How to Use the Google Cloud Storage Bucket MCP in Google ADK

Q: How do I initialize a Google Cloud Storage Bucket connection in Google ADK?

Use the McpToolset class with the server's HTTP endpoint. Pass this toolset into your LlmAgent constructor to expose the storage tools to your Gemini model.

Connect your Google Cloud Storage Bucket directly to Gemini models using the Google ADK framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Google Cloud Storage Bucket MCP to Google ADK

Create your Vinkius account to connect Google Cloud Storage Bucket 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 Cloud Storage Bucket with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Native Gemini context feeding via MCP Server

Gemini models in the Google ADK thrive on massive contexts, and this MCP Server lets them ingest files directly. By invoking `get_object`, your agent pulls text or code files straight from your Google Cloud Storage Bucket into the 1M+ token window. This eliminates the need to build custom GCP storage connectors in Python. Your Gemini-powered Google ADK agent simply requests the file contents when the conversation requires deeper background knowledge.

BigQuery results archiving from Gemini runs

Save structured analysis directly to your Google Cloud Storage Bucket during active Google ADK sessions. Your agent can run `put_object` to store raw CSV or JSON outputs generated from BigQuery queries. Keeping these outputs in a central Google Cloud Storage Bucket makes them instantly available for downstream Google ADK processing. You don't have to manage local file paths or write complex export routines in your agent code.

Dynamic directory scanning for enterprise agents

Let your Google ADK agent discover new data files autonomously. Running `list_objects` returns a clean list of file metadata from your Google Cloud Storage Bucket, allowing Gemini to decide which file to analyze next. If a file is no longer needed, the Google ADK agent can call `delete_object` to keep the directory clean. This creates an autonomous feedback loop where the Gemini model manages its own workspace.

Setup guide

Set up Google Cloud Storage Bucket 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 Cloud Storage Bucket 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 Cloud Storage Bucket_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Google Cloud Storage Bucket 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 Cloud Storage Bucket. 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 Cloud Storage Bucket 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 Cloud Storage Bucket MCP in Google ADK

Use the `McpToolset` class with the server's HTTP endpoint. Pass this toolset into your `LlmAgent` constructor to expose the storage tools to your Gemini model.

Yes, you can use the optional tool names filter during initialization to restrict access. For example, you can expose `list_objects` while completely hiding the delete tool.

Yes, it supports both. We recommend using the HTTP transport option for cloud-hosted agent deployments to ensure stable, long-running connections.

While Gemini handles massive contexts, downloading huge files via `get_object` can hit memory limits. We suggest keeping your bucket objects under 100MB to avoid buffering issues.

Yes, because the MCP Server operates inside a zero-trust sandbox. Your file payloads and object metadata are never logged or stored on Vinkius, keeping your enterprise data strictly private.

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