How to Use the Google Firestore Collection MCP in Google ADK

Q: How do I connect Google Firestore Collection to Google ADK?

Install the package using pip install google-adk and configure McpToolset with your Vinkius HTTP URL. Pass that toolset into your LlmAgent tools array to let Gemini discover the database tools.

Q: Can I limit which Google Firestore Collection tools the Google ADK agent can access?

Yes, you can pass a list of allowed tool names to your McpToolset instance. If you want a read-only agent, simply omit setdocument and deletedocument from the allowed list.

Give your Google ADK enterprise agents direct access to Firestore documents in seconds.

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 Google ADK

Create your Vinkius account to connect Google Firestore Collection to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Direct document reads for Gemini agents

This MCP server exposes `get_document` to let your Gemini-powered agents fetch NoSQL records on demand. You don't need to write boilerplate API calls or handle complex Google Cloud authentication in your code. Your agent reads the document and uses the data directly in its reasoning loop. This works perfectly with Gemini's long-context window, letting the agent analyze large document payloads easily.

Real-time updates via this Firestore MCP Server

This MCP Server enables your agents to modify or create records instantly using `set_document`. When your agent finishes a task, it writes the result directly to your Firestore collection. This makes it easy to sync agent decisions with your existing Google Cloud infrastructure. Your BigQuery pipelines can ingest these updates immediately without extra glue code.

Targeted record purging

The `delete_document` tool on this MCP server gives your agent the ability to remove specific documents when they are no longer relevant. This keeps your collections clean and prevents your NoSQL database from bloating with temporary agent data. You can restrict this tool using the ADK's native tool filters if you want to prevent accidental deletions. The agent only invokes it when explicit conditions are met.

Setup guide

Set up Google Firestore Collection MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Google Firestore Collection tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Google Firestore Collection_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Google Firestore Collection tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install the package using `pip install google-adk` and configure `McpToolset` with your Vinkius HTTP URL. Pass that toolset into your `LlmAgent` tools array to let Gemini discover the database tools.

Yes, you can pass a list of allowed tool names to your `McpToolset` instance. If you want a read-only agent, simply omit `set_document` and `delete_document` from the allowed list.

This MCP Server runs in an isolated sandbox and uses a standardized protocol, making it easier to test locally. It avoids the complex setup and deployment cycles required by traditional Vertex AI extensions.

Yes, the ADK supports both transport methods. For production deployments on Google Cloud, we recommend using the Streamable HTTP transport to connect your MCP tools.

Data processing happens inside an ephemeral, zero-trust V8 sandbox managed by Vinkius. Your database records are never persisted on our servers, and transport encryption secures every transaction.

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