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

Q: Can LlamaIndex search Firebase (REST & Admin APIs) data semantically?

Yes, by combining firestorelistdocs with an embedding pipeline. The agent fetches the raw text fields from your documents, generates embeddings, and stores them in your vector index for retrieval.

Q: Does the Firebase (REST & Admin APIs) MCP Server support LlamaIndex resource loading?

Yes. You can enable includeresources=True on your client to allow the agent to treat Firestore collections as native LlamaIndex data resources for direct querying.

Q: Can the agent send push notifications based on index queries?

Yes, using the fcmsendmessage tool. When an index query detects an anomaly or a specific threshold, the agent constructs and sends a push notification payload immediately.

Index Firestore records and Realtime DB states directly into LlamaIndex vector stores for context-aware, hallucination-free generation.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live Firestore data for LlamaIndex RAG

This MCP Server exposes `firestore_list_docs` and `firestore_get_doc` to feed raw document data directly into your LlamaIndex pipelines. Your agent pulls documents, indexes them into a vector store, and performs semantic search over live database records. This process eliminates stale data issues in your RAG system. The agent queries Firestore, parses the structured fields, and answers user questions using actual, real-time database state instead of relying on training data.

Write agent decisions back to the database

The server provides `firestore_create_doc` and `firestore_patch_doc` so your LlamaIndex agent can log its findings or update user profiles. After querying your index, the agent writes its synthesis back to Firestore to keep other services updated. You configure the agent to run these writes autonomously. If a document requires partial updates, the agent uses patch operations to modify only the targeted fields, preserving the rest of the document structure.

Sync real-time state for context retrieval

This toolset includes `rtdb_get` and `rtdb_put` to let LlamaIndex track transient application state. The agent reads the current state from the Realtime Database to ground its reasoning in the user's active session. This keeps your agent aligned with what the user sees on screen. By fetching the raw JSON state, the agent avoids making assumptions about the user's current progress.

Setup guide

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

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Firebase (REST & Admin APIs) MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Firebase (REST & Admin APIs) tools.",
)
response = await agent.run("List recent Firebase (REST & Admin APIs) data")

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 LlamaIndex

You initialize the MCP client with your Vinkius URL and wrap it in a `McpToolSpec`. Call `to_tool_list_async()` to convert the server's tools into a format your `FunctionAgent` understands.

Yes, by combining `firestore_list_docs` with an embedding pipeline. The agent fetches the raw text fields from your documents, generates embeddings, and stores them in your vector index for retrieval.

Yes. You can enable `include_resources=True` on your client to allow the agent to treat Firestore collections as native LlamaIndex data resources for direct querying.

Yes, using the `fcm_send_message` tool. When an index query detects an anomaly or a specific threshold, the agent constructs and sends a push notification payload immediately.

Your Firestore documents and Realtime DB JSON payloads pass through our MCP architecture's zero-trust, ephemeral V8 sandbox. No data is cached or stored on Vinkius servers, and all database interactions occur over encrypted HTTPS connections using your credentials.

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