How to Use the UPYUN Developer Platform MCP in Google ADK

Q: How does Google ADK use the UPYUN Developer Platform for asset management?

The agent uses tools like listdirectory and getfileinfo to gather structured information about your assets. This metadata is then passed into Gemini's large context window, giving it full visibility over external resources.

Q: What process does the UPYUN Developer Platform follow when Google ADK creates a file?

When createtextfile runs, the data is securely uploaded to your UPYUN bucket. The agent receives confirmation and structured metadata immediately after the action completes.

Q: Does the MCP Server guarantee reliable usage metrics when paired with Google ADK?

Yes. The getserviceusage tool provides direct, verifiable metrics about your UPYUN bucket consumption. This allows you to build cost-aware agents that factor cloud spending into their logic.

Q: If I need to check asset status using the UPYUN Developer Platform with Google ADK, what tools do I use?

You should use getfileinfo to confirm a specific file's metadata or listdirectory if you need an overview of all assets in a given path.

Act on UPYUN Cloud Data Streams with Google ADK for Enterprise Agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect UPYUN Developer Platform MCP to Google ADK

Create your Vinkius account to connect UPYUN Developer Platform 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 UPYUN Developer Platform with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Examine Assets using the MCP Server in Google ADK

Before running complex queries against BigQuery, your agent can call `list_directory` to confirm asset existence within UPYUN. This confirms that the necessary files or directories are present for data ingestion. This capability allows you to build reliable pipelines where cloud assets must be verified before any heavy computation begins.

Get Detailed Asset Information via Google ADK

`get_file_info` provides detailed metadata about UPYUN files, including their size and last modified date. This data enriches the context available to Gemini models before they generate a response. If you need to update or create new source material for your agent's reasoning, `create_text_file` lets it write content directly to UPYUN.

Audit Cloud Infrastructure with the MCP Server

`get_service_usage` gives an immediate snapshot of your total UPYUN bucket service usage. This is critical for long-context agents that need to factor cost and capacity into their operational plans. Furthermore, using `delete_file` allows the agent to manage its own cloud environment by safely purging outdated or unnecessary assets.

Setup guide

Set up UPYUN Developer Platform 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 UPYUN Developer Platform 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="UPYUN Developer Platform_agent",
    model="gemini-2.0-flash",
    instruction="You have access to UPYUN Developer Platform 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 UPYUN. 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 UPYUN Developer Platform 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 UPYUN Developer Platform MCP in Google ADK

The agent uses tools like `list_directory` and `get_file_info` to gather structured information about your assets. This metadata is then passed into Gemini's large context window, giving it full visibility over external resources.

When `create_text_file` runs, the data is securely uploaded to your UPYUN bucket. The agent receives confirmation and structured metadata immediately after the action completes.

Yes. The `get_service_usage` tool provides direct, verifiable metrics about your UPYUN bucket consumption. This allows you to build cost-aware agents that factor cloud spending into their logic.

It accesses file metadata, directory structures, and service usage metrics. All returned data is structured for optimal use within BigQuery and Vertex AI workflows.

You should use `get_file_info` to confirm a specific file's metadata or `list_directory` if you need an overview of all assets in a given path.

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