How to Use the Firebase (REST & Admin APIs) MCP in Mastra AI

Q: How do I register the Firebase (REST & Admin APIs) tools in Mastra AI?

Install @mastra/mcp@latest and initialize MCPClient with your Vinkius server URL. Call mcpClient.listTools() and spread them directly into your agent configuration.

Q: Can I require human approval before Mastra AI modifies Firebase (REST & Admin APIs) data?

Yes. Mastra supports requireToolApproval for sensitive actions like firestoredeletedoc or rtdbput, pausing the workflow until a developer approves the action.

Q: How does Mastra AI handle Firebase (REST & Admin APIs) connection drops?

Mastra uses built-in workflow retries. If a REST call like rtdbget fails due to network issues, the system automatically retries the operation based on your backoff settings.

Q: Can I send push notifications through this setup?

Yes, your agents can call fcmsendmessage to send push alerts. You can trigger this at the end of any workflow to notify users of completed tasks.

Run reliable, multi-step database workflows in Mastra AI using this Firebase (REST & Admin APIs) toolset.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Firebase (REST & Admin APIs) MCP to Mastra AI

Create your Vinkius account to connect Firebase (REST & Admin APIs) 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 Firebase (REST & Admin APIs) with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-step data migrations with Mastra AI workflows

`firestore_create_doc` writes new records while Mastra manages the retry logic if the network hiccups. The workflow engine can catch errors during execution and automatically trigger a rollback or a fallback notification. You can chain this with `firestore_delete_doc` to clean up temporary records. Mastra handles the state between these steps, making sure your database doesn't end up with orphaned documents.

Automated user provisioning loops

`auth_sign_up` registers new users during complex onboarding flows. Mastra agents run this tool, check the output, and then immediately run `auth_lookup` to verify the profile details are correct. If the lookup fails, the workflow branches to notify your team. This keeps your user registration pipeline accurate without requiring manual database checks.

Self-healing Realtime Database updates

`rtdb_patch` updates specific child nodes in your database tree. Mastra AI agents use this tool to apply granular state updates, avoiding the risk of overwriting the entire database path. If a conflict occurs, Mastra triggers an exponential backoff retry. This makes your database operations highly resilient even during high-traffic events.

Setup guide

Set up Firebase (REST & Admin APIs) 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 Firebase (REST & Admin APIs) 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: "firebase-rest-admin-apis-mcp-client",
  servers: {
    "firebase-rest-admin-apis-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Firebase (REST & Admin APIs) Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Firebase (REST & Admin APIs) tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Firebase (REST & Admin APIs) 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 Firebase. 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 Firebase (REST & Admin APIs) 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 Firebase (REST & Admin APIs) MCP in Mastra AI

Install `@mastra/mcp@latest` and initialize `MCPClient` with your Vinkius server URL. Call `mcpClient.listTools()` and spread them directly into your agent configuration.

Yes. Mastra supports `requireToolApproval` for sensitive actions like `firestore_delete_doc` or `rtdb_put`, pausing the workflow until a developer approves the action.

Mastra uses built-in workflow retries. If a REST call like `rtdb_get` fails due to network issues, the system automatically retries the operation based on your backoff settings.

Yes, your agents can call `fcm_send_message` to send push alerts. You can trigger this at the end of any workflow to notify users of completed tasks.

Your Firebase Auth records and API keys are stored securely within Vinkius environment variables. They are injected into ephemeral V8 isolates at runtime, ensuring your administrative credentials remain private and isolated.

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