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

Q: How do I connect Firebase (REST & Admin APIs) to LangChain?

You use the MultiServerMCPClient from the langchain-mcp-adapters package. Point it to your Vinkius endpoint URL and call client.gettools() to pass the tools directly to your agent.

Run live Firestore queries and manage auth users directly inside your LangChain reasoning loops without writing custom API code.

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 LangChain

Create your Vinkius account to connect Firebase (REST & Admin APIs) to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain-linked user authentication in LangChain

This MCP Server lets your LangChain agent run `auth_sign_up` and `auth_lookup` within a single execution graph. You pass the output of a user creation step directly into subsequent database operations without handling raw HTTP requests yourself. The agent inspects the returned user record to decide if it needs to trigger a database setup. This setup replaces manual glue code, letting LangSmith trace every payload change and token count in real time.

Multi-step Firestore document updates

This toolset exposes `firestore_create_doc` and `firestore_patch_doc` directly to your multi-step LangChain chains. Your agent queries a collection with `firestore_list_docs`, reads a specific record, and applies partial updates based on the context of the conversation. You configure the chain to feed the output of one step into the next. If a document does not exist, the agent creates it, tracking the exact latency and input parameters inside your LangSmith dashboard.

Low-latency Realtime Database state synchronization

The server provides `rtdb_put` and `rtdb_patch` to sync ephemeral state across your LangChain application. When an agent finishes a reasoning loop, it writes the final state to your Firebase Realtime Database to update connected frontends instantly. This approach keeps your application state synchronized without relying on heavy client-side SDKs. Your agent writes raw JSON payloads, and the REST API executes the write within milliseconds.

Setup guide

Set up Firebase (REST & Admin APIs) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Firebase (REST & Admin APIs) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "firebase-rest-admin-apis-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Firebase (REST & Admin APIs) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You use the `MultiServerMCPClient` from the `langchain-mcp-adapters` package. Point it to your Vinkius endpoint URL and call `client.get_tools()` to pass the tools directly to your agent.

No, this MCP Server uses REST endpoints which do not support multi-document transactions. Your agent must manage sequential logic using `firestore_patch_doc` and handle failures within your chain's error-handling steps.

LangSmith automatically captures every tool execution, including the payload size sent to Firestore or Auth. You see the exact input and output JSON structure in your tracing dashboard.

No. The Vinkius MCP Server handles all communication with Firebase over REST. Your local environment only needs the standard HTTP client adapter, keeping your deployment package small.

All Firestore documents, Realtime DB JSON payloads, and Auth user records stay inside a sandboxed V8 isolate. Vinkius executes these requests using your configured environment credentials, meaning no credentials or database payloads are ever written to persistent log files.

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