AI

Install the client with `npm install @mastra/mcp@latest`. Instantiate `MCPClient`, call `mcpClient.listTools()`, and spread those tools directly into your Mastra agent's tool array.

Yes, you can use the `requireToolApproval` setting on your Mastra AI agent. This pauses the workflow and asks for confirmation before the tool executes.

If a network hiccup interrupts `set_document`, Mastra AI uses its built-in workflow engine to retry the operation. This keeps your database writes reliable during transient failures.

The client automatically detects and handles both Streamable HTTP and SSE transports. You only need to provide the server URL during initialization.

Yes, your raw NoSQL document payloads pass directly through an encrypted, ephemeral V8 isolate sandbox managed by Vinkius. The platform never caches or inspects your database records during automated workflow executions.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript