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

Q: How do I connect the Firebase (REST & Admin APIs) MCP Server to Vercel AI SDK?

Install @ai-sdk/mcp and ai. Initialize the client with createMCPClient pointing to your Vinkius HTTP endpoint, then pass mcpClient.tools() to streamText.

Q: Does Vercel AI SDK support user sign-ups using this Firebase (REST & Admin APIs) connection?

Yes, your agent can call authsignup to create new accounts or sign in users anonymously. The tool returns the user record which you can immediately feed back into your React component state.

Q: How does the server handle Firebase Cloud Messaging?

The agent uses fcmsendmessage to dispatch push alerts. It sends the payload directly through the Google REST API, bypassing standard server setup.

Stream live Firebase data directly to your Next.js UI using this MCP Server and Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect Firebase (REST & Admin APIs) to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Firestore rendering via Vercel AI SDK

`firestore_get_doc` pulls raw document data directly into your edge-rendered streaming components. Your agent triggers this tool to fetch user profiles, and the results stream straight to the UI without forcing a full page reload. You can also use `firestore_patch_doc` to modify fields on the fly. The Vercel AI SDK handles the tool execution loop, allowing your application to show UI updates the millisecond the database confirms the edit.

Instant user lookups in streaming chat

`auth_lookup` retrieves user metadata directly within your active conversational streams. When a user asks about their account status, your agent calls this tool to verify their record without leaving the edge function. This setup avoids the overhead of loading heavy client-side SDKs. You get clean, fast JSON payloads that feed right into your LLM prompt context, maintaining a snappy user experience.

Realtime Database sync with zero loading spinners

`rtdb_put` overwrites JSON nodes in your Realtime Database during active user sessions. Using this tool with the Vercel AI SDK means your agent updates state variables while the user watches the progress bar fill up in real time. If you need to append logs, `rtdb_push` adds timestamped entries without breaking the stream. It keeps your interface fast because you aren't waiting for a massive backend bundle to initialize.

Setup guide

Set up Firebase (REST & Admin APIs) MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Firebase (REST & Admin APIs) tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Firebase (REST & Admin APIs) transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Install `@ai-sdk/mcp` and `ai`. Initialize the client with `createMCPClient` pointing to your Vinkius HTTP endpoint, then pass `mcpClient.tools()` to `streamText`.

Yes. Since this server uses raw REST endpoints rather than the bulky gRPC-based Firebase Admin SDK, it runs inside lightweight Vercel Edge Functions without hitting bundle size limits.

Yes, your agent can call `auth_sign_up` to create new accounts or sign in users anonymously. The tool returns the user record which you can immediately feed back into your React component state.

The agent uses `fcm_send_message` to dispatch push alerts. It sends the payload directly through the Google REST API, bypassing standard server setup.

Your Firestore documents and Realtime Database JSON payloads are protected by the Vinkius zero-trust sandbox. Every request goes through isolated V8 runtimes, meaning your credentials and database records are never cached or exposed to other users.

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