How to Use the Amazon S3 Bucket MCP in Google ADK

Q: How do I filter files during a directory listing?

The listobjects tool accepts prefix and delimiter arguments. Your agent uses these to search specific folders rather than dumping the entire bucket contents at once.

Give your Google ADK agents scoped read and write access to a specific S3 bucket right from your Gemini workflows via MCP.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amazon S3 Bucket MCP to Google ADK

Create your Vinkius account to connect Amazon S3 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 Amazon S3 Bucket with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed S3 objects into Gemini's context

Enterprise agents run on massive datasets. When you hook this MCP Server into your Google Cloud environment, your Gemini model can pull raw files straight from S3. The massive token window means your agent can ingest dozens of documents at once. A typical workflow starts with `list_objects` to find relevant files based on a prefix delimiter. The agent then loops through `get_object_data` to dump text, JSON, or CSV content directly into the prompt for reasoning alongside your BigQuery data.

Output artifacts via Google ADK

Processing data requires a place to store the results. After your Gemini agent finishes crunching numbers or generating summaries, it pushes the output back to AWS storage. You avoid building custom upload scripts or staging areas. The agent formats the final artifact and fires `put_object` to save it. If the job involves cleaning up old inputs, it triggers `delete_object` right after the upload completes. You manage the exposed MCP tools using the tool_names filter in your McpToolset setup.

Verify bucket access rules on the fly

Cross-cloud operations often hit permission snags. Before attempting a large data transfer, your agent can inspect the destination's security posture. It reads the raw rules to confirm write access exists. Executing `get_bucket_policy` and `get_bucket_acl` returns the exact IAM configurations for the target bucket. If the policy denies writes from your current service account, the agent can alert an admin instead of failing silently mid-upload.

Setup guide

Set up Amazon S3 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 Amazon S3 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="Amazon S3 Bucket_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Amazon S3 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 Amazon S3 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 Amazon S3 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 Amazon S3 Bucket MCP in Google ADK

Install the google-adk package. Initialize an McpToolset with your Vinkius HTTP endpoint URL, and pass it to your LlmAgent in the tools list.

Gemini handles massive context windows, but you still need to be careful with raw file sizes. Have your agent check get_object_metadata first before pulling the full payload.

You can filter the exact tools exposed to the agent. Use the tool_names parameter in your McpToolset configuration to hide destructive actions like delete_object.

The list_objects tool accepts prefix and delimiter arguments. Your agent uses these to search specific folders rather than dumping the entire bucket contents at once.

We use ephemeral sandboxing for all connections. When your agent pulls object content or bucket ACLs, the session data exists only in memory and vanishes the second the task finishes.

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