How to Use the UpCloud MCP in Google ADK

Q: What if I need to check billing information with UpCloud using the Google ADK?

The agent calls getbillingsummary, retrieving your monthly costs. This data can then be passed into BigQuery for deeper, long-context analysis alongside other business metrics.

Q: Does the Google ADK help manage UpCloud resources?

Absolutely. You use tools like updateserver or deleteserver. The framework supports Stdio and HTTP transports, making it easy to embed these actions into existing Google Cloud pipelines.

Run enterprise cloud operations with Google ADK on UpCloud MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect UpCloud MCP to Google ADK

Create your Vinkius account to connect UpCloud 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 UpCloud with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Provisioning Complex Infrastructure

Building a multi-tier app? You can provision the whole stack. First, you make an SDN private network using `create_network`, then launch servers with `create_server`, and finally protect it all with a firewall rule via `create_firewall_rule`. The long context window of Gemini models allows your agent to hold the entire deployment plan in memory while executing these steps, keeping track of dependencies across multiple tools.

Retrieving and Analyzing Account Data

The agent can gather all necessary account data. Need host details? Use `get_host`. Want to see what IPs are available? Call `list_ips`. Since your workflow involves BigQuery, the Google ADK lets you pass these retrieved metrics—like listing routers (`list_routers`)—directly for further analysis in your data warehouse.

Managing Identity and Access

Security starts with control. You can create new API tokens using `create_api_token` or list all existing ones with `list_api_tokens`. If you need to change who has access, you use the specific tools provided. The Google ADK's enterprise focus means it treats every token and credential (`get_kubernetes_kubeconfig`) as a critical asset requiring detailed context-aware handling.

Setup guide

Set up UpCloud 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 UpCloud 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="UpCloud_agent",
    model="gemini-2.0-flash",
    instruction="You have access to UpCloud 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 UpCloud. 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 UpCloud 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 UpCloud MCP in Google ADK

The MCP Server exposes all its tools to your LlmAgent. Because you're building enterprise agents, the Google ADK supports native integration for passing operational data directly into BigQuery.

Yes. You can plan deployments by first listing available zones (`list_zones`) and then creating a managed load balancer using `create_load_balancer`. The model maintains this complex state across steps.

The agent calls `get_billing_summary`, retrieving your monthly costs. This data can then be passed into BigQuery for deeper, long-context analysis alongside other business metrics.

Absolutely. You use tools like `update_server` or `delete_server`. The framework supports Stdio and HTTP transports, making it easy to embed these actions into existing Google Cloud pipelines.

The server handles account audit logs. The long context capability allows your agent to process and analyze this sensitive audit log data alongside other enterprise information in BigQuery.

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